Forecdiction of electricity price intervals for dynamic Bayesian networks

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

The increasing volatility of electricity prices, driven by the growing share of renewable energy in the market, calls for a new approach to interval prediction. This paper proposes a dynamic Bayesian network (DBN) method for electricity price range forecasting. The model uses predicted values of wind power generation, total power generation, total electricity consumption, and historical electricity prices as input data. The network structure is determined using a greedy search algorithm, and the model parameters are estimated through maximum likelihood estimation (MLE).By treating the predicted values of wind power generation, total power generation, and total electricity consumption as reasoning evidence, the method employs joint tree reasoning to generate discrete values and posterior probabilities for electricity price predictions, enabling interval forecasting. The DBN-based interval prediction results achieve a forecast interval coverage probability (PICP) of 95.24%, a normalized average width of forecast interval (PINAW) of 9.25%, and a cumulative width deviation (AWD) of 0.56%.The proposed method?s effectiveness was evaluated by comparing its predictions with actual electricity prices and with results from PSO-KELM methods. This innovative approach not only provides prediction intervals for electricity prices but also associates them with corresponding probabilities, offering significant potential to enhance market participants' decision-making and mitigate price risks.

Article activity feed