The control issues in the network caused by the increasing proportion of dispersed production & sources of clean energy need coordinated handling of these assets. Virtual power plants (VPPs) may be thought of as systems that comprise resources like electric vehicles, energy storage, controlled loads, and other distributed generators. Operation, resource unpredictability, energy management, involvement in electrical markets, etc. are just a few of the many obstacles VPPs must overcome. The challenge of the study is to optimize the performance of VPPs in managing dispersed clean energy sources, and the proposed model employs a distributed control approach and particle swarm optimization (PSO)-based learning reinforcement technique to address this challenge by maximizing VPP output and operational efficiency in various energy market scenarios. In this research, we explore the topic of ongoing electrical power in massively distributed systems based on VPPs. To maximize the VPP output & reach an ideal operational point, the authors of this work used a distributed control approach. The purpose of this article is to examine VPP performance under a variety of markets for energy configurations. Further, a PSO-based learning reinforcement technique is used to examine the benefits and drawbacks of VPPs’ power management.