src.baseline.bbo.sahlpso

Module Contents

Classes

SAHLPSO

Introduction

Self-Adaptive two roles hybrid learn-ing strategies-based particle swarm optimization.It uses exploration-role and exploitation-role learning strategies with self-adaptively updating parameters manner.

API

class src.baseline.bbo.sahlpso.SAHLPSO(config)[source]

Bases: src.environment.optimizer.basic_optimizer.Basic_Optimizer

Introduction

Self-Adaptive two roles hybrid learn-ing strategies-based particle swarm optimization.It uses exploration-role and exploitation-role learning strategies with self-adaptively updating parameters manner.

Original paper

“Self-Adaptive two roles hybrid learning strategies-based particle swarm optimization.” Information Sciences 578 (2021): 457-481.

Initialization

Introduction

Initializes the SAHLPSO (Self-Adaptive Hybrid Learning Particle Swarm Optimization) algorithm with the provided configuration parameters.

Args:

- config (object): Configuration object containing algorithm parameters.
    - The Attributes needed for the SAHLPSO optimizer in config are the following:
        - maxFEs (int): Maximum number of function evaluations allowed.Default value depends on the type of the problem.
        - n_logpoint (int): Number of log points for tracking progress. Default is 50.
        - log_interval (int): Interval at which logs are recorded. Default is maxFEs // n_logpoint.
        - full_meta_data (bool): Flag indicating whether to store complete solution history. Default is False.
        - seed (int): Random seed for reproducibility. Used for initializing positions and velocities.

Attributes:

  • NP (int): Number of particles in the swarm (default: 40).

  • lb (float): Lower bound for particle positions (default: -5).

  • ub (float): Upper bound for particle positions (default: 5).

  • v_max (float): Maximum velocity for particles (default: 1).

  • H_cr (int): Number of crossover rates (default: 5).

  • M_cr (list of float): List of crossover rates.

  • H_ls (int): Number of local search strategies (default: 15).

  • M_ls (range): Range of local search strategies.

  • LP (int): Learning period (default: 5).

  • Lg (float): Learning gain (default: 0.2).

  • p (float): Probability parameter (default: 0.2).

  • c1 (float): Cognitive acceleration coefficient (default: 1.49445).

  • log_interval (int): Logging interval, taken from config.

  • full_meta_data (bool): Flag indicating whether to store full meta data, taken from config.

__str__()[source]

Introduction

Returns the string representation of the SAHLPSO class.

Returns:

  • str: The string ‘SAHLPSO’.

run_episode(problem)[source]

Introduction

Executes a single optimization episode using the Self-Adaptive History Learning Particle Swarm Optimization (SAHLPSO) algorithm on the provided problem instance. The method manages the population, velocity, and adaptive parameters, and logs the optimization progress.

Args:

  • problem (object): An optimization problem instance that must provide the following attributes and methods:

    • dim (int): Dimensionality of the problem.

    • lb (array-like): Lower bounds for each dimension.

    • ub (array-like): Upper bounds for each dimension.

    • optimum (float or None): Known optimum value for the problem (optional).

    • eval(X) (callable): Function to evaluate the fitness of a population X.

Returns:

  • dict: A dictionary containing:

    • ‘cost’ (list): The best cost (fitness) found at each logging interval.

    • ‘fes’ (int): The total number of function evaluations performed.

    • ‘metadata’ (dict, optional): If self.full_meta_data is True, includes:

      • ‘X’ (list): History of population positions.

      • ‘Cost’ (list): History of population costs.

Notes:

  • The method adapts crossover and learning strategies based on historical success rates.

  • Population size is dynamically reduced during the run.

  • Logging intervals and meta-data collection are controlled by the class configuration.