A Deep Learning Method for Short-Term Residential Load Forecasting in Smart Grid

Abstract

Residential demand response is vital for the efficiency of power system. It has attracted much attention from both academic and industry in recent years. Accurate short-term load forecasting is a fundamental task for demand response. While short-term forecasting for aggregated load data has been extensively studied, load forecasting for individual residential users is still challenging due to the dynamic and stochastic characteristic of single users' electricity consumption behaviors, i.e., the variability of the residential activities. To address this challenge, this paper presents a short-term residential load forecasting framework, which makes use of the spatio-temporal correlation existing in appliances' load data through deep learning. Multiple time series are conducted in the framework to describe electricity consumption behaviors and their internal spatio-temporal relationship. And a method based on deep neural network and iterative ResBlock is proposed to learn the correlation among different electricity consumption behaviors for shortterm load forecasting. Experiments based on real world measurements have been conducted to evaluate the performance of the proposed forecasting approach. The results show that both the appliances' load data and iterative ResBlocks can help to improve the forecasting performance. Compared with existing methods, measurements on Root Mean Squared Error, Mean Absolute Error and Mean Absolute Percentage Error for the proposed approach are reduced by 3.89%-20.00%, 2.18%-22.58% and 0.69%-32.78%. In addition, further experiments are conducted to evaluate the impact of using appliances' load data, iterative ResBlocks as well as other factors for the proposed approach. INDEX TERMS Smart grid, short-term load forecasting, deep learning, residential load forecasting, iterative ResBlocks.

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

“…Deep Neural Network (DNN) is a mechanism built upon FFNN where there are multiple hidden layers. Iterative ResBlocks (IRB) based DNN has been developed for individual residential loads [58]. BP algorithm has been utilized with DNN [116].…”

Genetic Algorithm Based Optimized Feature Engineering and Hybrid Machine Learning for Effective Energy Consumption Prediction

“…Therefore, several nonlinear models have been studied over the past decade, such as artificial neural networks [18], Gaussian process regression [19], recurrent neural networks (RNNs) [20], and LSTM [21] have been studied over the past decade to accommodate the nonlinearity of data in a hybrid forecasting model. Hong et al [22] examined the spatial relationship between different types of appliances to predict individual occupants' short-term strength requirements. An effective short-term Residential prediction framework provides data collection model preprocessing data models, training modules, and load prediction models.…”

From Load to Net Energy Forecasting: Short-Term Residential Forecasting for the Blend of Load and PV Behind the Meter

“…Although the vast majority of research, including the above literature, focuses on the substation level, load forecasting at the low-aggregate level and, particularity, at the single household level have been of interest to researchers in recent years [13][14][15][16][17], mainly due to power system modernization. In this regard, Stephen et al, in [13], apply a clustering technique to provides a forecast for aggregated residential load based on the practice theory of human behavior.…”

“…Thanks to monitoring of the household appliances by separate meters, single customer forecasting improves through more meaningful temporal relationships [16]. Moreover, Hong et al show that the spatial correlations between different appliances used in a household can potentially increase the accuracy of single household load forecasting [17]. However, all the above studies focus on load forecasting, the inclusion of household PV generations behind the meter has been ignored.…”

“…Moreover, a variant of LSTM, called gated recurrent unit (GRU) has been tested in [14]. Application of iterative residual blocks (ResBlocks) in deep neural networks has also been illustrated in extracting spatial and temporal correlations [17]. A predictive model based on the artificial neural networks (ANN) has been developed for the net energy forecasting to apply feature selection technique in the context of lag signals [20].…”