Multi-Step-Ahead Electricity Price Forecasting Based on Temporal Graph Convolutional Network
نویسندگان
چکیده
Traditional electricity price forecasting tends to adopt time-domain methods based on time series, which fail make full use of the regional information market, and ignore extra-territorial factors affecting within region under cross-regional transmission conditions. In order improve accuracy forecasting, this paper proposes a novel spatio-temporal prediction model, is combined with graph convolutional network (GCN) temporal (TCN). First, model automatically extracts relationships between areas through construction module. Then, mix-jump GCN used capture spatial dependence, dilated splicing TCN dependence forecast for all areas. The results show that outperforms other models in both one-step multi-step indicating has superior performance forecasting.
منابع مشابه
A Hybrid Multi-Step Model for Forecasting Day-Ahead Electricity Price Based on Optimization, Fuzzy Logic and Model Selection
The day-ahead electricity market is closely related to other commodity markets such as the fuel and emission markets and is increasingly playing a significant role in human life. Thus, in the electricity markets, accurate electricity price forecasting plays significant role for power producers and consumers. Although many studies developing and proposing highly accurate forecasting models exist...
متن کاملA Hybrid Artificial Neural Network and VEPSO based on Day-ahead Price Forecasting of Electricity Markets
In this paper a new Hybrid technique of Artificial Neural Network (ANN) and Vector Evaluated Particle Swarm Optimization (VEPSO) is presented as a forecasting strategy for day-ahead price of electricity market. The proposed technique the proposed intelligent technique is applied to weights and bias of ANN to improve the learning capability through the minimum error. A comprehensive comparative ...
متن کاملWavelets in Multi-step-ahead Forecasting
This paper investigates the possibility of obtaining long-into-the-future reliable forecasts of observed nonlinear cyclical phenomena. Unsmoothed monthly sunspot numbers that are characteristically cyclical with nonlinear dynamics as well as their wavelet-transformed and wavelet-denoised series are forecasted through October 2008. The objective is to determine whether modelling wavelet-conversi...
متن کاملDay-Ahead Electricity Price Forecasting Using a Hybrid Principal Component Analysis Network
Bidding competition is one of the main transaction approaches in a deregulated electricity market. Locational marginal prices (LMPs) resulting from bidding competition and system operation conditions indicate electricity values at a node or in an area. The LMP reveals important information for market participants in developing their bidding strategies. Moreover, LMP is also a vital indicator fo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematics
سال: 2022
ISSN: ['2227-7390']
DOI: https://doi.org/10.3390/math10142366