Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting

Abstract

Load forecasting is critical for power system operation and market planning. With the increased penetration of renewable energy and the massive consumption of electric energy, improving load forecasting accuracy has become a difficult task. Recently, it was demonstrated that deep learning models perform well for short-term load forecasting (STLF). However, prior research has demonstrated that the hybrid deep learning model outperforms the single model. We propose a hybrid neural network in this article that combines elements of a convolutional neural network (1D-CNN) and a long short memory network (LSTM) in novel ways. Multiple independent 1D-CNNs are used to extract load, calendar, and weather features from the proposed hybrid model, while LSTM is used to learn time patterns. This architecture is referred to as a CNN-LSTM network with multiple heads (MCNN-LSTM). To demonstrate the proposed hybrid deep learning model's superior performance, the proposed method is applied to Ireland's load data for single-step and multi-step load forecasting. In comparison to the widely used CNN-LSTM hybrid model, the proposed model improved single-step prediction by 16.73% and 24-step load prediction by 20.33%. Additionally, we use the Maine dataset to verify the proposed model's generalizability.INDEX TERMS short-term load forecast, deep learning, multi-head CNN-LSTM, multi-step load prediction.

P-ConvLSTM: An Effective Parallel ConvLSTM-based model for Short-term Electricity Load Forecasting

“…This ensemble model provides improved and stable forecasted results. Another hybrid STLF model is presented in [24] that uses multi-headed CNN to extract features from independent variables and LSTM layers to process these features. Work in [25] suggested a model that combined empirical mode decomposition and neural network.…”

“…This network architecture has multiple input nodes that can take as many inputs as there are features in the dataset. Individual input sequences of size 96 are converted to multidimensional input of shape (4,24), corresponding to 4 days with 24-hour entries. These multidimensional inputs are processed independently through separate network branches, each specialized for modeling a specific feature.…”

Short-Term Load Forecasting and Associated Weather Variables Prediction Using ResNet-LSTM Based Deep Learning

“…In [47], the merged particle swarm optimization with fuzzy neural networks is proposed. A neural network was proposed that combined elements of a convolutional neural network (CNN) and a long short memory network (LSTM) in [48].…”

Short-term load forecasting based on CEEMDAN-FE-ISSA-LightGBM model

“…It is difficult to meet the conditions needed for them because of the non-smoothness and randomness of the electric load. Machine learning methods mainly include artificial neural networks (Goh et al, 2021), support vector machines (Liu et al, 2018), and decision tree models (Song et al, 2021), which can better deal with non-linear problems, especially decision tree models, which have unique advantages in solving prediction problems. The literature (Yao et al, 2022) achieved power prediction of electric loads based on the LightGBM algorithm to screen features and make predictions.…”