A genetic algorithm-determined deep feedforward neural network architecture (GA-DFNN) is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United Kingdom. Due to the comprehensive relationship between affecting factors and real-world building electricity consumption, the adoption of multiple hidden layers in the deep neural network (DFNN) algorithm would improve its prediction accuracy. The architecture of a DFNN model mainly refers to its quantity of hidden layers, quantity of neurons in the hidden layers, activation function in each layer and learning process to obtain the connecting weights. The optimal architecture of DFNN model was generally determined through a trial-and-error process, which is an exponential combinatorial problem and a tedious task. To address this problem, genetic algorithm (GA) is adopted to automatically design an optimal architecture with improved generalization ability. One year and six months of measurement data from a campus building is used for training and testing the proposed GA-DFNN model, respectively. To demonstrate the effectiveness of the proposed GA-DFNN prediction model, its prediction performance, including mean absolute percentage error, coefficient of determination, root mean square error and mean absolute error, was compared to the reference feedforward neural network models with single hidden layer, DFNN models with other architecture, random search determined DFNN model, long-short-term-memory model and temporal convolutional network model. The comparison results show that the proposed GA-DFNN predictive model has superior performance than all the reference prediction models, demonstrating the optimization effectiveness of GA and the prediction effectiveness of DFNN model with multiple hidden layers and optimal architecture.
Luo, X. J., Oyedele, L. O., Ajayi, A. O., Akinade, O. O., Delgado, J. M. D., Owolabi, H. A., & Ahmed, A. (2020). Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings. Energy and AI, 2, https://doi.org/10.1016/j.egyai.2020.100015