evomo.problems.constrained

class evomo.problems.constrained.CTP1(m=2, d=5, **kwargs)#

Bases: CTP

CTP1 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP2(m=2, d=5, **kwargs)#

Bases: CTP

CTP2 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP3(m=2, d=5, **kwargs)#

Bases: CTP

CTP3 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP4(m=2, d=5, **kwargs)#

Bases: CTP

CTP4 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP5(m=2, d=5, **kwargs)#

Bases: CTP

CTP5 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP6(m=2, d=5, **kwargs)#

Bases: CTP

CTP6 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP7(m=2, d=5, **kwargs)#

Bases: CTP

CTP7 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.CTP8(m=2, d=5, **kwargs)#

Bases: CTP

CTP8 constrained multiobjective optimization problem.

pf()#

class evomo.problems.constrained.DASCMOP1(d=30, m=2, n_iq=11, ref_num=1000, difficulty=torch.tensor([0, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

constraints(X: torch.Tensor, g: torch.Tensor, f0: torch.Tensor | None = None, f1: torch.Tensor | None = None)#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP2(d=30, m=2, n_iq=11, ref_num=1000, difficulty=torch.tensor([0, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP1

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP3(difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP1

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP4(difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP1

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP5(difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP1

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP6(difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP1

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP7(d=30, m=3, n_iq=7, ref_num=1000, difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

constraints(X: torch.Tensor, g: torch.Tensor, f0: torch.Tensor, f1: torch.Tensor, f2: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP8(d=30, m=3, n_iq=7, ref_num=1000, difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP7

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

objectives(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DASCMOP9(d=30, m=3, n_iq=7, ref_num=1000, difficulty=torch.tensor([0.5, 0.5, 0.5]), **kwargs)#

Bases: DASCMOP8

The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.

Z. Fan, W. Li, X. Cai, H. Li, C. Wei, Q. Zhang, K. Deb, and E. Goodman, Difficulty adjustable and scalable constrained multi-objective test problem toolkit, Evolutionary Computation, 2020, 28(3): 339-378.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

fn(X: torch.Tensor) → torch.Tensor#

class evomo.problems.constrained.DOC1(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

Z. Liu and Y. Wang, Handling constrained multiobjective optimization problems with constraints in both the decision and objective spaces. IEEE Transactions on Evolutionary Computation, 2019, 23(5): 870-884.

m = 2#

d = 6#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC2(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 16#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC3(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 10#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC4(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 8#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC5(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 8#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC6(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 11#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC7(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 2#

d = 11#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC8(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 3#

d = 10#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.DOC9(ref_num: int = 1000, **kwargs)#

Bases: evomo.problems.constrained.base.CMOP

m = 3#

d = 11#

lower#

upper#

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.FCP1(d: int = 30, ref_num: int = 1000, **kwargs)#

Bases: FCP

J. Yuan, H. Liu, Y. Ong, and Z. He, Indicator-based evolutionary algorithm for solving constrained multi-objective optimization problems, IEEE Transactions on Evolutionary Computation, 2022, 26(2): 379-391.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.FCP2(d: int = 30, ref_num: int = 1000, **kwargs)#

Bases: FCP

J. Yuan, H. Liu, Y. Ong, and Z. He, Indicator-based evolutionary algorithm for solving constrained multi-objective optimization problems, IEEE Transactions on Evolutionary Computation, 2022, 26(2): 379-391.

fn(X: torch.Tensor) → torch.Tensor#

pf() → torch.Tensor#

class evomo.problems.constrained.FCP3(d: int = 30, ref_num: int = 1000, **kwargs)#

Bases: FCP

J. Yuan, H. Liu, Y. Ong, and Z. He, Indicator-based evolutionary algorithm for solving constrained multi-objective optimization problems, IEEE Transactions on Evolutionary Computation, 2022, 26(2): 379-391.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.FCP4(d: int = 30, ref_num: int = 1000, **kwargs)#

Bases: FCP

J. Yuan, H. Liu, Y. Ong, and Z. He, Indicator-based evolutionary algorithm for solving constrained multi-objective optimization problems, IEEE Transactions on Evolutionary Computation, 2022, 26(2): 379-391.

fn(X: torch.Tensor) → torch.Tensor#

pf() → torch.Tensor#

class evomo.problems.constrained.FCP5(d: int = 30, ref_num: int = 1000, **kwargs)#

Bases: FCP

J. Yuan, H. Liu, Y. Ong, and Z. He, Indicator-based evolutionary algorithm for solving constrained multi-objective optimization problems, IEEE Transactions on Evolutionary Computation, 2022, 26(2): 379-391.

