Energy performance prediction of vapor-injection air source heat pumps in residential buildings using a neural network model

A novel deep learning‐based integrated photovoltaic, energy storage system and electric heat pump system: Optimising energy usage and costs

“…Previous studies employed multiple variables to predict building energy demand and RES energy generation. For example, Wang et al 41 considered system operational variable, outdoor and indoor environmental variables, and time‐related variables to predict energy performance of a vapour‐injection heat pump. Ye et al 40 used nine inputs and predicted the energy consumption of an air‐source heat pump.…”

“…Moreover, similar studies have often relied on traditional prediction techniques, which have potential limitations (eg, in terms of accuracy) in modelling complex behaviour, to predict/forecast building energy demand or PV energy generation. 29,30,[33][34][35][36]41 To overcome such limitations and improve prediction accuracy, we employ the DNN algorithm to forecast PV energy generation and EHP energy demand and subsequently determine the ESS charging/discharging schedules. [45][46][47][48][49][50] Another critical aspect of our study is related to the parameters used in forecasting EHP energy consumption and PV energy generation.…”

“…Ye et al 40 elaborated the use of ANNs and predicted the energy consumption of an air‐source heat pump. A study by Wang et al 41 developed an ANN with two hidden layers and predicted the energy performance of a vapour injection air source heat pump.…”

“…The forecasting module uses real‐time weather information and is composed of two deep neural networks (DNN), forecasting models for EHP energy consumption and PV energy generation. Moreover, similar studies have often relied on traditional prediction techniques, which have potential limitations (eg, in terms of accuracy) in modelling complex behaviour, to predict/forecast building energy demand or PV energy generation 29,30,33‐36,41 . To overcome such limitations and improve prediction accuracy, we employ the DNN algorithm to forecast PV energy generation and EHP energy demand and subsequently determine the ESS charging/discharging schedules 45‐50 …”

“…Previous studies mentioned above have mainly used a large number of parameters to predict/forecast EHP energy demand and PV energy generation. For instance, Ye et al 40 and Wang et al 41 used 9 and 10 variables to predict the energy demand of heat pump systems using neural network models, respectively. Similarly, Massa Gray and Schmidt 51 used 21 variables while Hwang et al 52 utilised 12 variables to predict the energy performance of a heat pump.…”