An Improved Population-Based Incremental Learning Algorithm

2013 ◽  
Vol 4 (1) ◽  
pp. 35-61 ◽  
Author(s):  
Komla A. Folly
Keyword(s):  
Incremental Learning ◽  
Optimization Problems ◽  
Learning Algorithm ◽  
Search Space ◽  
Population Based ◽  
Learning Rate ◽  
Parameters Optimization ◽  
New Class ◽  
System Controller ◽  
Better Than

Population-Based Incremental Learning (PBIL) is a relatively new class of Evolutionary Algorithms (EA) that has been recently applied to a range of optimization problems in engineering with promising results. PBIL combines aspects of Genetic Algorithm with competitive learning. The learning rate in the standard PBIL is generally fixed which makes it difficult for the algorithm to explore the search space effectively. In this paper, a PBIL with adapting learning rate is proposed. The Adaptive PBIL (APBIL) is able to thoroughly explore the search space at the start of the run and maintain the diversity consistently during the run longer than the standard PBIL. The proposed algorithm is validated by applying it to power system controller parameters optimization problem. Simulation results show that the Adaptive PBIL based controller performs better than the standard PBIL based controller, in particular under small disturbance.

scholarly journals Parallel Pbil Applied to Power System Controller Design

2013 ◽  
Vol 3 (3) ◽  
pp. 215-223 ◽  
Author(s):  
Komla Folly
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Power System ◽  
Incremental Learning ◽  
Controller Design ◽  
Population Based ◽  
Loss Of Diversity ◽  
System Controller ◽  
Two Populations ◽  
Better Than

Abstract Population-Based Incremental Learning (PBIL) algorithm is a combination of evolutionary optimization and competitive learning derived from artificial neural networks. PBIL has recently received increasing attention in various engineering fields due to its effectiveness, easy implementation and robustness. Despite these strengths, it was reported in the last few years that PBIL suffers from issues of loss of diversity in the population. To deal with this shortcoming, this paper uses parallel PBIL based on multi-population. In parallel PBIL, two populations are used where both probability vectors (PVs) are initialized to 0.5. It is believed that by introducing two populations, the diversity in the population can be increased and better results can be obtained. The approach is applied to power system controller design. Simulations results show that the parallel PBIL approach performs better than the standard PBIL and is as effective as another diversity increasing PBIL called adaptive PBIL

Modified Sub-Population Based Heat Transfer Search Algorithm for Structural Optimization

2017 ◽  
Vol 8 (3) ◽  
pp. 1-23 ◽  
Author(s):  
Ghanshyam Tejani ◽  
Vimal Savsani ◽  
Vivek Patel
Keyword(s):  
Heat Transfer ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Optimal Solution ◽  
Population Based ◽  
Truss Optimization ◽  
Feasible Region ◽  
Frequency Constraints ◽  
Local Optimal Solution ◽  
Better Than

In this study, a modified heat transfer search (MHTS) algorithm is proposed by incorporating sub-population based simultaneous heat transfer modes viz. conduction, convection, and radiation in the basic HTS algorithm. However, the basic HTS algorithm considers only one of the modes of heat transfer for each generation. The multiple natural frequency constraints in truss optimization problems can improve the dynamic behavior of the structure and prevent undesirable vibrations. However, shape and size variables subjected to frequency constraints are difficult to handle due to the complexity of its feasible region, which is non-linear, non-convex, implicit, and often converging to the local optimal solution. The viability and effectiveness of the HTS and MHTS algorithms are investigated by six standard trusses problems. The solutions illustrate that the MHTS algorithm performs better than the HTS algorithm.

