Accurate detection and classification of Power Quality Disturbances (PQDs) are critical for ensuring reliability in modern distribution networks with high renewable energy penetration. This study evaluates four signal decomposition methods—Empirical Mode Decomposition (EMD), Ensemble EMD (EEMD), Complete Ensemble EMD with Adaptive Noise (CEEMDAN), and Variational Mode Decomposition (VMD)—in conjunction with a Random Forest Classifier (RFC) for PQD classification. The IEEE-1159 synthetic benchmark dataset comprising fifteen single and multiple PQD classes was used for training and testing, with 5-fold cross-validation employed to ensure robustness. Hyper parameter tuning of the RF model was performed using grid search to optimize the number of trees, depth, and feature selection strategy. Among the methods, VMD + RFC consistently outperformed the EMD-family techniques, achieving a confusion matrix–based accuracy of 99.16% and a cross-validation accuracy of 94.6% ± 1.42 (95% CI). Paired t-tests confirmed that the accuracy improvements of VMD over the other decomposition methods were statistically significant (p < 0.05). Beyond synthetic benchmarks, the proposed study was validated on a field dataset of the university campus in India collected at the point of common coupling (PCC) where a 500 kWp photovoltaic (PV) system is integrated. Here, VMD + RFC predictions are closely aligned with the reference PQA logs, demonstrating strong generalization capability. The results establish VMD + RFC as a robust and computationally efficient study for PQD classification, combining superior accuracy, statistical significance, and real-world applicability. This contributes both methodological rigor and practical validation, distinguishing the work from prior studies limited to smaller PQD sets or lacking external verification.
31 August 2023 in International Journal of Intelligent Engineering and Systems
Self-forming and adaptation characteristics make MANETs suitable to deploy at places where Infrastructure is hard to set up. It consists of peer-to-peer mobile nodes with heterogeneous resources. Applications of the networks include healthcare, disaster recovery, and the military. The data present in these applications is susceptible. High-level security mechanisms are required to protect the data. One of the attacks present at the network layer in MANETs is packet dropping by the intermediatory node during the communication. The number of Mitigation mechanisms devised to focus on the issue but fail to differentiate packet dropping is due to malicious behavior of the node or system fault. Thus, the paper aims to develop a mechanism that mitigates the packet-dropping nodes from the communication path, whether due to system faults or malicious. The proposed work is validated with a network simulator. The results demonstrate that the proposed work achieved the most outstanding throughput compared to the current work.
1 March 2024 in International Journal of Power Electronics and Drive Systems (IJPEDS)
In this research paper effect of pandemic and performance analysis of the utility grid connected PV system under net metering is evaluated for one years based on PV plant generation data. The performance of the system depends on annual average final yield, reference yield, and array yield and their values are 3.87 kWh kWp-1. d-1, 4.57 kWh kWp-1. d-1, and 4.29 7kWh kWp-1d-1 the performance ratio and capacity utilization factor are 77.48% and 15.68%. Due to pandemic campus energy consumption is less so energy export to grid is more than the energy import from grid. As per the state energy policy minimum billing is done even the export units are more than the imported units which result in increase in return on investment (ROI) compared to post pandemic. The above statistics illustrate the quite strong performance of solar power plants built in the Indian state of the Andhra Pradesh, Guntur.