Detecting Abnormal Human Behavior in Microgrid Based on Machine Learning
Article Sidebar
Main Article Content
Abstract
Development of electronic systems and intellectual controls and information exchange has led to the formation of a new informatics and energy concept SmartGrid, which addresses the local electrical engineering objects - MicroGrid. MicroGrid contains a certain set of sources and loads that are typically connected to a centralized power grid. As part of MicroGrid, there are a number of management and device-specific tasks that result in the need to handle large information flows. Compared to fully automated systems, Microgrid is characterized by the presence of a person, which leads to the need to take into account subjective factors - the presence of a person, its interference in the functioning of electrical equipment and the impact of his actions on the working modes of the whole system. The presence of a human factor leads to the need to operate large volumes of data. In turn, it forces researchers to turn to specialized methods of working with large data (Big Data). Big Data is a series of approaches, tools and methods for processing structured and unstructured data of large volumes to produce results that are suitable for human perception and effective in the conditions of their continuous increase. To solve the problem of processing large amounts of data, it is necessary to use methods of machine learning (Machine Learning). Machine Learning as a branch of informatics uses statistical techniques to give computer systems the ability to "learn" (that is, to gradually improve performance in a particular task) without explicit programming. In this paper, Anomaly Detection was considered as one of the Machine Learning tools for defining anomalies in MicroGrid. One of the regime in MicroGrid that was considered as anomaly is non-usual activity, non-typical behavior of the person – “human factor”. Research directed to revealing of non-typical (abnormal) behavioral models is topical for the systems of psycho-physiological monitoring of elderly people, persons who need constant observation and care, persons in post-stress condition or under the extraordinary conditions. Subjective factors, in turn, can cause the appearance of emissions as a result of false interpretation or unauthorized human intervention in the work of technical equipment. In the analysis of behavioral characteristics, the task of choosing from the whole set of parameters describing the behavior and movement of a person, the very decisive parameters on the basis of which it is possible to detect emissions or novelty of behavior. In the application to distributed generation MicroGrid, the problem of detecting user behavior abnormalities is considered. The problem is solved by the use of Machine Learning methods, in particular, the Anomaly Detection method. As the key parameters for the simplest case of detecting abnormal behavior, we consider the average power consumption at five-minute intervals, as well as the number of triggers of the motion sensor installed in the MicroGrid indoor space.
Ref. 12, fig. 4, tabl. 2.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
T. M. Baziuk, I. V. Blinovv, O. F. Butkevich, I. S. Honcharenko, S. P. Denysiuk, and et. al., Intelektualʹni elektrychni merezhi: elementy ta rezhymy [Intelligent Electric Networks: Elements and Modes]. Kyiv, Ukraine: The National Academy of Sciences of Ukraine The Institute of Electrodynamics, 2016, ISBN: 978-966-02-7913-1.
D. Q. Oliveira, A. C. Zambroni de Souza, A. B. Almeida, M. V. Santos, B. I. L. Lopes, and D. Marujo, “Microgrid management in emergency scenarios for smart electrical energy usage,” in 2015 IEEE Eindhoven PowerTech, 2015, pp. 1–6, DOI: 10.1109/PTC.2015.7232309.
J. Yamnenko, T. Tereshchenko, L. Klepach, and D. Palii, “Forecasting of electricity consumption in SmartGrid,” in 2017 International Conference on Modern Electrical and Energy Systems (MEES), 2017, pp. 208–211, DOI: 10.1109/MEES.2017.8248891.
S. Singh and N. Singh, “Big Data analytics,” in 2012 International Conference on Communication, Information & Computing Technology (ICCICT), 2012, pp. 1–4, DOI: 10.1109/ICCICT.2012.6398180.
A. Gulenko, M. Wallschlager, F. Schmidt, O. Kao, and F. Liu, “Evaluating machine learning algorithms for anomaly detection in clouds,” in 2016 IEEE International Conference on Big Data (Big Data), 2016, pp. 2716–2721, DOI: 10.1109/BigData.2016.7840917.
Xueqin Zhang, Chunhua Gu, and Jiajun Lin, “Support Vector Machines for Anomaly Detection,” in 2006 6th World Congress on Intelligent Control and Automation, 2006, pp. 2594–2598, DOI: 10.1109/WCICA.2006.1712831.
Y. S. Yamnenko and T. O. Tereshchenko, “Spectral methods for processing biotelemetrical data,” Electron. Commun., vol. 21, no. 4, pp. 38–43, Nov. 2016, DOI: 10.20535/2312-1807.2016.21.4.81904.
X. Song, M. Wu, C. Jermaine, and S. Ranka, “Conditional Anomaly Detection,” IEEE Trans. Knowl. Data Eng., vol. 19, no. 5, pp. 631–645, 2007, DOI: 10.1109/TKDE.2007.1009.
H. M. Abdullah and A. M. Zeki, “Frontend and Backend Web Technologies in Social Networking Sites: Facebook as an Example,” in 2014 3rd International Conference on Advanced Computer Science Applications and Technologies, 2014, pp. 85–89, DOI: 10.1109/ACSAT.2014.22.
M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander, “LOF,” in Proceedings of the 2000 ACM SIGMOD international conference on Management of data - SIGMOD ’00, 2000, pp. 93–104, DOI: 10.1145/342009.335388.
P. S. Badase, G. P. Deshbhratar, and A. P. Bhagat, “Classification and analysis of clustering algorithms for large datasets,” in 2015 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), 2015, pp. 1–5, DOI: 10.1109/ICIIECS.2015.7193191.
R. Lin, E. Khalastchi, and G. A. Kaminka, “Detecting anomalies in unmanned vehicles using the Mahalanobis distance,” in 2010 IEEE International Conference on Robotics and Automation, 2010, pp. 3038–3044, DOI: 10.1109/ROBOT.2010.5509781.
