Author ORCID Identifier
0000-0002-6998-2247
0000-0002-6998-2247
Biosketch
Dr. S. Sheik Mohideen Shah is an Assistant Professor in the Department of Computer Science and Engineering at the Srinivasa Ramanujan Centre, SASTRA Deemed To Be University, Kumbakonam. He has over 15 years of experience in teaching, research, and academic administration. He obtained his Bachelor’s degree in Information Technology from Annamalai University, followed by a Master’s degree in Computer Science and Engineering from Annamalai University. He has completed his Doctor of Philosophy (Ph.D.) under the guidance of Dr. S. Meganathan, Associate Professor, Srinivasa Ramanujan Centre,SASTRA DEEMED TO BE UNIVERSITY,Kumbakonam. His research interests include Data Mining, Machine Learning, Data Analytics, and Internet of Things (IoT). He has published research papers in reputed international journals indexed in SCI, Scopus, and Web of Science.Dr. S. Sheik Mohideen Shah has guided numerous undergraduate and postgraduate projects and actively mentors students in academic and research activities. His research contributions focus on developing intelligent and sustainable computing solutions for real-world applications. He has also participated in several faculty development programmes, certification courses, and collaborative research initiatives to enhance his professional expertise.His commitment to excellence in teaching, research, and institutional service continues to contribute significantly to academic development and technological innovation.
Date of Award
22-5-2026
Document Type
Thesis
School
School of Computing
Programme
Ph.D.-Doctoral of Philosophy
First Advisor
Dr.S.Meganathan
Keywords
SRVPC, HEVC
Abstract
Power consumption trends are essential to be identified in the energy grid areas to analyze the utilization, deficiency, and the measures to be taken for an effective and comfortable usage of energy. There are two scenarios in which the power consumption can be analyzed, namely identification and prediction. Identification deals with the post-utilization analysis of energy trends, whereas prediction deals with prior analysis of various factors of energy utilization, including the cost, supply details, shortages, and the need for new energy resources. In the existing models, the power consumption-related data are collected through smart meters, and the energy forecasting methods are incorporated using the sensor nodes, machine learning, and deep learning models to calculate the trend for futuristic analysis. The primary concerns with existing models include imbalanced data, low accuracy, analyzing only the short-term load consumption, etc.
We proposed four major approaches to overcome this limitation and to perform an efficient power consumption prediction and energy forecasting mechanism in our research. A novel prediction model, Support Resistance Value Plane Classifier (SRVPC), has been constructed to perform effective predictive analysis from the smart meter data collected from various regions of Tamil Nadu. The predictive model is implemented in the forecasting environment through our novel model, named Hybrid Ensemble Voting Classifier (HEVC). The proposed predictive and forecasting model performs well in a trained dataset, whereas to make them more effective in handling larger unknown datasets, we proposed a Cat Boost energy forecasting model that analyses the extensive data and provides the SRVPC and HEVC with accurate information on energy utilization.
The energy forecasting system is further enhanced by integrating the AI model in a real-time environment to predict energy consumption. This was implemented by our proposed Bidirectional-LSTM model, which analyzes the energy flow in dual directions, including the demand by the consumer to the energy model and the resources that the model shares with the consumer. Our proposed models in each phase are compared with their equivalent existing models, where the proposed models outperformed all the other models through their benchmark results. This model has improved overall performance and introduced a predictive mechanism for power consumption and energy forecasting.
Recommended Citation
S, Sheik Mohideen Shah Mr, "Power Consumption Prediction and Energy Forecasting using Machine Learning Models" (2026). Theses and Dissertations. 218.
https://knowledgeconnect.sastra.edu/theses/218