An improved meta-heuristic method to maximize the penetration of distributed generation in radial distribution networks

• Published in: Neural computing & applications Vol. 32; no. 14; pp. 10159 - 10181
• Main Authors: Truong, Khoa Hoang, Nallagownden, Perumal, Elamvazuthi, Irraivan, Vo, Dieu Ngoc
• Format: Journal Article
• Language: English
• Published: London Springer London 01-07-2020; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Distributed generation; Heuristic; Heuristic methods; Image Processing and Computer Vision; Machine learning; Networks; Original Article; Penetration; Power factor; Power loss; Probability and Statistics in Computer Science; Radial distribution; Searching; Unity; Optimal power factor; Quasi-oppositional; Distributed generation; Power loss reduction; Symbiotic organisms search; Optimal placement
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-019-04548-4

This paper proposes a novel scheme based on an improved meta-heuristic method to determine the optimal number of distributed generation (DG) units to be installed in distribution networks for maximum DG penetration. The proposed meta-heuristic method is the quasi-oppositional chaotic symbiotic organisms search (QOCSOS) algorithm, which is the improved version of the original SOS algorithm. QOCSOS integrates two search strategies including quasi-opposition-based learning and chaotic local search into SOS to achieve better performance. In this study, QOCSOS was implemented to find the optimal number, location, size, and power factor of DG units considering different values of DG power factor (unity and non-unity), with the objective of maximum real power loss reduction. The effectiveness of the proposed method was validated on the standard IEEE radial distribution networks including 33, 69, and 118-bus test networks. The results obtained by QOCSOS were compared to those from other methods available in the literature and the standard SOS algorithm. Comparative results revealed that QOCSOS obtained better solutions than other compared methods, and performed greater than SOS. Accordingly, QOCSOS can be a very favourable method to cope with the optimal DG placement problem.