Research on large-scale data anomaly detection based on edge computing and LSTM method

Dan Ji

International Journal of Low-Carbon Technologies, 2025, vol. 20, 1292-1299

Abstract: This study proposes a comprehensive solution that integrates edge computing and deep learning techniques to address the anomaly detection problem in large-scale power load data. The model introduced herein combines Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Random Forest (RF) models to efficiently capture the spatiotemporal characteristics of power load data. Moreover, by conducting data preprocessing and feature extraction on edge devices, this approach significantly reduces data transmission latency and bandwidth requirements. The research findings indicate that the proposed model achieves an anomaly detection accuracy of 93% on large-scale datasets.

Keywords: edge computing; BiLSTM; power industry; anomaly detection (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctaf086 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:20:y:2025:i::p:1292-1299.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().