Neuro-Fuzzy Paradigms for Intelligent Energy Management

Abstract

Intelligent energy management has become one of the major research fields in electrical engineering. It constitutes an important tool for efficient planning and operation of power systems and its significance has been intensifying particularly, because of the recent movement towards open energy markets and the need to assure high standards on reliability. Hybrid neuro-fuzzy paradigms have recently gained a lot of interest in research and application. In this chapter, we discuss two neuro-fuzzy paradigms for intelligent energy management. In the first approach, a neural network learning algorithm is used to fine tune the parameters of a Mamdani and Takagi-Sugeno Fuzzy Inference System (FIS). Mamdani FIS is used to predict the energy demand and the Takagi-Sugeno FIS is used to predict the reactive power flow. In the second approach, fuzzy if-then rules were embedded into an Artificial Neural Network (ANN) learning algorithm (fuzzy-neural network) to achieve improved performance for short-term load forecast. The performance of the different neuro-fuzzy paradigms were tested using real world data and compared with a direct neural network and FIS approach. The different performance results obtained clearly demonstrates the importance of the proposed techniques for intelligent energy management.