Electrical and Electronic Engineering, Renewable Energy, Sustainability and the Environment
37
Scopus Publications
Scopus Publications
Weighted cost emission dispatch optimization using GA–APO hybridization under priority sensitive scheduling for thermal power systems Chodagam Srinivas, M. Rama Prasad Reddy, Vineet Kumar, Vineet Kumar, Ark Dev, Negasa Muleta Scientific Reports, 2026 Modern utilities operate in an environment where fuel expenditure cannot be viewed in isolation from the environmental impact of generation. This creates a scheduling problem that is harder to address with traditional single objective tools, especially when the fuel and emission characteristics of thermal units do not behave smoothly. In this work, a two-stage solution strategy is developed for the economic-emission dispatch problem. The idea is straightforward: use a Genetic Algorithm (GA) to search widely for feasible production patterns and then pass its best candidate to an Arctic Puffin Optimization (APO) based refinement step, which adjusts the schedule locally and attempts to settle it closer to a desirable operating point. The economic and environmental indices are combined through a weighted formulation so that the dispatch can be steered toward cost saving, emission reduction, or an intermediate compromise without reworking the underlying model. Proposed method is tested on three generators thermal power plant with 24 h scheduling. Under different conditions, the proposed algorithm performed satisfactory by maintaining the results within the operational limits. Comparative study validates the effectiveness of the proposed design over GA approach. In cost-priority operation the hybrid approach achieves up to 1.88% reduction in total operating cost compared to GA. In emission priority condition the proposed GA-APO reduced the emission consumption nearly 0.21% and in balanced case cost per MWh reduced nearly 0.68%.
Cost Minimization in Residential Hybrid Energy Systems Using Advanced Scheduling Algorithms Chodagam Srinivas, A. V. Pavan Kumar, V. Pranay Teja Reddy, B Pavan, K Himasagar Reddy, Y Yugandhar Reddy 2025 5th International Conference on Advances in Electrical Computing Communication and Sustainable Technologies Icaect 2025, 2025 This study proposes an advanced optimization methodology for managing a grid-connected residential hybrid thermal and electrical energy system, incorporating a combined heat and power (CHP) fuel cell and a battery-based energy storage system (ESS). A predictive scheduling framework is designed to optimize the operational plan for distributed energy resources (DER) over a 24-hour period. The main objective is to reduce the operational expenses of a smart home by strategically allocating resources while considering dynamic electricity tariffs and the efficiency of the ESS. To achieve this, an enhanced Adaptive Gravitational Search Algorithm (AGSA) is employed. The research also includes a comparative evaluation of the AGSA against conventional Gravitational Search Algorithm (GSA) and Harmony Search Algorithm (HSA) methods. This comparison underscores the AGSA's superior performance in optimizing residential energy systems. The findings offer significant insights into the application of optimization algorithms for improving cost-efficiency and energy management in modern smart homes.
Integrated SOC Estimation for Grid-Interactive EV Batteries using Temperature-Dependent Kalman Filtering Chodagam Srinivas, A. V. Pavan Kumar, Shaik Mohammad Basha, Vadla Lokesh, Lokesh Kumar Reddy, Punyavathi Avula 3rd IEEE International Conference on Data Science and Network Security Icdsns 2025, 2025 The integration of electric vehicles (EVs) into smart grids through Vehicle-to-Grid (V2G) operations transforms them from passive loads into active energy assets. This evolution necessitates precise and robust estimation of the State of Charge (SOC), especially under operating scenarios characterized by thermal variability and long-term battery aging, where many existing SOC estimation techniques demonstrate reduced reliability. This paper presents an enhanced Kalman Filter (EKF)-based SOC estimation framework specifically developed for lithium-ion batteries engaged in bidirectional V2G applications. The estimator integrates three key components: (i) a nonlinear Open Circuit Voltage (OCV)-SOC relationship derived from empirical battery profiles, (ii) a temperature-sensitive internal resistance model that captures the impact of aging, and (iii) a physicsinformed thermal model accounting for entropy-driven reversible heat generation. The approach is validated using comprehensive MATLAB simulations under synthesized V2G load profiles that replicate realistic grid-interactive conditions. Across three distinct scenarios-nominal operation, elevated thermal stress, and accelerated aging-the framework consistently achieves SOC estimation errors below 3% under standard conditions and maintains errors within 9 % under intensified stress, outperforming traditional EKF implementations. These results demonstrate the estimator's resilience and its applicability for integration within advanced Battery Management Systems (BMS) in smart grid-connected EV systems.
