2026· International Journal of Advanced Computer Science and Applications· 0 citations· 21 references
TL;DR
A new hybrid BMS for SOC estimation based on a transaction-oriented adaptive Kalman Filter that merges traditional voltage-based SOC estimation has been developed in this study and demonstrates that it serves as an efficient and effective alternative for achieving long-term energy optimization in IoT-enabled smart agriculture applications.
Abstract
Battery-powered sensor nodes operating in a remote environment are used in IoT-based smart agriculture deployments, where the maintenance of these devices is impractical. Thus, precise SOC (state-of-charge) estimation is critical to enhance both energy efficiency and system stability. A new hybrid BMS for SOC estimation based on a transaction-oriented adaptive Kalman Filter that merges traditional voltage-based SOC estimation has been developed in this study. Results show that our proposed method removes noise sensitivity and reduces SOC drift subjected to dynamic IoT workloads by integrating model prediction with measurement correction. Application experiments based on 30 days' real sensor workload data indicate that the cumulative battery consumption index of the proposed algorithm decreased from 78% to 56%, and provided a performance improvement of approximately 22.7% compared to the baseline method. Moreover, the proposed method shows better stability in terms of daily consumption fluctuation and drift. The findings demonstrate that the improved Kalman Filter–based hybrid BMS serves as an efficient and effective alternative for achieving long-term energy optimization in IoT-enabled smart agriculture applications.
The fast changing nature of connected vehicles requires smart systems that can monitor health in real-time and predict failures. This paper introduces an IoT-based Smart Vehicle Monitoring and Predictive Maintenance System that involves onboard sensors, edge computing, and cloud analytics to ensure high reliability and reduce unscheduled downtimes. Multi-modal transportation data (temperature, vibration, fuel consumption, and brake parameters) are continuously measured with the help of ESP32/Arduino devices connected to the CAN bus. An Extended Kalman Filter (EKF) is an algorithm that does nonlinear sensor fusion at the edge to enhance data reliability and noise minimization. The degradation prediction and Remaining Useful Life estimation of the fused time-series data are done with a Long Short-Term Memory (LSTM) network. A new adaptive thresholding system is used to dynamically regulate anomaly sensitivity according to driving context and historical trends. It was evaluated experimentally on 100,000 real-time sample divided into 70% training, 15% validation and 15% testing sample. The proposed framework was found to have 97.4% prediction accuracy with Precision (94.8%), Recall (95.6%), and F1-score (95.2%). EKF preprocessing minimized RMSE by 0.84, and it is a 56-percent improvement in estimation accuracy. The adaptive detection module reduced false positive rate to 4.1% which was 63% lower than the approaches to static threshold. The system forecasted failures almost 22 minutes earlier than it was actually detected which enhanced early detection by almost 30 percent. The edge deployment decreased latency by a factor of 4 to 160 ms, and thus, allowed the creation of nearly real-time alerts. The implementation of visualization and alert management was realized based on the use of Node-RED and Grafana dashboards, along with MQTT-based secure communication. All in all, the framework is statistically proven to be robust, scaled and applicable to next-generation intelligent vehicular IoT ecosystems.
Biswaraj Roy, B. Prasath, Ajit Kumar Singh et al.· 2026 6th International Confe...· 0 citations
Photovoltaic (PV) systems are extremely prone to wear and tear and physical damage due to large variation in environmental conditions. Integration of real-time monitoring systems with PV would be highly advantageous in detecting early faults and performance degradation consequently leads to timely maintenance and repair. This can also reduce recurring cost, enhance reliability, efficacy, and performance of PV systems that eventually lead to generation of sustainable energy. This study presents a cost-effective solution that uses the Internet of Things (IoT) for real-time monitoring of PV systems and for optimizing maximum power point tracking (MPPT). A fuzzy logic-based algorithm is used in hardware to track the MPPT and process data. Furthermore, the developed solution is experimentally validated on a real system under varying outdoor conditions. The developed system is found to be 99.4% efficient in the real experimental setup under outdoor conditions. The simulated outcomes closely match the experimental results, and the developed hardware can adjust the duty cycle for MPPT tracking across varying irradiance levels.
Pratibha Sharma, Nishakant Kalia, M. Awasthi et al.· Journal of Thermal Analysis...· 0 citations
IoT is one of the significant enabling technologies in the contemporary energy landscape. This work addresses intelligent load management under fault, under-load, and overload conditions. Electrical equipment requires automatic and rapid response to avoid damage and prevent service interruption. In contrast to traditional circuit breakers that disconnect the entire system, the proposed architecture employs ESP32-based intelligent control, together with ACS712 current sensors, to provide accurate per-load current measurements and load-specific overcurrent protection. The system is also capable of selective load isolation, meaning that it maintains the operation of healthy circuits and automatically disconnects only the faulty load without affecting other loads. Cloud-based monitoring is implemented via the ThingSpeak platform, enabling real-time remote system surveillance through any internet-connected device. The faulty section of the system is readily identified from the current readings visualised on the cloud dashboard and mobile interface. The proposed system is powered primarily by solar photovoltaic sources and can also operate from the utility grid, providing flexibility across renewable and conventional supply scenarios. Experimental testing demonstrates protection response times in the sub-200 ms range and high-accuracy current monitoring with a mean absolute error below 0.05 A. The key contributions include: selective load protection, real-time IoT-based energy analysis, and a cost-effective open-hardware architecture. The work advances the safety and efficiency of smart energy control systems in distributed renewable energy environments.
