An improved differential evolution algorithm with fitness-based adaptation of the control parameters
Introduction
The Differential Evolution (DE) [21], [29], [27], [28] algorithm emerged as a very competitive form of evolutionary computing more than a decade ago. The first written article on DE appeared as a technical report by Storn and Price in 1995 [27]. One year later, the success of DE was demonstrated at the First International Contest on Evolutionary Optimization in May 1996, which was held in conjunction with the 1996 IEEE International Conference on Evolutionary Computation [28] (the first two places were given to non-evolutionary algorithms, which are not universally applicable but solved the test-problems faster than DE). Comprehensive surveys on the recent research on and with DE can be found in [6], [19].
In the DE community, the individual trial solutions (which constitute a population) are called parameter vectors or genomes. DE operates through the same computational steps as employed by a standard EA. However, unlike traditional EAs, DE employs difference of the parameter vectors to explore the objective function landscape. In this respect, it owes a lot to its two ancestors namely – the Nelder–Mead algorithm [17], and the Controlled Random Search (CRS) algorithm [22], which also relied heavily on the difference vectors to perturb the current trial solutions. Like other population-based search techniques, DE generates new points (trial solutions) that are perturbations of existing points, but these deviations are neither reflections like those in the CRS and Nelder–Mead methods, nor samples from a predefined probability density function, like those in Evolutionary Strategies (ES) [25]. Instead, DE perturbs current generation vectors with the scaled difference of two randomly selected population vectors. In its simplest form, DE adds the scaled, random vector difference to a third randomly selected population vector to create a donor vector corresponding to each population vector (also known as target vector). Next the components of the target and donor vectors are mixed through a crossover operation to produce a trial vector. In the selection stage, the trial (or offspring) vector competes against the population vector of the same index, i.e. the parent vector. Once the last trial vector has been tested the survivors of all the pair wise competitions become parents for the next generation in the evolutionary cycle.
The performance of DE is severely dependent on two of its most important control parameters: The crossover rate (Cr) and scale factor (F) [21]. Over the past decade many claims and counter-claims have been reported regarding the tuning and adaptation strategies of these control parameters. Some objective functions are very sensitive to the proper choice of the parameter settings in DE [13]. Therefore, researchers naturally started to consider some techniques to automatically find an optimal set of control parameters for DE [23], [2], [11], [12], [26], [1]. The most recent trend in this direction is the use of self-adaptive strategies like the ones reported in [23], [2]. However, self-adaptation schemes usually make the programming fairly complex and run the risk of increasing the number of function evaluations. Recently in [15], Mininno and Neri suggested an efficient adaptation scheme for the control parameters of DE. In their scheme, the randomized scale factor and crossover rate values are sampled from truncated Gaussian probability distribution functions. In [32], Weber et al. proposed to regulate the choice of the scale factors for each individual of DE in a self-adaptive manner, based on their success on structured populations.
This article suggests a novel automatic tuning method for the scale factor and crossover rate of population members in DE, based on their individual objective function values. The key sense of this adaptation mechanism is that if a search-agent (DE-vector) moves near to the optimum, its mutation step-size decreases and during crossover, it passes more genetic information to its offspring (trial vector in DE terminology) in order to favor exploitation. However, if the agent moves away from the optima, then it is more perturbed and during DE-type crossover, the offspring inherits lesser genetic information from the parent, so that the agent may be able to explore alternate regions quickly. Our fitness-based parametric adaptation schemes attempt to achieve a better trade-off between the explorative and the exploitative tendencies of DE. From this perspective they are conceptually related to the fitness diversity adaptation used in Memetic Algorithms (MAs). Some significant research works that need mention in this context are [3], [4], [20], [30]. The fitness-adaptive DE algorithm has been compared with some of the recently developed and best-known DE-variants like jDE [2], SaDE [23], and JADE [36] over 14 numerical benchmarks taken from [10] and one engineering optimization problem involving spread-spectrum radar polyphase code design [16]. The results of such comparison indicate that DE with this very simple fitness-based adaptation scheme is able to meet or beat its nearest competitors in a statistically meaningful way.
