Energy management optimisation using a combined Long Short-Term Memory recurrent neural network – Particle Swarm Optimisation model

Energy load forecasting is essential to effectively optimise the use of energy for the purpose of smart grid operation. In this work, a focus is placed on Short-Term Load Forecasts (STLF) using measured heat pump data from the UK utilising the Long Short-Term Memory (LSTM) method. A load forecasting program is developed to forecast the electricity consumption of heat pumps based on historical data. LSTM is compared to Backpropagation Neural Network (BPNN), Seasonal Autoregressive Integrated Moving Average (SARIMA), Random Forest (RF) and Holt-Winters Exponential Smoothing (ES). The best average Mean Absolute Percent Error (MAPE) of 1.59% is achieved for the test data set by LSTM, which outperforms other models compared and a number of models presented in papers in the literature. By conducting the Wilcoxon signed-rank test, it is proven that the prediction accuracy improvement of LSTM compared to other models is statistically significant with the exception when comparing with RF with the training data. The impact of data aggregation resolution to forecast accuracy is investigated. The proposed LSTM model performs best on 1-h resolution data compared with other resolution time periods. The results of the LSTM model are integrated with Home Energy Management Systems (HEMS). The electricity costs of the HEMS are compared when using forecasted and measured heat pump data respectively. The results indicate an average percentage difference of 2.06% between the predicted and the actual electricity cost of HEMS for the test data. Furthermore, this paper presents a combined neural network and Particle Swarm Optimisation (PSO) model to develop an optimised energy management system while proving the effectiveness of the LSTM algorithm.