Volume 8, Issue 9 (September 2021), Pages: 102-111

----------------------------------------------

 Original Research Paper

 Title: Detecting abnormal electricity usage using unsupervised learning model in unlabeled data

 Author(s): M. Z. H. Jesmeen ¹, G. Ramana Murthy ^2, *, J. Hossen ¹, Jaya Ganesan ³, A. Abd Aziz ¹, K. Tawsif ¹

 Affiliation(s):

 ¹Faculty of Engineering and Technology, Multimedia University, Melaka, Malaysia
 ²Department of Electronics and Communication Engineering, Vignan's Foundation for Science Technology and Research, Vadlamudi, India
 ³Faculty of Business, Multimedia University, Melaka, Malaysia

  Full Text - PDF          XML

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0002-3556-9294

 Digital Object Identifier: 

 https://doi.org/10.21833/ijaas.2021.09.014

 Abstract:

Smart-home systems achieved great popularity in the last decade as they increase the comfort and quality of life. Reduction of energy consumption became a very important desiderate in the context of the explosive technological development of modern society with a major impact on the future development of mankind. Moreover, due to the large amount of data available from smart meters installed in households. It makes leverage to able to find data abnormalities for better monitoring and forecasting. Detecting data anomalies helps in making a better decision for reducing energy usage wasted. In recent years, machine learning models are widely used for developing intelligent systems. Currently, researchers’ main focus is on developing supervised learning models for predicting anomalies. However, there are challenges to train models with unlabeled data indicating data anomaly or not. In this paper, abnormalities are detected in electricity usage using unsupervised learning and evaluated using Excess Mass. The unsupervised anomaly detection model is based on Gaussian Mixture Model (GMM) and Isolation Forest (iForest). The models are compared with Local Outlier Factor (LOF) and One-class support vector machine (OCSVM). The proposed framework is tested with actual electricity usage and temperature data obtained from Numenta Anomaly Benchmark (NAB), which contains normal and anomaly data in time series. Finally, it has been observed that the iForest out-performed as the detection model for the selected use case. The outcome showed that the iForest can quickly detect anomalies in electricity usage data with only a sequence of data without feature extraction. The proposed model is suitable for the Smart Home Energy Management System's practical requirement and can be implemented in various houses independently. The proposed system can also be extended with the various use cases having similar data types. 

 © 2021 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords: Electricity usage, Unsupervised learning, Excess mass, Machine learning, iForest, Gaussian mixture model

 Article History: Received 26 February 2021, Received in revised form 23 May 2021, Accepted 24 June 2021

 Acknowledgment 

No Acknowledgment.

 Funding 

This work was supported in part by Telekom Malaysia under Grant TMRND [MMUE/190007].

 Compliance with ethical standards

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Jesmeen MZH, Murthy GR, and Hossen J et al. (2021). Detecting abnormal electricity usage using unsupervised learning model in unlabeled data. International Journal of Advanced and Applied Sciences, 8(9): 102-111

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 Fig. 6 Fig. 7

 Tables

 Table 1 Table 2 Table 3 Table 4  

----------------------------------------------

 References (19)