Implementation of an Intelligent Battery Management System using Fuzzy Logic and Adaptive Neural Networks M Venkatesh, Chodagam Srinivas, A. V. Pavan Kumar, Mafthar G, Shanawaz S, Athika L S Proceedings of the 7th International Conference on Intelligent Sustainable Systems Iciss 2025, 2025 The rapid advancements in battery-powered technologies, particularly for electric vehicles (EVs) and renewable energy applications, necessitate the development of intelligent and accurate battery management systems (BMS) to ensure safety, reliability, and extended performance. This paper proposes an advanced framework for predicting the State of Health (SOH) by integrating Fuzzy Logic with Adaptive Neural Networks (ANN). The hybrid approach leverages Fuzzy Logic to address uncertainties in critical battery parameters such as internal resistance, capacity degradation, and temperature, while ANN enhances precision by modeling complex nonlinear relationships among these variables. The system combines the outputs of Fuzzy Logic and ANN dynamically, ensuring robust and adaptive SOH estimation under varying operational conditions. Comprehensive MATLAB simulations demonstrate the effectiveness of the proposed framework, achieving superior accuracy with a mean squared error (MSE) and robust adaptability to diverse battery aging profiles. Results highlight the hybrid system's significant performance improvements over standalone methods, showcasing its potential for real-world implementation in next-generation BMS. This novel methodology lays the groundwork for future research and practical deployment, enhancing battery lifespan and system efficiency in sustainable energy technologies.
Active Time-based Demand Response for Industrial Load Management using Quantum Mesh Neural Networks Chodagam Srinivas, I Kranthi Kumar, G Bharathi, Rudresha S J, A Uma Siva Naga Prasad, V.S. Aditya Proceedings of the 7th International Conference on Intelligent Sustainable Systems Iciss 2025, 2025 This paper presents an advanced optimization framework for Time-Based Demand Response (TBDR) scheduling tailored to industrial consumers. Traditional TBDR models often rely on uniform pricing strategies, which fail to account for diverse operational constraints across industrial sectors, leading to suboptimal load redistribution. To address this limitation, we propose an Active Time-Based Demand Response (ATB) framework integrated with a novel Quantum Mesh Neural Network (QMNN) model. The ATB framework segments industrial consumers based on their operational characteristics, enabling utilities to implement customized dynamic pricing strategies for improved engagement and efficiency.The proposed methodology is evaluated using a cement manufacturing case study, where simulation results demonstrate a 15% reduction in peak demand and an 18% decrease in operational costs compared to traditional passive TBDR approaches. The QMNN model significantly enhances load scheduling accuracy, ensuring real-time adaptability to fluctuating electricity prices. Furthermore, the results validate the effectiveness of the ATB framework in mitigating demand peaks, improving grid stability, and optimizing cost-efficient industrial energy management. By leveraging quantum-inspired optimization techniques, this study contributes to the advancement of intelligent and scalable demand response strategies in industrial applications, facilitating a more adaptive, cost-effective, and resilient power management system.
Optimization of Electric Vehicle Charging Infrastructure using Adaptive Large Neighbourhood Search K. Lakshmikhandan, Chodagam Srinivas, Tanakanti Shravya, Talla Chaitanya Lakshmi, Morupuri Mahesh Reddy, Avulannagari Dinesh Proceedings of 5th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2025, 2025 The growth of electric vehicles (EVs) has created an urgent demand for reliable charging infrastructure in cities. However, selecting where to deploy stations is a challenging decision, as it must reconcile financial limitations, user preferences, and long-term sustainability objectives. This work develops a planning framework that integrates a behavioural demand model with an Adaptive Large Neighbourhood Search (ALNS) heuristic to design profitable and resilient charging networks. The demand component is based on a nested logit structure, capturing how drivers weigh distance, charging cost, and local amenities when choosing stations. The optimization module evaluates 10-year revenues and costs, including construction, operations, and maintenance, to identify the most advantageous set of sites. Several scenarios are studied: a five-station, high-growth case emphasizing convenience; a four-station, sustainability case balancing economics with green goals; and smaller rollout cases for constrained budgets. The algorithm provides not only a single best solution but also alternative portfolios that remain close to optimal, improving robustness if conditions change. Results show that the approach can guide planners toward infrastructure strategies that are financially viable, responsive to demand, and adaptable to uncertain urban futures.
