Saved in:
Bibliographic Details
Main Authors: Ahmadi, Amirhossein, Zareipour, Hamidreza, Leung, Henry
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.11729
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916845161807872
author Ahmadi, Amirhossein
Zareipour, Hamidreza
Leung, Henry
author_facet Ahmadi, Amirhossein
Zareipour, Hamidreza
Leung, Henry
contents Forecasting load in power transmission networks is essential across various hierarchical levels, from the system level down to individual points of delivery (PoD). While intuitive and locally accurate, traditional local forecasting models (LFMs) face significant limitations, particularly in handling generalizability, overfitting, data drift, and the cold start problem. These methods also struggle with scalability, becoming computationally expensive and less efficient as the network's size and data volume grow. In contrast, global forecasting models (GFMs) offer a new approach to enhance prediction generalizability, scalability, accuracy, and robustness through globalization and cross-learning. This paper investigates global load forecasting in the presence of data drifts, highlighting the impact of different modeling techniques and data heterogeneity. We explore feature-transforming and target-transforming models, demonstrating how globalization, data heterogeneity, and data drift affect each differently. In addition, we examine the role of globalization in peak load forecasting and its potential for hierarchical forecasting. To address data heterogeneity and the balance between globality and locality, we propose separate time series clustering (TSC) methods, introducing model-based TSC for feature-transforming models and new weighted instance-based TSC for target-transforming models. Through extensive experiments on a real-world dataset of Alberta's electricity load, we demonstrate that global target-transforming models consistently outperform their local counterparts, especially when enriched with global features and clustering techniques. In contrast, global feature-transforming models face challenges in balancing local and global dynamics, often requiring TSC to manage data heterogeneity effectively.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11729
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Globalization for Scalable Short-term Load Forecasting
Ahmadi, Amirhossein
Zareipour, Hamidreza
Leung, Henry
Machine Learning
Artificial Intelligence
Forecasting load in power transmission networks is essential across various hierarchical levels, from the system level down to individual points of delivery (PoD). While intuitive and locally accurate, traditional local forecasting models (LFMs) face significant limitations, particularly in handling generalizability, overfitting, data drift, and the cold start problem. These methods also struggle with scalability, becoming computationally expensive and less efficient as the network's size and data volume grow. In contrast, global forecasting models (GFMs) offer a new approach to enhance prediction generalizability, scalability, accuracy, and robustness through globalization and cross-learning. This paper investigates global load forecasting in the presence of data drifts, highlighting the impact of different modeling techniques and data heterogeneity. We explore feature-transforming and target-transforming models, demonstrating how globalization, data heterogeneity, and data drift affect each differently. In addition, we examine the role of globalization in peak load forecasting and its potential for hierarchical forecasting. To address data heterogeneity and the balance between globality and locality, we propose separate time series clustering (TSC) methods, introducing model-based TSC for feature-transforming models and new weighted instance-based TSC for target-transforming models. Through extensive experiments on a real-world dataset of Alberta's electricity load, we demonstrate that global target-transforming models consistently outperform their local counterparts, especially when enriched with global features and clustering techniques. In contrast, global feature-transforming models face challenges in balancing local and global dynamics, often requiring TSC to manage data heterogeneity effectively.
title Globalization for Scalable Short-term Load Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.11729