Health monitoring and analysis of photovoltaic (PV) systems are critical for optimizing energy efficiency, improving reliability, and extending the operational lifespan of PV power plants. Effective fault detection and monitoring are vital for ensuring the proper functioning and maintenance of these systems. PV power plants operating under fault conditions show significant deviations in current-voltage (I-V) characteristics compared to those under normal conditions. This paper introduces a diagnostic methodology for photovoltaic panels using I-V curves, enhanced by new techniques combining optimization and classification-based artificial intelligence. The research is organized into two key sections. The first section outlines the implementation of a DC/DC buck-boost converter, which is designed to extract and display real-time data from the PV system based on actual (I-V) measurements. The second section focuses on the comprehensive processing of the experimental dataset, where the Harris Hawks Optimization (HHO) algorithm is combined with machine learning methods to identify the most critical features. The HHO algorithm is combined with an advanced machine learning model, XGBoost, to accurately detect faults within the PV system. The proposed HHO-XGBoost algorithm achieves an impressive accuracy of 99.49%, outperforming other classification-based artificial intelligence methods in fault detection. In validation and comparison with previous approaches, the HHO-XGBoost model consistently outperforms established methods such as GADF-ANN, PCA-SVM, PNN, and Fuzzy Logic, achieving an overall accuracy of 98.48%. This outstanding performance confirms the model's effectiveness in accurately diagnosing PV system conditions, further validating its robustness and reliability in fault detection and classification.
The integration of Electric Vehicles (EVs) into power grids introduces several critical challenges, such as limited scalability, inefficiencies in real-time demand management, and significant data privacy and security vulnerabilities within centralized architectures. Furthermore, the increasing demand for decentralized systems necessitates robust solutions to handle the growing volume of EVs while ensuring grid stability and optimizing energy utilization. To address these challenges, this paper presents the Demand Response and Load Balancing using Artificial intelligence (DR-LB-AI) framework. The proposed framework leverages Artificial intelligence (AI) for predictive demand forecasting and dynamic load distribution, enabling real-time optimization of EV charging infrastructure. Furthermore, Blockchain technology is employed to facilitate decentralized, secure communication, ensuring tamper-proof energy transactions while enhancing transparency and trust among stakeholders. The DR-LB-AI framework significantly enhances energy distribution efficiency, reducing grid overload during peak periods by 20%. Through advanced demand forecasting and autonomous load adjustments, the system improves grid stability and optimizes overall energy utilization. Blockchain integration further strengthens security and privacy, delivering a 97.71% improvement in data protection via its decentralized framework. Additionally, the system achieves a 98.43% scalability improvement, effectively managing the growing volume of EVs, and boosts transparency and trust by 96.24% through the use of immutable transaction records. Overall, the findings demonstrate that DR-LB-AI not only mitigates peak demand stress but also accelerates response times for Load Balancing, contributing to a more resilient, scalable, and sustainable EV charging infrastructure. These advancements are critical to the long-term viability of smart grids and the continued expansion of electric mobility.
- Klíčová slova
- Artificial intelligence, Blockchain, Demand response, EV charging stations, Load balancing,
- Publikační typ
- časopisecké články MeSH
Microgrids (MGs) have gained significant attention over the past two decades due to their advantages in service reliability, easy integration of renewable energy sources, high efficiency, and enhanced power quality. In India, low-voltage side customers face significant challenges in terms of power supply continuity and voltage regulation. This paper presents a novel approach for optimal power scheduling in a microgrid, aiming to provide uninterrupted power supply with improved voltage regulation (VR). To address these challenges, a crow search algorithm is developed for effective load scheduling within the distribution system. The proposed method minimizes the total operating cost (TOC) and maximizes VR under varying loading conditions and distributed generation (DG) configurations. A case study in Tamil Nadu, India, is conducted using a microgrid composed of three distributed generation sources (DGs), modeled and simulated using the Electrical Transient Analyzer Program (ETAP) environment. The proposed approach is tested under three operational scenarios: grid-connected mode, islanded mode, and grid-connected mode with one DG outage. Results indicate that the crow search algorithm significantly optimizes load scheduling, leading to a substantial reduction in power loss and enhancement in voltage profiles across all scenarios. The islanded mode operation using the crow search algorithm demonstrates a remarkable reduction in TOC and maximizes voltage regulation compared to other modes. The main contributions of this work include: (1) developing a new meta-heuristic approach for power scheduling in microgrids using the crow search algorithm, (2) achieving optimal power flow and load scheduling to minimize TOC and improve VR, and (3) successfully implementing the proposed methodology in a real-time distribution system using ETAP. The findings showcase the effectiveness of the crow search algorithm in microgrid power management and its potential for application in other real-time power distribution systems.
