A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources

Shuman Luo, Yang Weng

Research output: Contribution to journalArticle

Abstract

Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved.

Original languageEnglish (US)
Pages (from-to)1497-1512
Number of pages16
JournalApplied Energy
Volume242
DOIs
StatePublished - May 15 2019

Fingerprint

Supervised learning
electricity
Electricity
forecasting method
Learning systems
Wind power
wind power
method
price
supervised learning
Polynomials
Neural networks
Economics
penetration
learning
market
economics
modeling
energy
Power markets

Keywords

  • Electricity price forecast
  • Machine learning methods
  • Renewables
  • Wind power generation

ASJC Scopus subject areas

  • Building and Construction
  • Energy(all)
  • Mechanical Engineering
  • Management, Monitoring, Policy and Law

Cite this

A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources. / Luo, Shuman; Weng, Yang.

In: Applied Energy, Vol. 242, 15.05.2019, p. 1497-1512.

Research output: Contribution to journalArticle

@article{90208f4d2080406dbcd0e525e5016add,
title = "A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources",
abstract = "Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved.",
keywords = "Electricity price forecast, Machine learning methods, Renewables, Wind power generation",
author = "Shuman Luo and Yang Weng",
year = "2019",
month = "5",
day = "15",
doi = "10.1016/j.apenergy.2019.03.129",
language = "English (US)",
volume = "242",
pages = "1497--1512",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources

AU - Luo, Shuman

AU - Weng, Yang

PY - 2019/5/15

Y1 - 2019/5/15

N2 - Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved.

AB - Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved.

KW - Electricity price forecast

KW - Machine learning methods

KW - Renewables

KW - Wind power generation

UR - http://www.scopus.com/inward/record.url?scp=85063406671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063406671&partnerID=8YFLogxK

U2 - 10.1016/j.apenergy.2019.03.129

DO - 10.1016/j.apenergy.2019.03.129

M3 - Article

VL - 242

SP - 1497

EP - 1512

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -