Annual Electricity and Energy Consumption Forecasting for the UK Based on Back Propagation Neural Network, Multiple Linear Regression, and Least Square Support Vector Machine

The long-term demand forecast for annual national electricity and energy consumption plays a vital role in future strategic planning, power system installation programming, investment next-generation unit construction. Three machine learning algorithms of BP-NN, MLR, LS-SVM were chosen training forecasting models, with the data on population, GDP, mean temperature, sunshine, rainfall, frost days 1993–2019 serving as input variables. total divided by 70% into set (1993–2011) 30% test (2012–2019), chronological order. RMSE, MAPE, MaxError adopted performance criteria. statistical results show that gross population UK increases year from 1993 to 2020. GDP generally before 2007 but has decline, then varies large amplitude afterward. increase reach peak around 2005. Afterward, decline occurs basically until 2019. simulation reveal all three models predict well have some overestimation set. model best among it is feasible use country based past economic livelihood data. In this way, decision-makers can rely predicted values make well-founded layout construction avoid waste or shortage resources.