ASSESSMENT OF THE INFLUENCE OF NEURAL NETWORK HYPERPARAMETERS ON THE ACCURACY OF FORECASTING ENERGY CONSUMPTION

The work is devoted to the problem of improving the accuracy of short-term forecasting of electricityconsumption using deep machine learning tools. The influence of the specified neural network NNhyperparameters on the error in predicting power consumption, such as: data packet size – Bs; number ofNN layers – j; neuron activation functions – Fa; optimizers – O. The optimal hyperparameters of the NNmodel for predicting electrical consumption (EC) for consumers of additive and cyclic types have beendetermined. The analysis of the impact of the batch size on the accuracy of the forecast showed an increasein the effectiveness of NN training with the growth of the input data package. The analysis of theinfluence of the number of layers showed that with an increase in the number of layers of the NN, thelearning time decreases and its predictions become more accurate. A study of various optimizers forlearning speed has shown that the best results are demonstrated by the optimizers “Adam” and“RMSProp". It is shown that the choice of the activation function determines how quickly the NN will betrained and how accurate its forecasts will be. The use of various regularization methods allows NS toachieve better results in practice, improving their generalization ability and increasing the accuracy ofpredictions. It is shown that in order to achieve the minimum forecasting error, it is necessary to individuallyconfigure the network parameters for each consumer, taking into account significant differences inthe nature of energy consumption. The training and testing of the created network with selected parameterswas carried out on a training and test sample containing data on electricity consumption for 2 years(17520 hours). The analysis of input data on power consumption showed that the optimal parameters of the predictive neural network model in manual mode are: package size 250 (selected empirically), 5 layers,activation function “ReLU", optimizer “Adam". Various ways of selecting hyperparameters (manuallyand by means of genetic algorithm (GA)) are considered.