Browsing by Author "Rao, V.S."

Now showing 1 - 5 of 5

A Novel Transformer-Based Approach for Reliability Evaluation of Composite Systems With Renewables and Plug-in Hybrid Electric Vehicles
(Institute of Electrical and Electronics Engineers Inc., 2025) Yarramsetty, C.; Moger, T.; Jena, D.; Rao, V.S.
This paper proposes a novel hybrid framework that integrates machine learning (ML) techniques with Sequential Monte Carlo Simulation (SMCS) to enhance the reliability assessment of modern power systems incorporating renewable energy resources (RER) and plug-in hybrid electric vehicle (PHEVs) integration. While PHEVs can leverage RER to significantly reduce greenhouse gas emissions, the increased energy demand from large PHEVs fleets poses potential challenges to power system reliability. To address these issues, this research presents an advanced mixed-integer linear programming (MILP) based algorithm for optimizing EV charging. The algorithm prioritizes clean energy utilization through intelligent power allocation strategies while considering cost-revenue trade-offs. A probabilistic model is developed to account for factors such as driving distance, charging times, locations, battery state of charge, and charging needs of PHEVs. The proposed approach is tested on the IEEE RTS-79 test system and evaluates multiple ML architectures, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Transformer models, often combined with boosting algorithms, across three scenarios: base case, uncontrolled charging, and intelligent charging. Results highlight that ML-based approaches, particularly the Transformer model, achieve computational time reductions of up to 49% compared to traditional SMCS methods while maintaining comparable accuracy. The Transformer model identified 1,788 loss-of-load states compared to 1,510 actual instances, requiring only 176 minutes of computation. Among all models, the BiLSTM with Adaptive Boosting (BiLSTM+AB) achieved the lowest overestimation, exceeding actual instances by just 256 states. Performance metrics such as Loss of Load Probability (LOLP) and Expected Demand Not Supplied (EDNS) validate the effectiveness of the proposed ML approaches in balancing accuracy and computational efficiency. © 2013 IEEE.
Advances in Composite Power System Reliability Assessment: Trends and Machine Learning Role
(Institute of Electrical and Electronics Engineers Inc., 2025) Yarramsetty, C.; Moger, T.; Jena, D.; Rao, V.S.
This paper provides a detailed review of reliability assessment methods for composite power systems, focusing on integrating renewable energy and advanced computational approaches. The study classifies existing research into three main areas: investigation studies, planning and optimization studies, and efficient evaluation studies. Findings indicate that machine learning techniques are increasingly important in improving accuracy and computational performance in reliability analysis. A comparative examination of conventional and Machine Learning (ML)-based methods demonstrates that deep learning models, such as Convolutional Neural Networks, offer substantial reductions in computational time while maintaining reliability assessment precision. The review also identifies key research gaps, such as the need for realistic test systems and enhanced hybrid ML strategies. Additionally, recommendations are proposed to address these challenges and strengthen the effectiveness of future reliability evaluation methodologies. The insights presented in this study aim to support researchers and industry professionals in developing more efficient and scalable reliability assessment models for evolving power systems. Â© 2013 IEEE.
Advances in Composite Power System Reliability Assessment: Trends and Machine Learning Role
(Institute of Electrical and Electronics Engineers Inc., 2025) Yarramsetty, C.; Moger, T.; Jena, D.; Rao, V.S.
This paper provides a detailed review of reliability assessment methods for composite power systems, focusing on integrating renewable energy and advanced computational approaches. The study classifies existing research into three main areas: investigation studies, planning and optimization studies, and efficient evaluation studies. Findings indicate that machine learning techniques are increasingly important in improving accuracy and computational performance in reliability analysis. A comparative examination of conventional and Machine Learning (ML)-based methods demonstrates that deep learning models, such as Convolutional Neural Networks, offer substantial reductions in computational time while maintaining reliability assessment precision. The review also identifies key research gaps, such as the need for realistic test systems and enhanced hybrid ML strategies. Additionally, recommendations are proposed to address these challenges and strengthen the effectiveness of future reliability evaluation methodologies. The insights presented in this study aim to support researchers and industry professionals in developing more efficient and scalable reliability assessment models for evolving power systems. © 2013 IEEE.
Novel Power Smoothing Technique for a Hybrid AC-DC Microgrid Operating with Multiple Alternative Energy Sources
(Universitatea "Stefan cel Mare" din Suceava, 2021) Nempu, P.B.; Sabhahit, J.N.; Gaonkar, D.N.; Rao, V.S.
The power produced by renewable sources such as photovoltaic systems and wind energy conversion systems is highly intermittent due to continuously changing irradiance and wind velocity. When the distributed generation systems employing photovoltaic (PV) array and wind energy conversion system (WECS) operate in grid-tied mode, the power fluctuations affect the power quality of the grid. In a hybrid AC-DC microgrid (HMG), the dynamics of DC and AC subgrids influence each other. This paper proposes a supercapacitor based novel power smoothing methodology for the HMG with PV array, WECS, fuel cell (FC) and electrolyzer (EL) based hydrogen storage system considering the power fluctuations in both subgrids. The power smoothing technique on the DC subgrid aims to facilitate instantaneous power balance. The Kalman filter (KF) based velocity smoothing (KFV) approach is developed for the WECS. The KFV technique is compared with the power smoothing techniques presented in the literature. The KFV method is found to be effective in computing the smooth power reference for the supercapacitor system. By incorporating the proposed power smoothing technique in the HMG, the stress on the interlinking converter (ILC) and utility grid are minimized and the power quality is enhanced. © 2021. All Rights Reserved.
Optimal Placement and Sizing of Electric Vehicle Charging Infrastructure in a Grid-Tied DC Microgrid Using Modified TLBO Method
(MDPI, 2023) Krishnamurthy, N.K.; Sabhahit, J.N.; Jadoun, V.K.; Gaonkar, D.N.; Shrivastava, A.; Rao, V.S.; Kudva, G.
In this work, a DC microgrid consists of a solar photovoltaic, wind power system and fuel cells as sources interlinked with the utility grid. The appropriate sizing and positioning of electric vehicle charging stations (EVCSs) and renewable energy sources (RESs) are concurrently determined to curtail the negative impact of their placement on the distribution network’s operational parameters. The charging station location problem is presented in a multi-objective context comprising voltage stability, reliability, the power loss (VRP) index and cost as objective functions. RES and EVCS location and capacity are chosen as the objective variables. The objective functions are tested on modified IEEE 33 and 123-bus radial distribution systems. The minimum value of cost obtained is USD 2.0250 × 106 for the proposed case. The minimum value of the VRP index is obtained by innovative scheme 6, i.e., 9.6985 and 17.34 on 33-bus and 123-bus test systems, respectively. The EVCSs on medium- and large-scale networks are optimally placed at bus numbers 2, 19, 20; 16, 43, and 107. There is a substantial rise in the voltage profile and a decline in the VRP index with RESs’ optimal placement at bus numbers 2, 18, 30; 60, 72, and 102. The location and size of an EVCS and RESs are optimized by the modified teaching-learning-based optimization (TLBO) technique, and the results show the effectiveness of RESs in reducing the VRP index using the proposed algorithm. © 2023 by the authors.