Smart City Gnosys
Smart city article details
| Title | Anomaly Detection In Smart Home Electrical Appliances Using Machine Learning With Statistical Algorithms And Optimized Time Series Algorithms |
|---|---|
| ID_Doc | 9623 |
| Authors | Galeb B.; Saad H.; Bashar H.; Al-Majdi K.; Al-Hilali A. |
| Year | 2024 |
| Published | Journal of Mechanics of Continua and Mathematical Sciences, 19, 5 |
| DOI | http://dx.doi.org/10.26782/jmcms.2024.05.00008 |
| Abstract | Over the last several years, there has been a significant increase in the amount of focus placed on the infrastructure development of smart cities. The primary issue that academics are attempting to address is the issue of energy efficiency. One of these issues was the identification of anomalies in energy usage, which was an essential component that needed to be taken into consideration when managing energy-saving systems that were efficient, hence lowering the total energy consumption and carbon emissions. Therefore, the proposal of a strong approach that is based on the Internet of Things (IoT) might provide more relevance for the identification of abnormal consumption in buildings and the provision of this information to customers and governments so that it can be handled in an appropriate manner to minimize payments. Consequently, the purpose of this work is to explore three different optimization methods, namely ADAM, AadMax, and Nadam, and to advocate for an optimization approach that makes use of the LSTM algorithm to identify anomalies. Statistical modelling techniques such as ARIMA and SARIMAX are used for the purpose of time series forecasting. The findings of the anomaly detection system reveal that the best results are obtained by using LSTM in conjunction with Nadar. The MSE and RMSE values reached were 0.15348 and 0.02356 respectively. Additionally, the ARIMA model yields the best overall results, with the AIC value being 0.13859 and the MSE value being 300.94365 correspondingly. Confirmation of the suggested model's dependability and flexibility in optimizing anomaly detection is provided by this particular fact. © 2024, Institute of Mechanics of Continua and Mathematical Sciences. All rights reserved. |
| Author Keywords | Abnormal Consumption; Anomaly Detection System; Energy-saving Systems; Statistical Modelling Techniques; Time Series Forecasting |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
35909  | 0.925 | Malki A.; Atlam E.-S.; Gad I. | Machine Learning Approach Of Detecting Anomalies And Forecasting Time-Series Of Iot Devices | Alexandria Engineering Journal, 61, 11 (2022) |
| 33828 | 0.892 | Gonzalez-Vidal A.; Cuenca-Jara J.; Skarmeta A.F. | Iot For Water Management: Towards Intelligent Anomaly Detection | IEEE 5th World Forum on Internet of Things, WF-IoT 2019 - Conference Proceedings (2019) |
| 23175 | 0.889 | Solís-Villarreal J.-A.; Soto-Mendoza V.; Navarro-Acosta J.A.; Ruiz-y-Ruiz E. | Energy Consumption Outlier Detection With Ai Models In Modern Cities: A Case Study From North-Eastern Mexico | Algorithms, 17, 8 (2024) |
| 19180 | 0.887 | Mund C.; Altherr L.C. | Detecting Anomalous Energy Consumptions In Smart Buildings - An Overview Of Two Unsupervised Techniques | Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 (2022) |
| 19250 | 0.883 | Śmiałkowski T.; Czyżewski A. | Detection Of Anomalies In The Operation Of A Road Lighting System Based On Data From Smart Electricity Meters | Energies, 15, 24 (2022) |
| 43509 | 0.864 | Hasani Z.; Krrabaj S.; Krasniqi M. | Proposed Model For Real-Time Anomaly Detection In Big Iot Sensor Data For Smart City | International Journal of Interactive Mobile Technologies, 18, 3 (2024) |
| 32368 | 0.86 | Ulloa-Vasquez F.; Garcia-Santander L.; Carrizo D.; Heredia-Figueroa V. | Intelligent Electrical Pattern Recognition Of Appliances Consumption For Home Energy Management Using High Resolution Measurement | IEEE Latin America Transactions, 20, 2 (2022) |
| 9645 | 0.86 | Zhou W.; Chen C.; Yan Q.; Li B.; Liu K.; Zheng Y.; Yang H.; Xiao H.; Su S. | Anomaly Usage Behavior Detection Based On Multi-Source Water And Electricity Consumption Information | IEEE Access, 13 (2025) |
| 33619 | 0.856 | Chatterjee A.; Ahmed B.S. | Iot Anomaly Detection Methods And Applications: A Survey | Internet of Things (Netherlands), 19 (2022) |
| 33620 | 0.852 | Villegas-Ch W.; Govea J.; Jaramillo-Alcazar A. | Iot Anomaly Detection To Strengthen Cybersecurity In The Critical Infrastructure Of Smart Cities | Applied Sciences (Switzerland), 13, 19 (2023) |