Jeevitha Kandasamy, Kalaivani C, Shashank S Bhagwat et al.· 2026 4th International Confe...· 0 citations
Rapid urbanization and the demand for energy-efficient buildings have driven the need for intelligent HVAC systems. Traditional systems rely on fixed or manual controls, limiting their ability to adapt to changing environmental and occupancy conditions. This paper presents a Smart HVAC system that integrates Artificial Intelligence (AI), Internet of Things (IoT) sensors, cloud-based analytics, and machine learning to enhance energy efficiency, thermal comfort, and reliability. The proposed system continuously monitors indoor conditions such as temperature, humidity, air quality, and occupancy in real time. It applies supervised learning for temperature prediction and reinforcement learning for adaptive control, enabling optimized HVAC operations based on both historical and real-time data. The architecture includes data acquisition, preprocessing, model training, and intelligent control, with considerations for scalability, security, and interoperability. Performance evaluation through simulations and real-world testing demonstrates significant energy savings, reduced carbon emissions, and improved occupant comfort compared to conventional systems. Additionally, the system supports fault detection, predictive maintenance, and reduced downtime. Overall, this work contributes to smart building development by providing an efficient, scalable AI-driven HVAC framework that promotes sustainable and cost-effective building management.
Suresh Babu Reddy· International Journal of Mod...· 0 citations
Battery energy storage (BES) systems are vital in the enhancement of sustainability, performance and reliability in today’s power systems particularly for Backup Power Systems (BES), electric vehicles (EV) and for requiring renewable energy integration. This paper presents the development/evaluation of an ESP32-based smart battery energy storage and health monitoring system with remote access and real time monitoring capabilities. The proposed system uses the appropriate sensors and data collection/monitoring methods to provide continuous monitoring of critical battery parameters i.e. Voltage, Current, Temperature and State of Charge (SOC). The results of experiments proved the system operated as expected under the following parameters: A safe working voltage range for the batteries was maintained (12.1–12.8 V) the maximum allowed charging rate of the batteries was approximately +5 A; overcharging and discharging current rates were managed within acceptable limits. Additionally, accurate tracking of SOC confirmed that energy estimates were reliable, with remarkably consistent and almost linear fluctuations of approximately 5% to 7% during the regulated charging/discharge cycles. The system also identified risk factors such as Deep Discharge (below 40% SOC), Overcharging (above 85% to 90% SOC) and Excessive Rise in Temperature (above 45°C); therefore, the system enabled prompt preventive action to mitigate potential battery deterioration and failure. Due to the low power consumption, built-in Wi-Fi capability and cost-effectiveness of the ESP32, the system is suitable for scalable and remote deployment.
B. Rohini, S. Amosedinakaran, G. Hemachandra et al.· International Conference on...· 0 citations
Energy efficiency assessment is fundamental to the reliable and sustainable operation of modern smart grids, particularly with the increasing deployment of Internet of Things (IoT) technologies and renewable energy resources. This study presents a data-driven framework for Energy Efficiency Score prediction that integrates Extreme Gradient Boosting Regression (XGBR) and Histogram-based Gradient Boosting Regression (HGBR) with Metaheuristic Optimization Algorithm (MOA), Particle Swarm Optimization (PSO), and Harris Hawks-inspired Learning Optimization Algorithm (HLOA) to optimize model parameters and improve predictive performance. Principal Component Analysis (PCA) is employed to reduce feature redundancy, while time-aware validation and cross-validation are used to improve the reliability of model evaluation. SHAP analysis is further incorporated to quantify feature contributions and improve model interpretability. The proposed framework achieved an R² of 0.9971 and an RMSE of 0.8744, demonstrating highly accurate estimation of the Energy Efficiency Score. The optimized hybrid configurations outperformed their corresponding baseline boosting models, confirming the benefit of metaheuristic parameter optimization for structured smart-grid data. The SHAP analysis further identified grid frequency, environmental conditions, reactive power, active power, and power consumption as among the most influential predictive variables. The results demonstrate that the proposed framework can provide an accurate and interpretable data-driven intelligence layer for energy-efficiency assessment and decision support in IoT-enabled smart grids. The framework therefore offers a scalable approach for predictive energy analytics while complementing, rather than replacing, physics-based grid optimization and operational models.
Yanqing Wei, Yanmei Sun, Kai-Jia Liu et al.· Scientific Reports· 0 citations