Power Market Price Forecasting via Deep Learning

Abstract

A study on power market price forecasting by deep learning is presented. As one of the most successful deep learning frameworks, the LSTM (Long short-term memory) neural network is utilized. The hourly prices data from the New England and PJM day-ahead markets are used in this study. First, a LSTM network is formulated and trained. Then the raw input and output data are preprocessed by unit scaling, and the trained network is tested on the real price data under different input lengths, forecasting horizons and data sizes. Its performance is also compared with other existing methods. The forecasted results demonstrate that, the LSTM deep neural network can outperform the others under different application settings in this problem.

Multi-Horizon Electricity Load and Price Forecasting Using an Interpretable Multi-Head Self-Attention and EEMD-Based Framework

“…Multiple forecasting frameworks premised around LSTM have been proposed for electricity price forecasting [17], [18] and load forecasting [19]. In study [20], authors have investigated the performance of LSTM network in comparison to support vector machines for different forecasting horizons on electricity price dataset. The study in [21] focuses on analyzing the key factors that influenced the electricity load and price forecasting.…”

Exploring Time-Series Forecasting Models for Dynamic Pricing in Digital Signage Advertising

“…RNN is a variation of ANN [117] with a feedback architecture that contains a feedback loop for later layers of the network to go back to the input layer. RNN has been proven to be a suitable method for time-series forecasting, as exemplified by the studies in forecasting the prices of stock [71][72][73][74][75], Bitcoin [76], fuel [77], gold [78], electricity [79][80][81], and agricultural [82] from 2006 to 2020. The introduced hidden state in RNN with the ability to memorize previous information helps improve its forecasting capability, even though the data scale is more extensive [82].…”

PVHybNet: a hybrid framework for predicting photovoltaic power generation using both weather forecast and observation data

“…DFN is a widely used choice for 24-hour-long prediction using weather forecast data in other studies as well [6,7]. Among the family of RNNs, the long short-term memory (LSTM) networks are well known to provide better performance than the vanilla RNN [26], and widely used for other applications as well [27][28][29][30]. Thus, several studies implement LSTM networks to capture the temporal dependence of the predictor variables [8,13,14,26].…”