Deep Reinforcement Learning Ensemble for Detecting Anomaly in Telemetry Water Level Data

Khampuengson, Thakolpat and Wang, Wenjia (2022) Deep Reinforcement Learning Ensemble for Detecting Anomaly in Telemetry Water Level Data. Water, 14 (16). ISSN 2073-4441

Preview

PDF (Deep Reinforcement Learning Ensemble for Detecting Anomaly in Telemetry Water Level Data -water-2022) - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Water levels in rivers are measured by various devices installed mostly in remote locations along the rivers, and the collected data are then transmitted via telemetry systems to a data centre for further analysis and utilisation, including producing early warnings for risk situations. So, the data quality is essential. However, the devices in the telemetry station may malfunction and cause errors in the data, which can result in false alarms or missed true alarms. Finding these errors requires experienced humans with specialised knowledge, which is very time-consuming and also inconsistent. Thus, there is a need to develop an automated approach. In this paper, we firstly investigated the applicability of Deep Reinforcement Learning (DRL). The testing results show that whilst they are more accurate than some other machine learning models, particularly in identifying unknown anomalies, they lacked consistency. Therefore, we proposed an ensemble approach that combines DRL models to improve consistency and also accuracy. Compared with other models, including Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM), our ensemble models are not only more accurate in most cases, but more importantly, more reliable.

Item Type:	Article
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and Statistics
Depositing User:	LivePure Connector
Date Deposited:	15 Dec 2022 03:50
Last Modified:	20 May 2023 01:29
URI:	https://ueaeprints.uea.ac.uk/id/eprint/90067
DOI:	10.3390/w14162492

Downloads

Actions (login required)

View Item