1. Ayodele T (2010). Types of machine learning algorithms. In: Zhang Y (Ed.), New advances in machine learning: 19-48. BoD–Books on Demand, Norderstedt, Germany.   [Google Scholar]
2. Carreño A, Inza I, and Lozano JA (2019). Analyzing rare event, anomaly, novelty and outlier detection terms under the supervised classification framework. Artificial Intelligence Review, 53: 3575–3594. https://doi.org/10.1007/s10462-019-09771-y   [Google Scholar]
3. Emerson RJ, Hossen J, Ervina E, Tawsif K, and Jesmeen M (2020). Broadband network fault prediction using complex event processing and predictive analytics techniques. Journal of Engineering Science and Technology, 15(4): 2289-2300.   [Google Scholar]
4. EPA (2018). Sources of greenhouse gas emissions. The United States Environmental Protection Agency, Washington, USA.   [Google Scholar]
5. Garcia-Font V, Garrigues C, and Rifà-Pous H (2018). Difficulties and challenges of anomaly detection in smart cities: A laboratory analysis. Sensors, 18(10): 3198. https://doi.org/10.3390/s18103198   [Google Scholar]
6. Goix N (2016). How to evaluate the quality of unsupervised anomaly detection algorithms? Available online at: https://arxiv.org/abs/1607.01152
7. Hu M, Ji Z, Yan K, Guo Y, Feng X, Gong J, and Dong L (2018). Detecting anomalies in time series data via a meta-feature based approach. IEEE Access, 6: 27760-27776. https://doi.org/10.1109/ACCESS.2018.2840086   [Google Scholar]
8. Jesmeen MZH, Hossen A, Hossen J, Raja JE, Thangavel B, and Sayeed S (2019). AUTO-CDD: Automatic cleaning dirty data using machine learning techniques. Telkomnika, 17(4): 2076-2086. https://doi.org/10.12928/telkomnika.v17i4.12780   [Google Scholar]
9. Jesmeen MZH, Hossen J, Sayeed S, Ho CK, Tawsif K, Rahman A, and Arif EMH (2018). A survey on cleaning dirty data using machine learning paradigm for big data analytics. Indonesian Journal of Electrical Engineering and Computer Science, 10(3): 1234-1243. https://doi.org/10.11591/ijeecs.v10.i3.pp1234-1243   [Google Scholar]
10. Lavin A and Ahmad S (2015). Evaluating real-time anomaly detection algorithms--The Numenta anomaly benchmark. In the IEEE 14^th International Conference on Machine Learning and Applications, IEEE, Miami, USA: 38-44. https://doi.org/10.1109/ICMLA.2015.141   [Google Scholar]
11. Liu FT, Ting KM, and Zhou ZH (2008). Isolation forest. In the 8^th IEEE International Conference on Data Mining, IEEE, Pisa, Italy: 413-422. https://doi.org/10.1109/ICDM.2008.17   [Google Scholar]
12. MEC (2014). Towards a world-class energy sector: Energy commission. Volume 3, Malaysia Energy Commission, Putrajaya, Malaysia.   [Google Scholar]
13. MEC (2019). Shaping the future of Malaysia’s energy sector. Volume 18, Malaysia Energy Commission, Putrajaya, Malaysia.   [Google Scholar]
14. Reynolds D (2009). Gaussian mixture models. In: Li SZ and Jain A (Eds.), Encyclopedia of biometrics: 659–663. Springer, Boston, USA. https://doi.org/10.1007/978-0-387-73003-5_196   [Google Scholar]
15. Saad A and Sisworahardjo N (2017). Data analytics-based anomaly detection in smart distribution network. In the International Conference on High Voltage Engineering and Power Systems, IEEE, Denpasar, Indonesia: 1-5. https://doi.org/10.1109/ICHVEPS.2017.8225855   [Google Scholar]
16. Sheridan K, Puranik TG, Mangortey E, Pinon-Fischer OJ, Kirby M, and Mavris DN (2020). An application of dbscan clustering for flight anomaly detection during the approach phase. In the AIAA SciTech 2020 Forum, Orlando, USA: 1851. https://doi.org/10.2514/6.2020-1851   [Google Scholar]
17. Sial A, Singh A, and Mahanti A (2019). Detecting anomalous energy consumption using contextual analysis of smart meter data. Wireless Networks: 1-18. https://doi.org/10.1007/s11276-019-02074-8   [Google Scholar]
18. Wang X and Ahn SH (2020). Real-time prediction and anomaly detection of electrical load in a residential community. Applied Energy, 259: 114145. https://doi.org/10.1016/j.apenergy.2019.114145   [Google Scholar]
19. Yip SC, Tan WN, Tan C, Gan MT, and Wong K (2018). An anomaly detection framework for identifying energy theft and defective meters in smart grids. International Journal of Electrical Power and Energy Systems, 101: 189-203. https://doi.org/10.1016/j.ijepes.2018.03.025   [Google Scholar]