A Short-Term Electric Load Forecasting Scheme Using 2-Stage Predictive Analytics

One key issue for stable power supply is to forecast electric load accurately. Since buildings of the same type show similar power consumption patterns, it should be considered for accurate electric load forecast. In particular, university buildings show various electric loads depending on time and other external factors. In this paper, we propose a short-term load forecast model for educational buildings using 2-stage predictive analytics for the effective operation of their power system. To do that, we collect the electric load data of five years from a university campus. Next, we consider the electric load pattern by using the moving average method according to the day of the week. Next, we predict the daily electric load using the random forest method and finally evaluate its performance using the time series cross-validation. The experimental results show that our forecasting model outperforms other competing methods in terms of prediction accuracy.

[1]  José Augusto Baranauskas,et al.  How Many Trees in a Random Forest? , 2012, MLDM.

[2]  Min Hee Chung,et al.  Potential opportunities for energy conservation in existing buildings on university campus: A field survey in Korea , 2014 .

[3]  Mohammad Yusri Hassan,et al.  A review on applications of ANN and SVM for building electrical energy consumption forecasting , 2014 .

[4]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[5]  Abbas Khosravi,et al.  A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings , 2015 .

[6]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[7]  Eenjun Hwang,et al.  Power Consumption Forecasting Scheme for Educational Institutions Based on Analysis of Similar Time Series Data , 2017 .

[8]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[9]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[10]  Miriam A. M. Capretz,et al.  Energy Forecasting for Event Venues: Big Data and Prediction Accuracy , 2016 .

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  Sang-Hong Lee,et al.  Feature selection for daily peak load forecasting using a neuro-fuzzy system , 2014, Multimedia Tools and Applications.

[13]  Jaime Lloret,et al.  A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings , 2014, IEEE Communications Surveys & Tutorials.

[14]  Khaled M. Abo-Al-Ez,et al.  A data mining based load forecasting strategy for smart electrical grids , 2016, Adv. Eng. Informatics.

[15]  Eenjun Hwang,et al.  Forecasting power consumption for higher educational institutions based on machine learning , 2017, The Journal of Supercomputing.

[16]  Kevin M. Smith,et al.  Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy , 2014 .

[17]  Khuram Pervez Amber,et al.  Electricity consumption forecasting models for administration buildings of the UK higher education sector , 2015 .

[18]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[19]  Jie Zhang,et al.  A data-driven multi-model methodology with deep feature selection for short-term wind forecasting , 2017 .

[20]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .