Development of deep learning artificial neural networks models to predict temperature and power demand variation for demand response application in cold storage. (November 2021)

• Record Type: Journal Article
• Authors: Hoang, H.M.; Akerma, M.; Mellouli, N.; Montagner, A. Le; Leducq, D.; Delahaye, A.
• Is Part Of: International journal of refrigeration. Volume 131(2021)
• Page Start: 857
• Page End: 873
• Publication Date: 2021-11
• Subjects: Demand response -- Cold storage -- Electric energy consumption -- Deep learning -- Long short-term memory -- Neural network; Réponse à la demande -- Entreposage frigorifique -- Consommation d'énergie électrique -- Apprentissage approfondi -- Mémoire à court et long terme -- Réseau neuronal; ANN Artificial neural networks -- ARIMA Autoregressive integrated moving average -- ARMA Autoregressive moving average -- BPNN Back propagation neural networks -- CNN Convolutional neural networks -- DNN Deep neural networks -- DR Demand response -- DT Decision tree -- GHG Greenhouse Gases Emissions -- GRNN General regression neural networks -- LSTM Long Short-Term Memory -- MAE Mean Absolute Error -- RBNN Radial basis neural networks -- RES Renewable energy sources -- RNN Recurrent neural networks -- SVM Support vector machine -- VARMA Vector autoregressive moving-average; Refrigeration and refrigerating machinery -- Periodicals; 621.56
• DOI: 10.1016/j.ijrefrig.2021.07.029
• Languages: English
• ISSNs: 0140-7007

Abstract

Highlights: Development of 4 LSTM models for demand response (DR) application in cold storage They are capable of predicting sudden temperature and power variations due to DR Convolutional LSTM model has best performance in predicting product temperatures Better prediction was obtained while using more sensors or well-positioned sensors Impact of data quality, quantity and DR patterns on the prediction was assessed ABSTRACT: Food warehouses and cold rooms have a significant potential for Demand Response (DR) application (stopping or reducing the power of fans and compressors of the refrigeration system) due to thermal inertia of food products. However, as air and food temperature might increase beyond acceptable limits during DR periods, DR needs to be carefully applied in order to respect the food temperature regulation and to maintain quality and safety of the products. It is thus important to predict the system behaviour in case of DR application in order to evaluate its potential impacts and to decide if DR can be performed or not. Four deep learning artificial neural networks (ANN) models, traditional Long Short-Term Memory LSTM, stacked LSTM, bidirectional LSTM and convolutional LSTM, were developed to predict future temperature and power demand perturbations due to the application of DR in cold storage. The aims of this work are: first, to assess the performance of those models in predicting the system behaviours, in particular the sudden variations during and after DR applications, and second, to identify the impact of data availability (number of sensors, their positions) and data characteristic (quality, quantity and DR patterns) on the prediction performance. The results have shown the high potential of deep learning ANN models in supporting DR application in cold storage.