2022 Jimenez, Victor A. and Lizondo, Diego F. and Araujo, Pedro B. and Will, Adrian L. E., A Conceptual Microgrid Management Framework Based on Adaptive and Autonomous Multi-Agent Systems, Journal of Computer Science and Technology, 22(1): 1—11, 2022.
Resumen: The Smart Grids paradigm emerged as a response to the need to modernize the electric grid and address problems related to the demand for better energy quality. However, there are no fully developed and implemented smart grids. Centralized systems are still common, with a low granularity of control and reduced monitoring capacity, especially in low-voltage networks. In this work, we propose a framework for Microgrid Management, providing solutions for three main problems: Peak Shaving addressed with a distributed control algorithm based on Artificial Immune Systems for demand-side management; Transformer Lifespan Estimation using a thermal model adjusted by Genetic Algorithms; Short-Term Load Forecasting based on Artificial Neural Networks and Genetic Algorithms. Combining these solutions, we can reduce peak loads by controlling air conditioners without affecting user comfort, determine the negative effects of overloading on distribution transformers and provide demand forecasting. The proposed framework is based on autonomous and distributed systems, so the Organization Centered Multi-Agent Systems methodology was applied for modeling and development. The implemented solutions were applied in the Tucumán province, Argentina, exposing the system’s benefits and the relevance of the information generated by the framework.