- Klíčová slova
- Crow search algorithm, Distributed generation, ETAP simulation, Load scheduling, Microgrid, Power management, Total operating cost, Voltage regulation,
- Publikační typ
- časopisecké články MeSH
In this paper, an improved voltage control strategy for microgrids (MG) is proposed, using an artificial neural network (ANN)-based adaptive proportional-integral (PI) controller combined with droop control and virtual impedance techniques (VIT). The control strategy is developed to improve voltage control, power sharing and total harmonic distortion (THD) reduction in the MG systems with renewable and distributed generation (DG) sources. The VIT is used to decouple active and reactive power, reduce negative power interactions between DG's and improve the robustness of the system under varying load and generation conditions. Simulation findings under different tests have shown significant improvements in performance and computational simulation. The rise time is reduced by 60%, the overshoot is reduced by 80%, the THD of the voltage is reduced by 75% (from 0.99 to 0.20%), and the THD of the current is reduced by 69% (from 10.73 to 3.36%) compared to the conventional PI controller technique. Furthermore, voltage and current THD values were maintained below the IEEE-519 standard limits of 5% and 8%, respectively, for the power quality enhancement. Fluctuations in voltage and frequency were also maintained at 2% tolerance and 1% tolerance, respectively, across all voltage limits, which is consistent with international norms. Power-sharing errors were reduced by 50% after conducting the robustness tests against the DC supply and load disturbances. In addition, the proposed strategy outperforms the previous control techniques presented at the state of the art in terms of adaptability, stability and, especially, the ability to reduce the THD, which validates its effectiveness for MG systems control and optimization under uncertain conditions.
Wind energy plays a crucial role as a renewable source for electricity generation, especially in remote or isolated regions without access to the main power grid. The intermittent characteristics of wind energy make it essential to incorporate energy storage solutions to guarantee a consistent power supply. This study introduces the design, modeling, and control mechanisms of a self-sufficient wind energy conversion system (WECS) that utilizes a Permanent magnet synchronous generator (PMSG) in conjunction with a Water pumping storage station (WPS). The system employs Optimal torque control (OTC) to maximize power extraction from the wind turbine, achieving a peak power coefficient (Cp) of 0.43. A vector control strategy is applied to the PMSG, maintaining the DC bus voltage at a regulated 465 V for stable system operation. The integrated WPS operates in both motor and generator modes, depending on the excess or shortfall of generated wind energy relative to load demand. In generator mode, the WPS supplements power when wind speeds are insufficient, while in motor mode, it stores excess energy by pumping water to an upper reservoir. Simulation results, conducted in MATLAB/Simulink, show that the system efficiently tracks maximum power points and regulates key parameters. For instance, the PMSG successfully maintains the reference quadrature current, achieving optimal torque and power output. The system's response under varying wind speeds, with an average wind speed of 8 m/s, demonstrates that the generator speed closely follows turbine speed without a gearbox, leading to efficient power conversion. The results confirm the flexibility and robustness of the control strategies, ensuring continuous power delivery to the load. This makes the system a feasible solution for isolated, off-grid applications, contributing to advancements in renewable energy technologies and autonomous power generation systems.
Renewable energies are interesting as an alternative and sustainable resource for air conditioning applications. But initial investment cost of equipment, whose employed for converting the renewable energy into usable shape and also for air conditioning duty, are significant. Therefore, determining the optimum sizing has high priority. In current study, water cooled vapor compression refrigeration cycle powered by wind energy and storage tank is proposed, simulated and optimized. To contribute the total effective aspects in system optimum size, the thermo-economic-environmental criteria is defined. By the help of databank of parametric analysis, the optimum design variables are determined by employing the GA optimization algorithm. In the following, an intelligence neural network is developed to learn the reliable correlation between the inputs and outputs data. Finally, the optimum size of each subsystem is determined by using triple-objective MPSO. Based on detailed economic analysis, the system payback period is estimated about 450 days which is 41% less than the conventional system. The daily COP and exergy efficiency of the whole system has improved up to 98% and 40%, after substituting the optimum design variable parameters. Triple-objective MPSO results show that, the ice storage tank should be selected 22% smaller than the initial amount.
