Comparison of Multiobjective Evolutionary Algorithms: Empirical Results
Evolutionary Computation
An overview of evolutionary algorithms in multiobjective optimization
Evolutionary Computation
A particle filtering framework for randomized optimization algorithms
Proceedings of the 40th Conference on Winter Simulation
Multiobjective evolutionary algorithms: a comparative case studyand the strength Pareto approach
IEEE Transactions on Evolutionary Computation
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
Distributed generation is small scale power cogeneration within an integrated energy network, that provides system wide and environmental benefits. Network benefits include enhancements to reliability, reduction of peak power requirements, improved power quality and enhanced resilience. Environmental benefits include better land use for transmission and distribution, and reduced ecological impact. Deploying distributed generation affects the power loss in the system and has an associated cost. Therefore, optimization of the penetration level of the distributed generation should consider both goals of minimizing total power loss and minimizing total operational costs. In this study, we propose a novel multi-objective optimization framework based on particle filtering to evaluate the effects of adding distributed generation to a networked system in terms of power loss and operational costs, simultaneously. The proposed framework has been demonstrated on the IEEE-30 bus system yielding to minimal power losses of 2.075 MW and minimal costs of $547.51 per hour.