Long-Term Electricity Demand Prediction via Socioeconomic Factors—A Machine Learning Approach with Florida as a Case Study

Predicting future energy demand will allow for better planning and operation of electricity providers. Suppliers will have an idea of what they need to prepare for, thereby preventing over and under-production. This can save money and make the energy industry more efficient. We applied a multiple regression model and three Convolutional Neural Networks (CNNs) in order to predict Florida’s future electricity use. The multiple regression model was a time series model that included all the variables and employed a regression equation. The univariant CNN only accounts for the energy consumption variable. The multichannel network takes into account all the time series variables. The multihead network created a CNN model for each of the variables and then combined them through concatenation. For all of the models, the dataset was split up into training and testing data so the predictions could be compared to the actual values in order to avoid overfitting and to provide an unbiased estimate of model accuracy. Historical data from January 2010 to December 2017 were used. The results for the multiple regression model concluded that the variables month, Cooling Degree Days, Heating Degree Days and GDP were significant in predicting future electricity demand. Other multiple regression models were formulated that utilized other variables that were correlated to the variables in the best-selected model. These variables included: number of visitors to the state, population, number of consumers and number of households. For the CNNs, the univariant predictions had more diverse and higher Root Mean Squared Error (RMSE) values compared to the multichannel and multihead network. The multichannel network performed the best out of the three CNNs. In summary, the multichannel model was found to be the best at predicting future electricity demand out of all the models considered, including the regression model based on the datasets employed.

[1]  Chao Wang,et al.  Electricity consumption probability density forecasting method based on LASSO-Quantile Regression Neural Network , 2019, Applied Energy.

[2]  D. H. Vu,et al.  A variance inflation factor and backward elimination based robust regression model for forecasting monthly electricity demand using climatic variables , 2015 .

[3]  António Rua,et al.  A wavelet approach for factor‐augmented forecasting , 2011 .

[4]  Julien Jacques,et al.  Short-Term Electricity Demand Forecasting Using a Functional State Space Model , 2018 .

[5]  Henning W. Rust,et al.  Evaluation of forecasts by accuracy and spread in the MiKlip decadal climate prediction system , 2016 .

[6]  Zhikun Xu,et al.  Application of an Optimized SVR Model of Machine Learning , 2014, MUE 2014.

[7]  M. E. Günay,et al.  Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey , 2016 .

[8]  Nooriya A. Mohammed.  Modelling of unsuppressed electrical demand forecasting in Iraq for long term , 2018, Energy.

[9]  Yi Liang,et al.  Analysis and Modeling for China's Electricity Demand Forecasting Based on a New Mathematical Hybrid Method , 2017, Inf..

[10]  S K Smith,et al.  An evaluation of population forecast errors for Florida and its counties. , 1992, Applied demography.

[11]  Mauro Costantini,et al.  How accurate are professional forecasts in Asia? Evidence from ten countries , 2016 .

[12]  Yannis Siskos,et al.  Disaggregating time series on multiple criteria for robust forecasting: The case of long-term electricity demand in Greece , 2019, Eur. J. Oper. Res..

[13]  Kashem M. Muttaqi,et al.  Load forecasting under changing climatic conditions for the city of Sydney, Australia , 2018 .

[14]  Lester C. Hunt,et al.  Modelling residential electricity demand in the GCC countries , 2016 .

[15]  C. Thangaraj,et al.  PREDICTION OF INDIA’S ELECTRICITY DEMAND USING ANFIS , 2015, SOCO 2015.

[16]  J. Ben Hadj Slama,et al.  Day-ahead load forecast using random forest and expert input selection , 2015 .

[17]  Upmanu Lall,et al.  A hierarchical Bayesian regression model for predicting summer residential electricity demand across the U.S.A. , 2017 .

[18]  Robert A. Buckle,et al.  Markov Switching Models for GDP Growth in a Small Open Economy: The New Zealand Experience , 2004 .

[19]  Sahil Shah,et al.  Predicting stock market index using fusion of machine learning techniques , 2015, Expert Syst. Appl..

[20]  Cheng-Chien Kuo,et al.  Energy Consumption Load Forecasting Using a Level-Based Random Forest Classifier , 2019, Symmetry.