Short Term Load Forecasting Using Fuzzy Inference and Ant Colony Optimization
The short term load forecasting (STLF) is required for the generation scheduling and the economic load dispatch at any time. The short term load forecast calculates the power requirement pattern for the forecasting day using known, similar previous weather conditions. This paper describes a new approach for the calculation of the short term load forecast that uses fuzzy inference system which is further optimized using an Ant Colony Optimization (ACO) algorithm. It takes into account the load of the previous day, maximum temperature, average humidity and also the day type for the calculation of the load values for the next day. The Euclidean norm considering the weather variables and type of the day with weights is used to get the similar days. The effectiveness of the proposed approach is demonstrated on a typical load and weather data.
KeywordsEuclidean Norm Fuzzy Inference System Mean Absolute Percentage Error Weather Variable Load Forecast
Unable to display preview. Download preview PDF.
- 7.Jain, A., Srinivas, E., Rauta, R.: Short term load forecasting using fuzzy adaptive inference and similarity. World Congress on Nature and Biologically Inspired Computing (NaBIC), 1743–1748 (2009)Google Scholar
- 8.Srinivas, E., Jain, A.: A Methodology for Short Term Load Forecasting Using Fuzzy Logic and Similarity. In: The National Conference on Advances in Computational Intelligence Applications in Power, Control, Signal Processing and Telecommunications, NCACI (2009)Google Scholar
- 9.Gross, G., Galiana, F.: Short term load forecasting. In: Proc. IEEE, Special Issue on Computers in Power System Operations, pp. 1558–1573 (1987)Google Scholar
- 10.Khaled, M., Naggar, E.L., Khaled, A., Rumaih, A.L.: Electric load forecasting using genetic based algorithm, optimal filter Estimator and least squares technique. Comparative Study World Academy of Science, Engineering and Technology, 134–142 (2005)Google Scholar