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP1(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

g1(X: torch.Tensor) → torch.Tensor#

g2(X: torch.Tensor) → torch.Tensor#

f1(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

f2(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

c(g: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP2(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP1

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

f2(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP3(d: int = 30, m: int = 2, n_iq: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP1

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

c3(X: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP4(d: int = 30, m: int = 2, n_iq: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP2

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

c3(X: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP5(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, cons_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

cons_params = None#

g1(X: torch.Tensor) → torch.Tensor#

g2(X: torch.Tensor) → torch.Tensor#

f1(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

f2(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

c(f1: torch.Tensor, f2: torch.Tensor, params: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP6(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, cons_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP5

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

cons_params = None#

f2(X, g)#

pf()#

class evomo.problems.constrained.LIRCMOP7(d: int = 30, m: int = 2, n_iq: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP5

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

pf()#

class evomo.problems.constrained.LIRCMOP8(d: int = 30, m: int = 2, n_iq: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP6

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

pf()#

class evomo.problems.constrained.LIRCMOP9(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, c1_params: torch.Tensor | None = None, c2_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP5

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

c1_params = None#

c2_params = None#

f1(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

f2(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

c1(f1: torch.Tensor, f2: torch.Tensor, params: torch.Tensor) → torch.Tensor#

c2(f1: torch.Tensor, f2: torch.Tensor, params: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP10(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, c1_params: torch.Tensor | None = None, c2_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP9

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

c1_params = None#

c2_params = None#

f2(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP11(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, c1_params: torch.Tensor | None = None, c2_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP10

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

pf()#

class evomo.problems.constrained.LIRCMOP12(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, c1_params: torch.Tensor | None = None, c2_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP9

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

pf()#

class evomo.problems.constrained.LIRCMOP13(d: int = 30, m: int = 3, n_iq: int = 2, ref_num: int = 1000, cons_params: torch.Tensor | None = None, **kwargs)#

Bases: LIRCMOP

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

cons_params = None#

g(X: torch.Tensor) → torch.Tensor#

f123(X: torch.Tensor, g: torch.Tensor) → torch.Tensor#

c(f1: torch.Tensor, f2: torch.Tensor, f3: torch.Tensor, params: torch.Tensor) → torch.Tensor#

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.LIRCMOP14(d: int = 30, m: int = 2, n_iq: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LIRCMOP13

Constrained benchmark MOP with large infeasible regions.

Z. Fan, W. Li, X. Cai, H. Huang, Y. Fang, Y. You, J. Mo, C. Wei, and E. Goodman, An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions, Soft Computing, 2019, 23: 12491-12510.

Parameters:

d – Number of decision variables.
m – Number of objectives.
n_iq – Number of inequality constraints.
n_eq – Number of equality constraints.
ref_num – Number of reference points used in the problem.

pf()#

class evomo.problems.constrained.LSCM1(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM2(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM3(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM4(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM5(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM6(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM7(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM8(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM9(d: int = 100, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM10(d: int = 100, m: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM11(d: int = 100, m: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.LSCM12(d: int = 100, m: int = 3, ref_num: int = 1000, **kwargs)#

Bases: LSCM

K. Qiao, J. Liang, K. Yu, W. Guo, C. Yue, B. Qu, and P. N. Suganthan. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm and Evolutionary Computation, 2024, 86: 101504.

ku_index = 1: index of LSCM function base: the dimension of each segment duan: the number of segments DCT: the form of unconstraint variable linkage CCT: the form of constraint variable linkage Dis_function: index of distance functions Q_form: index of Q functions PF_form: index of PF functions CEC_Problem: index of constraint functions lu: upper and lower bounds of constraint functions high_D_C: dimensions of constraint functions aaa: used for constraint functions optimal_f: optimal objective values of constraint functions

nk: Number of subcomponents in each subset sublen: Number of variables in each subset len: Cumulative sum of lengths of variable groups

CV: store the index of constaint variables Dis: store the index of distance function variables

h: objective function value of constraint function HC: constraint function value of constraint function

class evomo.problems.constrained.MW1(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW2(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW3(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW4(d=10, m=3, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW5(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW6(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW7(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW8(d=10, m=3, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW9(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW10(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW11(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW12(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW13(m=2, d=10, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.MW14(d=10, m=3, ref_num: int = 1000, **kwargs)#

Bases: MW

Base class for Constrained Multi-objective Optimization Problems (CMOP).

fn(X: torch.Tensor) → torch.Tensor#

pf()#

class evomo.problems.constrained.SDC1(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

class evomo.problems.constrained.SDC2(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

class evomo.problems.constrained.SDC3(info_idx=3, d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

pf()#

class evomo.problems.constrained.SDC4(info_idx=4, d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

pf()#

class evomo.problems.constrained.SDC5(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC3

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC6(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC4

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC7(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC8(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC9(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC3

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC10(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC4

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC11(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC3

