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.INDEX TERMS Short-term load forecasting, regression model, day-ahead load forecasting, Gaussian process regression, probabilistic models, university campus load.

Short-Term Mosques Load Forecast Using Machine Learning and Meteorological Data

“…Several forecasting models have been built in the literature to predict different types of buildings, such as hospitals, industrial, residential, and university campuses. In addition, it is shown that the type of weather conditions has a major influence on the load forecast [15]. Therefore, selecting the most accurate weather variables is essential to generate an accurate forecasting model.…”

“…The statistical approaches are allocated into time series models and machine learning methods. The study in [15], for instance, develops a short-term electrical load to predict the load of the Memorial University campus in Canada using 19 regression algorithms. These algorithms belong to five main algorithms, namely, Linear Regression (LR), regression trees, Support Vector Regression (SVR), Gaussian Process Regression (GPR), and the ensemble of trees.…”

Short-term power load forecasting based on gray relational analysis and support vector machine optimized by artificial bee colony algorithm

“…SVM is a machine learning algorithm proposed by Vapnik et al based on the structural risk minimization criterion in statistical learning theory, which has the functions of classification and regression ( Madhukumar et al, 2022 ; Li et al, 2020 ; Tan et al, 2020 ). Short-term load forecasting uses the regression function of the support vector machine.…”

Load Forecasting of Distributed System Host Based on Linear Time Series Model

“…For example, after determining the main data set, how to carry out appropriate load calculation according to the specific situation has also become an important factor. Therefore, in actual work, it is often necessary to establish a variety of data information indicators such as different types and the same type of use, similar performance, and can accurately reflect the change trend of the total demand of the system under various conditions to determine the relationship and relationship between various parameters [15][16].…”