Saved in:
Bibliographic Details
Main Authors: Gadde, Nishant, Alexander, Yoshua, Parthasarthy, Sarvesh, Allidina, Arman
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915538469388288
author Gadde, Nishant
Alexander, Yoshua
Parthasarthy, Sarvesh
Allidina, Arman
author_facet Gadde, Nishant
Alexander, Yoshua
Parthasarthy, Sarvesh
Allidina, Arman
contents Load forecasting has always been a challenge for grid operators due to the growing complexity of power systems. The increase in extreme weather and the need for energy from customers has led to load forecasting sometimes failing. This research presents a Support Vector Regression (SVR) framework for electric load forecasting that outperforms the industry standard. The SVR model demonstrates better accuracy across all evaluation metrics that are important for power system operations. The model has a 54.2\% reduction in Mean Squared Error (31.91 vs. 69.63), a 33.5\% improvement in Mean Absolute Error, and performance benefits across other metrics. These improvements show significant benefits when integrated with power forecasting tools and show that the approach provides an additional tool for accuracy checking for system planning and resource allocation in times of need for resource allocation in electric power systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimized SVR Framework for Electric Load Forecasting
Gadde, Nishant
Alexander, Yoshua
Parthasarthy, Sarvesh
Allidina, Arman
Signal Processing
Load forecasting has always been a challenge for grid operators due to the growing complexity of power systems. The increase in extreme weather and the need for energy from customers has led to load forecasting sometimes failing. This research presents a Support Vector Regression (SVR) framework for electric load forecasting that outperforms the industry standard. The SVR model demonstrates better accuracy across all evaluation metrics that are important for power system operations. The model has a 54.2\% reduction in Mean Squared Error (31.91 vs. 69.63), a 33.5\% improvement in Mean Absolute Error, and performance benefits across other metrics. These improvements show significant benefits when integrated with power forecasting tools and show that the approach provides an additional tool for accuracy checking for system planning and resource allocation in times of need for resource allocation in electric power systems.
title Optimized SVR Framework for Electric Load Forecasting
topic Signal Processing
url https://arxiv.org/abs/2510.06476