Automated control scheduling to improve the operative performance of smart renewable energy systems

Abstract

Smart renewable energy systems are designed as an alternative to conventional power generation methods that utilize natural resources. The development of automation and its allied technologies has improved the performance and operations of smart energy systems in recent years. In this article, automated control scheduling (ACS) for balancing power generation and deficiency in renewable energy systems is introduced. This scheduling control is supported by deep Q-learning to define the operation and shortage state of energy systems. Based on the definitive control schedule, the functions of the systems can be modeled without requiring additional time for power generation and dissemination. In addition, the power generation process relies on environmental conditions to gain maximum profitable power for the operating cost of the power systems. The energy generation system analyzes the environmental conditions suitable for achieving maximum profit, and power dissemination is also modeled. The performance of the proposed system was analyzed using the following metrics: operational profit, imbalance factor, successful prediction of operations, and time lag.