Renewable Energy‐Based Load Frequency Controller and Model with a Reduced Order for a Large‐Scale Power System

• Published in: Energy technology (Weinheim, Germany) Germany), 2024-01, Vol.12 (1), p.n/a
• Main Authors: Singh, Rahul, Kumar, Jitendra, Singh, Jay, Chaurasia, Giraja Shankar
• Format: Article
• Language: English
• Subjects: Algorithms; Alternative energy sources; Control algorithms; Electrical loads; Frequency control; frequency deviation; jellyfish; load frequency controllers; Optimization; Optimization techniques; power loss; Reduced order models; Renewable energy sources; Renewable resources; Solar energy; Solar power; Systems stability; Weather
• ISSN: 2194-4288; 2194-4296
• DOI: 10.1002/ente.202300618

Power system stability relies heavily on load frequency control (LFC) because it ensures that the power generated in a grid matches the load demand. The conventional LFC methods are no longer adequate with the rising use of renewable energy sources like wind and solar power. These resources are intermittent, and their power output varies depending on weather conditions. As a result, incorporating renewable energy resources (RERs) into the LFC system necessitates a different approach. One method is to use advanced control algorithms that can respond quickly to changes in power output. Hence, this article proposes an autoencoder‐based jellyfish optimization developed in this framework to reduce the power outage and control voltage and frequency fluctuations. The LFC system can be optimized by combining autoencoder and jellyfish optimization techniques to effectively handle the variability and unpredictability of RERs while maintaining the power system's stability and reliability. This approach may also result in more efficient and cost‐effective power system operation by reducing the need for conventional power generation and minimizing the impact of RERs on the system. Increasing integration of renewable energy sources such as wind and solar power has drawbacks such as power outages and frequency fluctuations. Therefore, autoencoder‐based jellyfish optimization hybrid approach is introduced with MATLAB environment to address these challenges. The proposed methodology leads to a more efficient and cost‐effective power system operation by reducing the reliance on conventional power generation systems.