Support Vector Regression for Reactive Power Compensation: A Data-Driven Approach to Power Loss Reduction K Lakshmikhandan, Chodagam Srinivas, K Swetha, S Gnapika, B Pavan, K Rajasekhar Proceedings of 3rd International Conference on Augmented Intelligence and Sustainable Systems Icaiss 2025, 2025 The modernization of distribution networks and the growing penetration of distributed energy resources (DERs) demand innovative strategies to manage reactive power and minimize losses. This study proposes a machine learning-based approach using Support Vector Regression (SVR) for determining optimal capacitor placement in the IEEE 33-bus distribution system. The method replaces traditional heuristic algorithms with a predictive model trained on various simulated configurations to estimate capacitor positions and sizes that minimize active power loss. Two configurations—using two and three capacitors—are assessed and validated via Backward-Forward Sweep (BFS) load flow analysis. Results indicate that SVR offers substantial loss reduction and voltage profile improvements, outperforming Particle Swarm Optimization (PSO) and Bat Algorithm (BAT) in terms of efficiency, accuracy, and computation time. This work highlights the potential of SVR as a practical tool for real-time optimization in smart distribution networks.
Interpretable Machine Learning Approach for State of Health Estimation in Lithium-Ion Batteries C Kamal Basha, Chodagam Srinivas, Muthyala Meenakshi, Poreddy Chandanareddy, Chatla Geetha, Mudi Ganesh 2025 IEEE International Conference on Communication Networks and Computing Cnc 2025, 2025 Reliable estimation of battery State of Health (SOH) is a critical requirement for ensuring safety, extending service life, and enabling predictive maintenance in electric vehicles and grid-scale energy storage systems. Existing approaches rely heavily on physics-based models or deep neural networks. While physics models are constrained by intrusive measurements and parameter drift, deep learning methods suffer from high computational cost, limited interpretability, and deployment challenges in resource-constrained battery management systems. This work presents a feature-engineered machine learning framework for SOH prediction that combines synthetic sequence generation with statistical descriptors of current, voltage, and temperature signals. By systematically capturing degradation signatures across varying C-rates, the framework provides a compact, interpretable representation of battery behavior. Classic tree-based regressors, including Decision Trees, Random Forests, and Gradient Boosted Trees, are benchmarked on the engineered feature space. The study demonstrates that ensemble learning not only improves predictive robustness but also offers transparency through feature importance analysis and stress-aware evaluation. The proposed approach successfully addresses the trade-off between accuracy, interpretability, and computational efficiency, making it well suited for real-time battery management and embedded applications. Beyond its immediate predictive capability, the framework establishes a foundation for scalable, stress-aware SOH monitoring, and opens avenues for integration with field data and hybrid lightweight neural models.
Minimization of Frequency Deviations in Multi-Area Power System with SSSC N Madhusudhan Reddy, Chodagam Srinivas, Peruri Naga Sai Varsha, Sypureddy Srujana, Nadimpalli Saipriya, Rayi Sai Ganesh Idciot 2023 International Conference on Intelligent Data Communication Technologies and Internet of Things Proceedings, 2023
Distribution Transformer Tap Setting Control using Particle Swarm Optimization Vijju Bindhu Naga Swathika Devi, Chodagam Srinivas, M V S Prem Sagar, N D V Prasad Pandalaneni, S Saravanan, Y V Balarama Krishna Rao 3rd International Conference on Electronics and Sustainable Communication Systems Icesc 2022 Proceedings, 2022
Regulation of Frequency in Multi-Source Two Area Power System with TCSC N D V Prasad Pandalaneni, Abolfazl Mehbodniya, Chodagam Srinivas, Bonthu Pavan Kumar, Vemana Ramanarayana, Kona Amarrendra Proceedings 4th International Conference on Smart Systems and Inventive Technology Icssit 2022, 2022
