Optimal scheduling of DG and EV parking lots simultaneously with demand response based on self?adjusted PSO and K?means clustering

Recently, the proliferation of distributed generation (DG) has been intensively increased in distribution systems worldwide. In systems, DGs and utility-owned electric vehicle (EV) to grid aggregators have be efficiently scaled for cost-effective network operation. Accordingly, with penetration power demand response (DR) is considered an advanced step towards a smart grid. To cope these advancements, this study aims develop innovative solution day-ahead sizing approach energy storage EVs parking lots complying DR minimizing pertinent costs. The unique feature proposed allow interactive customers participate effectively systems. accurately solve optimization model, two probabilistic self-adjusted modified particle swarm (SAPSO) algorithms are developed compared total operational costs addressing all constraints system, DG units, EV lots. K-means clustering Naive Bayes utilized determine that ready program. obtained results on IEEE-24 reliability test system genetic algorithm conventional PSO verify effectiveness algorithms. show first SAPSO outperforms terms running finding demonstrates near-optimal scheduling units simultaneous manner can minimize subjected DR.