Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Revisiting Day-ahead Electricity Price: Simple Model Save Millions

Linian Wang, Jianghong Liu, Huibin Zhang, Leye Wang

TL;DR

This work tackles day-ahead electricity price forecasting, where traditional time-series models underutilize the price formation mechanism driven by supply and demand. It introduces CoPiLinear, a Correlation-based Piecewise Linear model that fits a short-term-stable supply curve and derives prices from the intersection with forecasted demand, aided by forecasted capacity inputs. Across Shanxi and ISO New England datasets, CoPiLinear outperforms state-of-the-art TSF and correlation-based baselines, achieving lower MAE and sMAPE and higher revenue alpha, thereby delivering meaningful welfare gains. The approach demonstrates the value of embedding economic priors and supply–demand correlations into forecasting pipelines, offering a practical path to more accurate price forecasts and potential savings for residents.

Abstract

Accurate day-ahead electricity price forecasting is essential for residential welfare, yet current methods often fall short in forecast accuracy. We observe that commonly used time series models struggle to utilize the prior correlation between price and demand-supply, which, we found, can contribute a lot to a reliable electricity price forecaster. Leveraging this prior, we propose a simple piecewise linear model that significantly enhances forecast accuracy by directly deriving prices from readily forecastable demand-supply values. Experiments in the day-ahead electricity markets of Shanxi province and ISO New England reveal that such forecasts could potentially save residents millions of dollars a year compared to existing methods. Our findings underscore the value of suitably integrating time series modeling with economic prior for enhanced electricity price forecasting accuracy.

Revisiting Day-ahead Electricity Price: Simple Model Save Millions

TL;DR

This work tackles day-ahead electricity price forecasting, where traditional time-series models underutilize the price formation mechanism driven by supply and demand. It introduces CoPiLinear, a Correlation-based Piecewise Linear model that fits a short-term-stable supply curve and derives prices from the intersection with forecasted demand, aided by forecasted capacity inputs. Across Shanxi and ISO New England datasets, CoPiLinear outperforms state-of-the-art TSF and correlation-based baselines, achieving lower MAE and sMAPE and higher revenue alpha, thereby delivering meaningful welfare gains. The approach demonstrates the value of embedding economic priors and supply–demand correlations into forecasting pipelines, offering a practical path to more accurate price forecasts and potential savings for residents.

Abstract

Accurate day-ahead electricity price forecasting is essential for residential welfare, yet current methods often fall short in forecast accuracy. We observe that commonly used time series models struggle to utilize the prior correlation between price and demand-supply, which, we found, can contribute a lot to a reliable electricity price forecaster. Leveraging this prior, we propose a simple piecewise linear model that significantly enhances forecast accuracy by directly deriving prices from readily forecastable demand-supply values. Experiments in the day-ahead electricity markets of Shanxi province and ISO New England reveal that such forecasts could potentially save residents millions of dollars a year compared to existing methods. Our findings underscore the value of suitably integrating time series modeling with economic prior for enhanced electricity price forecasting accuracy.
Paper Structure (29 sections, 2 equations, 17 figures, 5 tables)

This paper contains 29 sections, 2 equations, 17 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminary and Problem Formulation
  4. Day-ahead Electricity Market Structure
  5. Limitation of Time Series Forecasting Models
  6. Problem Formulation
  7. Methodology
  8. Framework Overview
  9. Short-term Stability Assumptions
  10. Fitting Supply Curve by CoPiLinear
  11. Forecast related variables
  12. Evaluation
  13. Datasets and Baselines
  14. Experiment Settings and Evaluation Metric
  15. Results and Analysis
  16. ...and 14 more sections

Figures (17)

  • Figure 1: Overview of CoPiLinear.
  • Figure 2: Shanxi market transaction process.
  • Figure 5: Left Image: The green curve shows varying demand over time, while the blue curve represents a stable supply. Their intersection points indicate market prices. Right Image: The scatter points represent supply-demand intersections over time, from which a supply curve can be derived.
  • Figure 6: Shanxi market transaction process.
  • Figure 7: Shanxi market transaction process.
  • ...and 12 more figures