A Hybrid Neural Network Model for Power Demand Forecasting

Abstract

The problem of power demand forecasting for the effective planning and operation of smart grid, renewable energy and electricity market bidding systems is an open challenge. Numerous research efforts have been proposed for improving prediction performance in practical environments through statistical and artificial neural network approaches. Despite these efforts, power demand forecasting problems remain to be a grand challenge since existing methods are not sufficiently practical to be widely deployed due to their limited accuracy. To address this problem, we propose a hybrid power demand forecasting model, called (c, l)-Long Short-Term Memory (LSTM) + Convolution Neural Network (CNN). We consider the power demand as a key value, while we incorporate c different types of contextual information such as temperature, humidity and season as context values in order to preprocess datasets into bivariate sequences consisting of <Key, Context[1, c]> pairs. These c bivariate sequences are then input into c LSTM networks with l layers to extract feature sets. Using these feature sets, a CNN layer outputs a predicted profile of power demand. To assess the applicability of the proposed hybrid method, we conduct extensive experiments using real-world datasets. The results of the experiments indicate that the proposed (c, l)-LSTM+CNN hybrid model performs with higher accuracy than previous approaches.

A Hybrid LSTM Neural Network for Energy Consumption Forecasting of Individual Households

“…The forecasting results were further extended to a time interval of half an hour through a multi-step forecasting strategy that was proposed by the same study. Kim et al [20] proposed a hybrid power demand forecasting model, combining (c, l)-LSTM and CNN, for very short-term forecasting. The input sequence consists of multiple [Key, Context] pairs, where the key value is the power demand value; and context values include contextual information, such as temperature, humidity and season.…”

Energy Flexibility Prediction for Data Center Engagement in Demand Response Programs

“…In the context of DR programs hybrid ensemble-based approaches can obtain better results for complex models [37]. The authors of [38] propose a hybrid SVM model to forecast the hourly electricity demand of buildings while several articles report good energy forecasting results using hybrid models of convolutional neural network (CNN) and LSTM [39][40][41]. In [42], multiple CNN components are employed to extract rich features from the historical load sequence and an LSTM based recurrent neural component is used to model the variability and dynamics of historical energy data.…”

Genetic Algorithm Approach to Design of Multi-Layer Perceptron for Combined Cycle Power Plant Electrical Power Output Estimation

“…There are many approaches to solving ANN model selection problem such as: grid search [44,45], Bayesian model selection [46], etc. Another method for solving MLP model selection problem is a heuristic approach [47][48][49].…”