The rest of the paper is organized in the following way: Section 2 outlines the conventional DE family of algorithms and introduces its control parameters. The new fitness value based adaptation strategy has been described in sufficient details under Section 3. Section 4 explains the experimental settings, presents the experimental results of comparison between the competitive DE-variants and discusses the implications of the results. Finally Section 5 concludes the paper.
Section snippets
Classical DE
DE is a simple real-coded evolutionary algorithm. It works through a simple cycle of stages, which are detailed below.
Fitness-based adaptations in DE
The successful functioning of DE is critically dependent upon its two major control parameters: F and Cr. As can be perceived from the literature, several claims and counter-claims have been reported concerning the choice of suitable values for these parameters such that the resulting DE may enjoy a statistically superior performance over a wide variety of objective functions. Price et al.. [21] defined two new terms: jitter and dither in context to the randomization of F. The practice of
Benchmark functions used
We have used a test-bed of fourteen well-known boundary-constrained benchmark functions [10], [23] to evaluate the performance of the new adaptive DE variant. Among the functions, f1 − f4 are unimodal and functions f5 − f14 are multimodal. These 14 test functions are dimension wise scalable. The functions are briefly described below:
- (1)
Shifted Sphere Function: :
- (2)
Shifted Schwefel’s Problem 1.2:
- (3)
Rosenbrock’s Function:
Conclusions
Over the past decade research on and with DE has reached an impressive state. However, the most competitive variants of DE are not as simple as the basic DE family proposed by Storn and Price, and require considerable programming efforts for implementation. In a few cases such DE-variants also demand huge storage capacity, e.g. over an optimization problem involving 1000 variables, the archive size in JADE may become very large to manage with limited memory and computational time. Keeping such
References (36)
- et al.
Population set based global optimization algorithms: some modifications and numerical studies
Computers and Operations Research
(2004) - et al.
Differential evolution in constrained numerical optimization: an empirical study
Information Sciences
(2010) - et al.
Solving spread-spectrum radar polyphase code design problem by tabu search and variable neighborhood search
European Journal of Operational Research
(2003) - et al.
Estimation of distribution and differential evolution cooperation for large scale economic load dispatch optimization of power systems
Information Sciences
(2010) - et al.
Self-adapting control parameters in differential evolution: a comparative study on numerical benchmark problems
IEEE Transactions on Evolutionary Computation
(2006) - et al.
A fast adaptive memetic algorithm for off-line and on-line control design of PMSM drives
IEEE Transactions on Systems, Man and Cybernetics – Part B
(2007) - et al.
Super-fit control adaptation in memetic differential evolution frameworks
Soft Computing – A Fusion of Foundations Methodologies and Applications
(2009) - et al.
Differential evolution using a neighborhood based mutation operator
IEEE Transactions on Evolutionary Computation
(2009) - et al.
Differential evolution: a survey of the state-of-the-art
IEEE Transactions on Evolutionary Computation
(2011) - S. Das, A. Konar, U.K. Chakraborty, Two improved differential evolution schemes for faster global search, in:...
On stability and convergence of the population-dynamics in differential evolution
AI Communications
A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behavior: a case study on the CEC’2005 special session on real parameter optimization
Journal of Heuristics
A Fuzzy adaptive differential evolution algorithm
Soft Computing – A Fusion of Foundations, Methodologies and Applications
Estimation distribution differential evolution
A simplex method for function minimization
Computer Journal
Cited by (147)
A Q-learning based multi-strategy integrated artificial bee colony algorithm with application in unmanned vehicle path planning
2024, Expert Systems with ApplicationsImproving the search accuracy of differential evolution by using the number of consecutive unsuccessful updates
2022, Knowledge-Based SystemsNeighborhood global learning based flower pollination algorithm and its application to unmanned aerial vehicle path planning
2021, Expert Systems with ApplicationsSelective-candidate framework with similarity selection rule for evolutionary optimization
2020, Swarm and Evolutionary ComputationDevelopments and Design of Differential Evolution Algorithm for Non-linear/Non-convex Engineering Optimization
2024, Archives of Computational Methods in Engineering