A combined model based on multiple seasonal patterns and modified firefly algorithm for electrical load forecasting

•Improve the accuracy and stability significantly of electrical power forecasting.•Propose a combined model based on several artificial neural networks.•Use multiple seasonal patterns to pre-process data.•Modify firefly algorithm with BFGS to improve optimized performance. Short-term load forecasting (STLF) plays an irreplaceable role in the efficient management of electric systems. Particularly in the electricity market and industry, accurate forecasting could provide effective future plans and economic operations for operators of utilities and power systems. Hence, a more precise and stable load-forecasting model is essentially needed in the field of electricity load forecasting. To avoid the limitations of individual models, a new combined model is proposed. In this model, except for the multiple seasonal patterns used to reduce interferences from the original data, a new optimization algorithm is presented and applied to optimize the weight coefficients of the combined model based on non-positive constraint combination theory. To estimate the forecasting ability of the proposed combined model, half-hourly electricity power data from New South Wales, the State of Victoria and the State of Queensland in Australia were used in this paper as a case study. In the numerical experiments, compared with other six single models, the average mean absolute percent errors (MAPEs) of the combined model were reduced by 0.7138%, 1.0281%, 4.8394%, 0.9239%, 9.6316% and 7.3367%, respectively.