- Klíčová slova
- 5E analysis, Cold storage, Compression cycle, Triple-objective MPSO optimization, Wind energy,
- Publikační typ
- časopisecké články MeSH
While the proliferation of the Internet of Things (IoT) has revolutionized several industries, it has also created severe data security concerns. The security of these network devices and the dependability of IoT networks depend on efficient threat detection. Device heterogeneity, computing resource constraints, and the ever-changing nature of cyber threats are a few of the obstacles that make detecting cyber threats in IoT systems difficult. Complex threats often go undetected by conventional security measures, requiring more sophisticated, adaptive detection methods. Therefore, this study presents the Hybrid approach based on the Support Vector Machines Rule-Based Detection (HSVMR-D) method for an all-encompassing approach to identifying cyber threats to the IoT. The HSVMR-D employs SVM to categorize known and unknown threats using attributes acquired from IoT data. Identifying known attack signatures and patterns using rule-based approaches improves detection efficiency without retraining by adapting pre-trained models to new IoT contexts. Moreover, protecting vital infrastructure and sensitive data, HSVMR-D provides a thorough and adaptable solution to improve the security posture of IoT deployments. Comprehensive experiment analysis and simulation results compared to the baseline study have confirmed the efficiency of the proposed HSVMR-D. Furthermore, increased resilience to completely novel changing threats, fewer false positives, and improved accuracy in threat detection are all outcomes that show the proposed work outperforms others. The HSVMR-D approach is helpful where the primary objective is a secure environment in the Internet of Things (IoT) when resources are limited.
- Klíčová slova
- Anomaly Detection, Cyber threats detection, Heuristic algorithms, Hybrid, Integrating, Internet of things, Machine learning, Support Vector Machine, Transfer learning,
- Publikační typ
- časopisecké články MeSH
This study introduces a novel approach for analyzing photovoltaic (PV) systems that employ block lookup tables for speedy and efficient simulation. It introduces an innovative method for tracking the Global Maximum Power Point (GMPP) by utilizing Zebra Optimization Algorithm (ZOA). The suggested method was carefully evaluated under difficult Partial Shading Conditions (PSCs) and Dynamic Shading Conditions (DSCs) to determine its global and local search capability. ZOA's performance was examined in four scenarios and compared to four existing MPPT algorithms: Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Flower Pollination Algorithm (FPA), and Whale Optimization Algorithm (WOA). ZOA surpassed its competitors with an average tracking time of 0.875 s and a tracking efficiency of 99.95% in PSCs. In comparison, ZOA increased tracking efficiency by up to 2%, increased resilience under varied circumstances, and produced a faster convergence speed-approaching the maximum Power Point 10-15% faster than the other algorithms. Furthermore, ZOA significantly decreased operating point variations. The algorithm's overall performance was tested using an experimental setup with a DSPACE board and a PV emulator. These findings demonstrate that ZOA is a highly efficient and dependable MPPT solution for PV systems, especially in severe PSCs.
MXenes, a novel class of two-dimensional (2D) materials known for their excellent electronic conductivity and hydrophilicity, have emerged as promising candidates for lithium-ion battery anodes. This study presents a simple wet-chemical method for depositing interconnected SnO2 nanoparticles (NPs) onto MXene sheets. The SnO2 NPs act as both a high-capacity energy source and a spacer to prevent MXene sheets from restacking. The highly conductive MXene facilitates rapid electron and lithium-ion transport and mitigates the volume changes of SnO₂ during the lithiation/delithiation process by confining the SnO₂ NPs between the MXene layers. This composite anode, SnO2@MXene, leverages the high capacity of SnO2 and the structural and mechanical stability MXene provides. The SnO2@MXene anode exhibits superior electrochemical performance, with a high specific capacity of 678 mAh g- 1 at a current rate of 2.0 A g- 1 over 500 cycles, outperforming pristine MXenes and SnO2 nanoparticles.
- Klíčová slova
- Anode, Deposition of SnO2, Electrochemical performance, LIBs, MXene multilayers,
- Publikační typ
- časopisecké články MeSH
This paper presents a pioneering approach to bolstering network security and privacy by implementing chaotic optical communication with a hybrid optical feedback system (HOFS). The current baseline methods in network security are often less feasible for hybrid feedback systems, including limited robustness, compromised security, and synchronization challenges. Therefore, this paper proposes a hybrid approach to address these shortcomings by integrating the HOFS into chaotic optical communication systems (HOFS-COCS) to overcome the baseline challenges. This paper aims to improve network security while significantly maintaining efficient communication channels. Moreover, We designed two algorithms, one for chaotic maps generation and another for text encryption and decryption, to improve security in the hybrid feedback system. Our findings demonstrate through rigorous experimentation and analysis that the proposed (HOFS-COCS) method significantly improves network security by enabling reliable chaos generation, synchronization, and secure message transmission in chaotic optical communication systems. This research represents a significant advancement towards enhanced secrecy and synchronization in chaotic optical communication systems, promising a paradigm shift in network security protocols.
- Klíčová slova
- Chaotic optical communication, Hybrid optical feedback system, Network security, Protocols,
- Publikační typ
- časopisecké články MeSH
