A simplified fuzzy inference method with tabu search for short-term load forecasting in power systems

This paper proposes a new method for short-term load forecasting in power systems. The proposed method makes use of simplified fuzzy inference that has an output variable in crisp number rather than fuzzy. The technique is quite popular for reducing computational effort. Also, it is quite acceptable to system operators in a sense that the output variable in crisp number is friendly to power system engineers although each input variable has the fuzzy membership functions. In order to construct the optimal structure of the fuzzy membership functions, it is necessary to use a combinatorial technique that determines the number and the location of the fuzzy membership functions. In this paper, tabu search is applied to determine them efficiently. As a metaheuristic approach, the technique is better than others in terms of computational effort and solution accuracy. The effectiveness of the proposed method is demonstrated for real data of utilities. A comparison is made between the proposed method and others