A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features

Abstract

With economic growth, the demand for power systems is increasingly large. Short-term load forecasting (STLF) becomes an indispensable factor to enhance the application of a smart grid (SG). Other than forecasting aggregated residential loads in a large scale, it is still an urgent problem to improve the accuracy of power load forecasting for individual energy users due to high volatility and uncertainty. However, as an important variable that affects the power consumption pattern, the influence of weather factors on residential load prediction is rarely studied. In this paper, we review the related research of power load forecasting and introduce a short-term residential load forecasting model based on a long short-term memory (LSTM) recurrent neural network with weather features as an input.

Entropy-Based Anomaly Detection in Household Electricity Consumption

“…It should be noted that the diversity of these investigations is wide in the techniques applied, sampling frequency, and time span of the datasets. Besides, the study is conditioned to the extension of the monitored area since the household electricity consumption is influenced by external such as the habits of the dwellers [22].…”

“…Input Features [27] MLR, RT, SVR, RNN, ARIMA calendar effects, historical data [28] CNN-LSTM, LSTM, ARIMA, SVR [29] probabilistic models calendar effects, historical data, temperature [30] LR, DT, DNN RNN, LSTM, GRU temporal information [31] CNN-LSTM, LR, DT, RF, MLP, LSTM, GRU calendar effects, household characteristics, [22] LSTM weather features 1 The abbreviations of the models are found in the glossary at the end of the paper.…”

“…Some research focuses on predictions considering meteorological factors. In [29], the authors used outdoor temperature, while [22] took into account different weather characteristics. Wang et al [22] analyzed different users, and the results showed that weather features increase prediction accuracy.…”

“…In [29], the authors used outdoor temperature, while [22] took into account different weather characteristics. Wang et al [22] analyzed different users, and the results showed that weather features increase prediction accuracy. Although this improvement depends on behavior, if users are not susceptible to weather changes, the prediction will not be better.…”

Short-Term Load Probabilistic Forecasting Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Reconstruction and Salp Swarm Algorithm

“…Rafi et al [27] used convolutional neural networks combined with long-and short-term memory networks to construct a prediction model for short-term electricity load forecasting and achieved good prediction reliability. Wang et al [28] used a long-and short-term memory network to forecast short-term residential loads with consideration of weather features. Phyo et al [29] used classification and regression tree and the deep belief network for 30-min granularity load forecasting.…”