Prediction of Power System Ramping Demand Using Meteorological Features

Power system ramping demand consists of deterministic and uncertain components. This study focuses on predicting uncertain ramping demand influenced by meteorological factors. First, an adaptive trend identification algorithm is proposed to extract key features of upward and downward ramps, includin...

Full description

Saved in:
Bibliographic Details
Main Authors: Kuan Lu, Song Gao, Jun Li, Kang Chen, Chunhao Yu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10988543/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261371040563200
author Kuan Lu
Song Gao
Jun Li
Kang Chen
Chunhao Yu
author_facet Kuan Lu
Song Gao
Jun Li
Kang Chen
Chunhao Yu
author_sort Kuan Lu
collection DOAJ
description Power system ramping demand consists of deterministic and uncertain components. This study focuses on predicting uncertain ramping demand influenced by meteorological factors. First, an adaptive trend identification algorithm is proposed to extract key features of upward and downward ramps, including magnitude and duration. Multidimensional correlation analysis quantifies the relationships among net load characteristics, historical load forecasts, weather predictions, historical prediction errors, and uncertain ramping demands. The minimum redundancy maximum relevance (mRMR) method is applied to compress input data features, and a TimeXer-modified prediction framework is developed to capture long-term dependencies in time-series data while integrating meteorological features through attention mechanisms, outputting confidence intervals for uncertain ramping demand. To enhance performance under extreme weather conditions, a method for defining extreme weather indicators is proposed, establishing thresholds based on historical meteorological data distributions and creating binary features for each time step to denote extreme weather. The original TimeXer model’s output layer is modified to predict both the mean and variance of ramping demand, addressing uncertainty in extreme weather scenarios. A Gaussian negative log-likelihood loss function is employed for training to optimize uncertainty prediction performance. Validation using 2024 and 2025 operational data from Shandong, China, indicates that the proposed model improves prediction accuracy by 18.4%, achieves a 92.5% interval coverage rate, and produces narrower prediction interval bandwidths under equivalent coverage rates.
format Article
id doaj-art-147965c4dd3e4b0c86f89ecc9bfceb38
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-147965c4dd3e4b0c86f89ecc9bfceb382025-08-20T01:55:27ZengIEEEIEEE Access2169-35362025-01-0113857758578810.1109/ACCESS.2025.356714510988543Prediction of Power System Ramping Demand Using Meteorological FeaturesKuan Lu0https://orcid.org/0000-0003-2693-3995Song Gao1Jun Li2Kang Chen3https://orcid.org/0000-0002-0072-2463Chunhao Yu4State Grid Shandong Electric Power Research Institute, Jinan, Shandong, ChinaState Grid Shandong Electric Power Research Institute, Jinan, Shandong, ChinaState Grid Shandong Electric Power Research Institute, Jinan, Shandong, ChinaState Grid Shandong Electric Power Company, Jinan, Shandong, ChinaState Grid Shandong Electric Power Research Institute, Jinan, Shandong, ChinaPower system ramping demand consists of deterministic and uncertain components. This study focuses on predicting uncertain ramping demand influenced by meteorological factors. First, an adaptive trend identification algorithm is proposed to extract key features of upward and downward ramps, including magnitude and duration. Multidimensional correlation analysis quantifies the relationships among net load characteristics, historical load forecasts, weather predictions, historical prediction errors, and uncertain ramping demands. The minimum redundancy maximum relevance (mRMR) method is applied to compress input data features, and a TimeXer-modified prediction framework is developed to capture long-term dependencies in time-series data while integrating meteorological features through attention mechanisms, outputting confidence intervals for uncertain ramping demand. To enhance performance under extreme weather conditions, a method for defining extreme weather indicators is proposed, establishing thresholds based on historical meteorological data distributions and creating binary features for each time step to denote extreme weather. The original TimeXer model’s output layer is modified to predict both the mean and variance of ramping demand, addressing uncertainty in extreme weather scenarios. A Gaussian negative log-likelihood loss function is employed for training to optimize uncertainty prediction performance. Validation using 2024 and 2025 operational data from Shandong, China, indicates that the proposed model improves prediction accuracy by 18.4%, achieves a 92.5% interval coverage rate, and produces narrower prediction interval bandwidths under equivalent coverage rates.https://ieeexplore.ieee.org/document/10988543/Ramping demand predictionmeteorological factorsTimeXer modelmRMR feature selectionGaussian negative log-likelihood
spellingShingle Kuan Lu
Song Gao
Jun Li
Kang Chen
Chunhao Yu
Prediction of Power System Ramping Demand Using Meteorological Features
IEEE Access
Ramping demand prediction
meteorological factors
TimeXer model
mRMR feature selection
Gaussian negative log-likelihood
title Prediction of Power System Ramping Demand Using Meteorological Features
title_full Prediction of Power System Ramping Demand Using Meteorological Features
title_fullStr Prediction of Power System Ramping Demand Using Meteorological Features
title_full_unstemmed Prediction of Power System Ramping Demand Using Meteorological Features
title_short Prediction of Power System Ramping Demand Using Meteorological Features
title_sort prediction of power system ramping demand using meteorological features
topic Ramping demand prediction
meteorological factors
TimeXer model
mRMR feature selection
Gaussian negative log-likelihood
url https://ieeexplore.ieee.org/document/10988543/
work_keys_str_mv AT kuanlu predictionofpowersystemrampingdemandusingmeteorologicalfeatures
AT songgao predictionofpowersystemrampingdemandusingmeteorologicalfeatures
AT junli predictionofpowersystemrampingdemandusingmeteorologicalfeatures
AT kangchen predictionofpowersystemrampingdemandusingmeteorologicalfeatures
AT chunhaoyu predictionofpowersystemrampingdemandusingmeteorologicalfeatures