03952nas a2200421 a 4500 20260817171303.0 220616s2021 th uu m rtt 0 a eng d .b12385670 AIT Thesis no.ET-21-13 Makara Greadmeta Benefits of applying data analysis and machine learning to advanced metering infrastructure system Pathum Thani, Thailand : Asian Institute of Technology, 2021 243 leaves : ill. Thesis ; no. ET-21-13 A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Energy Thesis (M. Eng.) - Asian Institute of Technology, 2021 Nowadays, electricity is one of the most important form of final energies and living without it is very difficult to imagine. For electrical energy market, the correct measurement of electricity consumption is essential for both providers and consumers. Therefore, the Advanced Metering Infrastructure system has been developed. It is an integrated system of meters, communications and data management systems that enables two-way communication between utilities and consumers in near real-time. According to these functionalities, the large and diverse datasets will be collected and stored much more than before. Only storing may not be useful so this study proposes several processes to leverage these consumption datasets for both utility and consumer aspects. Data analysis and machine learning have been selected to address all of the objectives by mainly using Python programming language. The results show that every proposed process can successfully provide benefits to both of them. For utility aspect, the developed distribution transformer monitoring system and the introduced meters phase-swapping algorithms can help reducing technical losses. Moreover, non technical losses can also be reduced by the developed electricity theft detection system based on machine learning classification algorithms. For consumer aspect, the proposed tariff changing evaluation process can provide suggestions to consumers individually in order to help reducing their electricity bills. The insights from the created consumption comparisons can also be provided to consumers for having more comprehension and useful information. Furthermore, the abnormal consumption data points can be identified by the developed anomaly detection system based on outlier detection algorithms. Finally, this study also presents the convenient solution to deliver aforementioned benefits to end-users by developing the Web Application. All of the proposed processes and solution by this study are suitable and can be adapted for any energy provider and consumer. Electric power distribution Data processing Electric meters Technological innovations Machine learning Singh, Jai Govind, Chairperson Salam, Abdul P., Examination Committee Weerakorn Ongsakul, Examination Committee PEA-AIT Education Cooperation Project, Scholarship Donor Royal Thai Government Fellowship, Scholarship Donor Asian Institute of Technology. Thesis ; no. ET-21-13 Full-Text http://203.159.5.9/ait-thesis/detail.php?q=B16721 .b12385670 mnait m 240419 0 220616 m h m 0 mnarc mnarc 40 61 Barcode : 30020220006228 CREATED : 2022-03-06 RECORD # : i13381507 LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 Barcode : - CREATED : 2022-03-06 RECORD # : i13381519 LPATRON : 0 LCHKIN : - # RENEWALS : 0 # OVERDUE : 0 IUSE3 : 0 TOT CHKOUT : 0 TOT RENEW : 0 11621 11621 0 0 0 0 MAIN MAIN mnarc 2026-08-17 0 AIT Thesis no.ET-21-13 30020220006228 2026-08-17 17:13:03 1 2026-08-17 40 0 0 0 0 MAIN MAIN mnarc 2026-08-17 0 AIT Thesis no.ET-21-13 2026-08-17 17:13:03 2026-08-17 61