Comparison between Genetic Algorithms and Particle Swarm Optimization
EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
EMO'05 Proceedings of the Third international conference on Evolutionary Multi-Criterion Optimization
Comprehensive learning particle swarm optimizer for global optimization of multimodal functions
IEEE Transactions on Evolutionary Computation
Particle Swarm Optimization: Basic Concepts, Variants and Applications in Power Systems
IEEE Transactions on Evolutionary Computation
Damage detection based on improved particle swarm optimization using vibration data
Applied Soft Computing
Hi-index | 0.00 |
This paper presents a comprehensive study on mono- and multi-objective approaches for electrical distribution network design using particle swarm optimization (PSO). Specifically, two distribution network design problems, i.e., static and expansion planning, are solved using PSO. The network planning involves optimization of both network topology and branch conductor sizes. Both the planning problems are used to illustrate mono- and multi-objective optimization of distribution networks. Firstly, three PSO variants, i.e., PSO with inertia weight (PSO-IW), PSO with constriction factor (PSO-CF), and comprehensive learning PSO, are evaluated on a mono-objective (minimization of total cost of installation and energy loss) static planning problem. A novel encoding/decoding technique is devised to represent the network as a particle in PSO. Also, a heuristics based branch conductor size selection algorithm has been developed and used. Statistical tests performed to compare the performances of the three PSO variants reveal that the PSO-CF exhibits relatively better performance. Subsequently, the PSO-CF is applied for mono-objective expansion planning and multi-objective static and expansion planning problems. In the multi-objective planning with two conflicting objectives (total cost of installation and energy loss, and total non-delivered energy), the Pareto-optimality principle based tradeoff is done using the strength Pareto evolutionary algorithm-2. The efficiency of PSO for distribution system planning problem, in general, is demonstrated through different examples.