Centroid Opposition-Based Differential Evolution

2014 ◽  
Vol 5 (4) ◽  
pp. 1-25 ◽  
Author(s):  
Shahryar Rahnamayan ◽  
Jude Jesuthasan ◽  
Farid Bourennani ◽  
Greg F. Naterer ◽  
Hojjat Salehinejad
Keyword(s):  
Differential Evolution ◽  
Optimization Problems ◽  
Extreme Points ◽  
Search Space ◽  
Population Based ◽  
Effective Population ◽  
Centroid Point ◽  
Opposite Point ◽  
Novel Concept ◽  
Multiple Variants

The capabilities of evolutionary algorithms (EAs) in solving nonlinear and non-convex optimization problems are significant. Differential evolution (DE) is an effective population-based EA, which has emerged as very competitive. Since its inception in 1995, multiple variants of DE have been proposed with higher performance. Among these DE variants, opposition-based differential evolution (ODE) established a novel concept in which individuals must compete with theirs opposites in order to make an entry in the next generation. The generation of opposite points is based on the current extreme points (i.e., maximum and minimum) in the search space. This paper develops a new scheme that utilizes the centroid point of a population to calculate opposite individuals. The classical scheme of an opposite point is modified. Incorporating this new scheme into DE leads to an enhanced ODE that is identified as centroid opposition-based differential evolution (CODE). The accuracy of the CODE algorithm is comprehensively evaluated on well-known complex benchmark functions and compared with the performance of conventional DE, ODE, and other state-of-the-art algorithms. The results for CODE are found to be promising.

scholarly journals A-DVM: A Self-Adaptive Variable Matrix Decision Variable Selection Scheme for Multimodal Problems

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 1004
Author(s):  
Marco Antonio Florenzano Mollinetti ◽  
Bernardo Bentes Gatto ◽  
Mário Tasso Ribeiro Serra Neto ◽  
Takahito Kuno
Keyword(s):  
Variable Selection ◽  
Optimization Problems ◽  
Search Space ◽  
Population Based ◽  
Decision Variable ◽  
Numerical Comparison ◽  
Binary Matrix ◽  
Selection Scheme ◽  
Original Algorithm ◽  
Self Adaptive

Artificial Bee Colony (ABC) is a Swarm Intelligence optimization algorithm well known for its versatility. The selection of decision variables to update is purely stochastic, incurring several issues to the local search capability of the ABC. To address these issues, a self-adaptive decision variable selection mechanism is proposed with the goal of balancing the degree of exploration and exploitation throughout the execution of the algorithm. This selection, named Adaptive Decision Variable Matrix (A-DVM), represents both stochastic and deterministic parameter selection in a binary matrix and regulates the extent of how much each selection is employed based on the estimation of the sparsity of the solutions in the search space. The influence of the proposed approach to performance and robustness of the original algorithm is validated by experimenting on 15 highly multimodal benchmark optimization problems. Numerical comparison on those problems is made against the ABC and their variants and prominent population-based algorithms (e.g., Particle Swarm Optimization and Differential Evolution). Results show an improvement in the performance of the algorithms with the A-DVM in the most challenging instances.

A diversity maintaining population-based incremental learning algorithm

2008 ◽  
Vol 178 (21) ◽  
pp. 4038-4056 ◽  
Author(s):  
Mario Ventresca ◽  
Hamid R. Tizhoosh
Keyword(s):  
Incremental Learning ◽  
Learning Algorithm ◽  
Population Based

Hybrid Harmony Search Algorithm for Global Optimization Problems

2014 ◽  
Vol 1065-1069 ◽  
pp. 3438-3441
Author(s):  
Guo Jun Li
Keyword(s):  
Global Optimization ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Harmony Search ◽  
Population Based ◽  
Harmony Search Algorithm ◽  
Search Method ◽  
Local Optima ◽  
Population Based Algorithm ◽  
Better Than

Harmony search (HS) algorithm is a new population based algorithm, which imitates the phenomenon of musical improvisation process. Its own potential and shortage, one shortage is that it easily trapped into local optima. In this paper, a hybrid harmony search algorithm (HHS) is proposed based on the conception of swarm intelligence. HHS employed a local search method to replace the pitch adjusting operation, and designed an elitist preservation strategy to modify the selection operation. Experiment results demonstrated that the proposed method performs much better than the HS and its improved algorithms (IHS, GHS and NGHS).

Sign in / Sign up

Export Citation Format

Share Document