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC12(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC4

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC13(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC4

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC14(d: int = 30, m: int = 2, ref_num: int = 1000, **kwargs)#

Bases: SDC3

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

class evomo.problems.constrained.SDC15(d: int = 30, m: int = 3, ref_num: int = 1000, **kwargs)#

Bases: SDC

Scalable high-dimensional decicsion constraint benchamrk

K. Qiao, J. Liang, K. Yu, C. Yue, H. Lin, D. Zhang, and B. Qu. Evolutionary constrained multiobjective optimization: scalable high-dimensional constraint benchmarks and algorithm. IEEE Transactions on Evolutionary Computation, 2024, 28(4): 965-979.

param: THETA_ a CEC_Problem: index of high-dimension constraint function Distance_problem: index of distance function HCT: rate of unconstrained distance function variables that are used for high-dimensional constraint function HCT_type: type of transformation function DCT: rate of unconstrained distance function variables that are used for variable linkage DCT_type: type of variable linkage function Shape_problem: tyep of shape function b: a parameter of shape function that is used to control the overlap degree between CPF and UPF lu: upper and lower bounds of high-dimensional constraint function high_D_C: dimensions of high-dimensional constraint function aaa: used for high-dimensional constraint function optial_f: optimal objective value of high-dimensional constraints q1_upper: upper bound of shape function q1_lower:lower bound of shape function h: objective function value of high-dimensional constraint function HC: constraint function value of high-dimensional constraint function max_D_con: maximal number of variables that are used for transformation operator

ref_num = 1000#

fn(X: torch.Tensor) → torch.Tensor#: Return: [F1, F2, F3, c1, c2, HC] with shape (N, 6) - F*: 3 objectives (M=3) - c1,c2: shape constraints from SDC15 - HC: aggregated high-dimensional constraint violation from CEC_2006

`CTP1`	CTP1 constrained multiobjective optimization problem.
`CTP2`	CTP2 constrained multiobjective optimization problem.
`CTP3`	CTP3 constrained multiobjective optimization problem.
`CTP4`	CTP4 constrained multiobjective optimization problem.
`CTP5`	CTP5 constrained multiobjective optimization problem.
`CTP6`	CTP6 constrained multiobjective optimization problem.
`CTP7`	CTP7 constrained multiobjective optimization problem.
`CTP8`	CTP8 constrained multiobjective optimization problem.
`DASCMOP1`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP2`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP3`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP4`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP5`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP6`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP7`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP8`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DASCMOP9`	The DASCMOP test suite generator of constrained multibjecitve problems DASCMOP1-DASCMOP9.
`DOC1`
`DOC2`
`DOC3`
`DOC4`
`DOC5`
`DOC6`
`DOC7`
`DOC8`
`DOC9`
`FCP1`
`FCP2`
`FCP3`
`FCP4`
`FCP5`
`LIRCMOP1`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP2`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP3`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP4`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP5`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP6`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP7`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP8`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP9`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP10`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP11`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP12`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP13`	Constrained benchmark MOP with large infeasible regions.
`LIRCMOP14`	Constrained benchmark MOP with large infeasible regions.
`LSCM1`
`LSCM2`
`LSCM3`
`LSCM4`
`LSCM5`
`LSCM6`
`LSCM7`
`LSCM8`
`LSCM9`
`LSCM10`
`LSCM11`
`LSCM12`
`MW1`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW2`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW3`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW4`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW5`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW6`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW7`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW8`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW9`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW10`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW11`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW12`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW13`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`MW14`	Base class for Constrained Multi-objective Optimization Problems (CMOP).
`SDC1`	Scalable high-dimensional decicsion constraint benchamrk
`SDC2`	Scalable high-dimensional decicsion constraint benchamrk
`SDC3`	Scalable high-dimensional decicsion constraint benchamrk
`SDC4`	Scalable high-dimensional decicsion constraint benchamrk
`SDC5`	Scalable high-dimensional decicsion constraint benchamrk
`SDC6`	Scalable high-dimensional decicsion constraint benchamrk
`SDC7`	Scalable high-dimensional decicsion constraint benchamrk
`SDC8`	Scalable high-dimensional decicsion constraint benchamrk
`SDC9`	Scalable high-dimensional decicsion constraint benchamrk
`SDC10`	Scalable high-dimensional decicsion constraint benchamrk
`SDC11`	Scalable high-dimensional decicsion constraint benchamrk
`SDC12`	Scalable high-dimensional decicsion constraint benchamrk
`SDC13`	Scalable high-dimensional decicsion constraint benchamrk
`SDC14`	Scalable high-dimensional decicsion constraint benchamrk
`SDC15`	Scalable high-dimensional decicsion constraint benchamrk

evomo.problems.constrained#

Submodules#

Classes#

Package Contents#