Social optimization algorithm with application to economic dispatch problem

Abstract

Summary In this paper, a new population‐based meta‐heuristic algorithm called Social Optimization Algorithm (SOA) is proposed. This algorithm has been inspired by the social behavior of human‐beings, and mimics an ideal justly‐established society where the two principles of justice, that is, equality of opportunity and community principles are meticulously followed. Reaching goals in such a society is optimally achieved. Although a real fully‐just society does not exist in the real world, we implement the principles in such ideal societies through simulations to introduce our new optimization algorithm. The advantage of the proposed method is that it does not have any algorithm‐specified parameters to be set. This is a great merit compared to similar meta‐heuristics. The algorithm has been simulated on 23 well‐known test functions, and the results have been compared with those produced by Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA) and Differential Evolution (DE). In 57% of the 23 cases SOA yields superior results. The algorithm has also been tested on five other benchmark functions to be compared with Teaching‐Learning‐Based Optimization (TLBO) and Artificial Bee Colony (ABC).The results provide evidence for efficient performance with superior solution quality of the proposed algorithm in solving benchmark problems. To further illustrate the effectiveness of the proposed algorithm, it has been tested on the Economic Dispatch problem as a real‐world constrained optimization problem. The results have been compared with Biogeography‐Based Optimizer (BBO), Harmony Search (HS) and PSO. The results show that the SOA is able to produce very competitive results compared to other well‐known meta‐heuristic algorithms. Meta‐heuristic, SOA, Economic Dispatch.

FSOA‐DNFNet: Incremental indexing and image classification using hybrid optimization‐based deep neuro Fuzzy network

“…Once matching is done, the cluster centroid is updated then the cluster information based on features is passed through image classification, which is performed using the deep neuro fuzzy network 28 . However, training of network classifier is performed using developed FSOA, which is obtained by integrating Feedback Artificial Tree (FAT) 29 Algorithm, and Social Optimization Algorithm (SOA) 30 . Furthermore, dynamic classification is done using weight bounding decision based on error condition.…”

“…28 However, training of network classifier is performed using developed FSOA, which is obtained by integrating Feedback Artificial Tree (FAT) 29 Algorithm, and Social Optimization Algorithm (SOA). 30 Furthermore, dynamic classification is done using weight bounding decision based on error condition. This is the new hybrid algorithm that is being proposed in this work.…”

“…The Deep Neuro optimizer is trained using the proposed FSOA, which is derived by integrating the features of FAT 29 Algorithm and SOA. 30 SOA is a population-based meta-heuristic that inspires the social behavior of human-beings and imitates the two concepts of justice, such as equality of opportunity and principle of community. The major benefit of SOA is that it does not have any algorithm-specified factors to be set.…”

Improved Gradient-Based Optimizer for Modelling Thermal and Hydropower Plants

“…e proposed IGBO technique competence and ability are tested on the numerous benchmark functions, using the statistical measurement including the minimum values, mean values, median values, maximum values, and standard deviation (STD) for optimal solutions attained using the IGBO technique and the other recent algorithms. e data of the 23 benchmark functions are taken from [35]. e results achieved with the IGBO technique are compared with five recent techniques, hunter-prey optimization (HPO) [36], whale optimization algorithm (WOA) [37], supply demand-based optimization (SDO) [38], grey wolf optimizer (GWO) [39], and the original (GBO).…”

Application of chaotic quasi‐oppositional whale optimization algorithm on CHPED problem integrated with wind‐solar‐EVs

“…Ponnuvel et al 36 addressed the multiobjective squirrel search algorithm to analyze combined economic and environmental power dispatch (CEEPD), where renovate strategy and selection rules were utilized in the proposed method of efficiently handle the CEEPD constraints. The social optimization algorithm, which is independent on algorithm‐specified parameters, had been proposed by Karimi and Khandani 37 to analyze the ELD problem for optimal solution. Parouha and Verma 38 utilized an hybrid algorithm to solve the ELD problem with and without valve point loading.…”