Distributed Energy Resources for Techno-Economic with Ant Colony Optimization (ACO) based Artificial Neural Network

The integration of Distributed Energy Resources (DERs) into modern power systems presents both opportunities and challenges for achieving efficient and economically viable energy solutions. This research explores the application of Ant Colony Optimization (ACO) in conjunction with Artificial Neural Networks (ANNs) to address the techno-economic optimization of Distributed Energy Resources. The proposed approach leverages the swarm intelligence of ACO to enhance the learning capabilities of ANNs, aiming to optimize the operation and management of decentralized energy systems. In this study, the research focuses on the development of a novel framework that combines the optimization capabilities of ACO with the predictive power of ANNs to achieve a comprehensive and adaptive solution for DERs. The ACO algorithm is employed to search for optimal configurations and control strategies for distributed energy assets, considering factors such as generation, storage, and demand response. Meanwhile, the ANN model is trained to predict the techno-economic performance of different DER scenarios based on historical data and real-time information. The Ant colony Optimization strategies using Artificial Neural Networks performed better in terms of power loss (246.23 kw) and average purchase of real power (3677.33 kw), according to a final examination of the numerical data; nonetheless, these metrics do not favor the other optimization strategies. This demonstrated the viability and effectiveness of the suggested course of action.