Regression Model-Based Short-Term Load Forecasting for University Campus Load

Abstract

Load forecasting is a critical aspect for power systems planning, operation and control. In this paper, as part of research efforts of an ambitious project at Memorial University of Newfoundland in St. John’s, Canada, to achieve more energy efficient and environmental friendly “Sustainable Campus”, we present a day-ahead load forecasting approach for the energy management system of the project. The hourly load consumption dataset from January 1, 2016 to March 31, 2020 is used in the paper, which was collected from two power meters on campus. Using the load consumption dataset along with the collected meteorological dataset, a total of 19 regression model-based day-ahead load forecasting algorithms for Memorial University of Newfoundland’s campus load are developed and evaluated in this paper. These 19 models belong to five families of regression models in MATLAB Regression Toolbox: Linear Regression, Regression Trees, Support Vector Machines (SVM), Gaussian Process Regression (GPR), and Ensemble of Trees. It is found that the family of GPR models shows the best load forecasting performance because they are nonparametric kernel-based probabilistic models. Two GPR models, Rational Quadratic GPR and Exponential GPR, are recommended as the best models for load forecasting through this study.

Keywords

• Short-term load forecasting
• regression model
• day-ahead load forecasting
• Gaussian process regression
• probabilistic models
• university campus load