A hybrid method for short-term electricity consumption prediction

Electricity consumption prediction is an important but demanding issue in the study of power systems. It is difficult for the conventional prediction methods, such as linear models, to utilize relevant domain knowledge in the forecasting of power peaks. In this paper, we propose an approach merging a regression predictor and a peak compensator together. The latter is designed to compensate for the prediction errors related to power peaks caused by the former. The proposed hybrid short-term prediction scheme has been demonstrated in a real-world case study to efficiently yield performances moderately better than the standalone regression predictors.

[1]  Elena Tsiporkova,et al.  Predicting Hourly Energy Consumption. Can Regression Modeling Improve on an Autoregressive Baseline? , 2015, DARE.

[2]  Manuel Berenguel,et al.  A Comparison of Energy Consumption Prediction Models Based on Neural Networks of a Bioclimatic Building , 2016 .

[3]  Zainab H. Osman,et al.  Neural network based approach for short-term load forecasting , 2009, 2009 IEEE/PES Power Systems Conference and Exposition.

[4]  Yu-Hsiang Hsiao,et al.  Household Electricity Demand Forecast Based on Context Information and User Daily Schedule Analysis From Meter Data , 2015, IEEE Transactions on Industrial Informatics.

[5]  Yonggang Wu,et al.  Short-term Load Forecasting Using Improved Similar Days Method , 2010, 2010 Asia-Pacific Power and Energy Engineering Conference.

[6]  Yi Yang,et al.  A hybrid application algorithm based on the support vector machine and artificial intelligence: An example of electric load forecasting , 2015 .

[7]  D.W. Bunn,et al.  Forecasting loads and prices in competitive power markets , 2000, Proceedings of the IEEE.

[8]  Hongye Su,et al.  Forecasting building energy consumption with hybrid genetic algorithm-hierarchical adaptive network-based fuzzy inference system , 2010 .

[9]  Sauro Longhi,et al.  Fuzzy logic home energy consumption modeling for residential photovoltaic plant sizing in the new Italian scenario , 2014 .

[10]  Zhibin Wu,et al.  Predicting and optimization of energy consumption using system dynamics-fuzzy multiple objective programming in world heritage areas , 2013 .

[11]  Min-Seok Kim,et al.  Short-term electric load forecasting using data mining technique , 2013 .

[12]  A. Elkamel,et al.  Electricity demand estimation using an adaptive neuro-fuzzy network: A case study from the Ontario province – Canada , 2013 .

[13]  Y. Shimakura,et al.  Short-term load forecasting using an artificial neural network , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[14]  Yi Wang,et al.  Clustering of Electricity Consumption Behavior Dynamics Toward Big Data Applications , 2016, IEEE Transactions on Smart Grid.