A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Das, Subhabrata, Khan, Bodruzzaman, Liu, Xiao-Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915504723066880
author Das, Subhabrata
Khan, Bodruzzaman
Liu, Xiao-Yang
author_facet Das, Subhabrata
Khan, Bodruzzaman
Liu, Xiao-Yang
contents Accurately forecasting power outages is a complex task influenced by diverse factors such as weather conditions [1], vegetation, wildlife, and load fluctuations. These factors introduce substantial variability and noise into outage data, making reliable prediction challenging. Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN), are particularly effective for modeling nonlinear and dynamic time-series data, with proven applications in stock price forecasting [2], energy demand prediction, demand response [3], and traffic flow management [4]. This paper introduces a hybrid deep learning framework, termed PCA-PR-Seq2Seq-Adam-LSTM, that integrates Principal Component Analysis (PCA), Poisson Regression (PR), a Sequence-to-Sequence (Seq2Seq) architecture, and an Adam-optimized LSTM. PCA is employed to reduce dimensionality and stabilize data variance, while Poisson Regression effectively models discrete outage events. The Seq2Seq-Adam-LSTM component enhances temporal feature learning through efficient gradient optimization and long-term dependency capture. The framework is evaluated using real-world outage records from Michigan, and results indicate that the proposed approach significantly improves forecasting accuracy and robustness compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction
Das, Subhabrata
Khan, Bodruzzaman
Liu, Xiao-Yang
Machine Learning
Artificial Intelligence
Accurately forecasting power outages is a complex task influenced by diverse factors such as weather conditions [1], vegetation, wildlife, and load fluctuations. These factors introduce substantial variability and noise into outage data, making reliable prediction challenging. Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN), are particularly effective for modeling nonlinear and dynamic time-series data, with proven applications in stock price forecasting [2], energy demand prediction, demand response [3], and traffic flow management [4]. This paper introduces a hybrid deep learning framework, termed PCA-PR-Seq2Seq-Adam-LSTM, that integrates Principal Component Analysis (PCA), Poisson Regression (PR), a Sequence-to-Sequence (Seq2Seq) architecture, and an Adam-optimized LSTM. PCA is employed to reduce dimensionality and stabilize data variance, while Poisson Regression effectively models discrete outage events. The Seq2Seq-Adam-LSTM component enhances temporal feature learning through efficient gradient optimization and long-term dependency capture. The framework is evaluated using real-world outage records from Michigan, and results indicate that the proposed approach significantly improves forecasting accuracy and robustness compared to existing methods.
title A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.16743