arXiv subjects

Pratyush Chakraborty

Publications and source records attributed to Pratyush Chakraborty.

At least 19 recordsLinked to original sources

arXiv2026

A Vendor-Agnostic LiDAR Data Conversion System with Multi-Signal Detection and Multi-Format Output

LiDAR (Light Detection and Ranging) sensors capture the surrounding environment as dense 3D point clouds by measuring the time-of-flight of emitted laser pulses, making them foundational across autonomous vehicles, robotics, and large-scale mapping. PCAP (Packet Capture) files from these sensors are the starting point of most 3D perception pipelines, yet internal packet structures, UDP (User Datagram Protocol) port conventions and encoding schemes differ enough across manufacturers that no single tool reads them all. Ouster, Velodyne, Hesai, and Livox each require their own SDK (Software Development Kit), their own environment setup, and their own conversion workflow. Supporting all four means maintaining four disconnected pipelines with no shared infrastructure. The pipeline described here takes a raw PCAP as input and handles vendor identification automatically, scoring six independent file characteristics through a weighted multi-signal approach to determine the source sensor. C++ SDKs handle Ouster and Velodyne, while Hesai and Livox rely on Python-based dpkt parsing where no open source SDK exists. From there, a single command writes output to any of five industry-standard formats. We tested on real outdoor captures. Ouster peaks at 2.08M points per second, Velodyne at 1.47M, both running through native C++ packet decoding. Hesai and Livox land at 110K and 150K respectively, where Python-layer parsing introduces overhead that compounds under sustained load. The 8-10x gap held consistently across runs. Tested on a consumer-grade i3 with 8GB RAM, no vendor configuration required

cs.RO↗

arXiv2026

Optimal Placement and Sizing of PV-Based DG Units in a Distribution Network Considering Loading Capacity

This research paper proposes an efficient methodology for the allocation of multiple photovoltaic (PV)-based distributed generation (DG) units in the radial distribution network (RDN), while considering the loading capacity of the network. The proposed method is structured using a two-stage approach. In the first stage, the additional active power loading capacity of the network and each individual bus is determined using an iterative approach. This analysis quantifies the network's additional active loadability limits and identifies buses with high active power loading capacity, which are considered candidate nodes for the placement of DG units. Subsequently, in the second stage, the optimal locations and sizes of DG units are determined using the Monte Carlo method, with the objectives of minimizing voltage deviation and reducing active power losses in the network. The methodology is validated on the standard IEEE 33-bus RDN to determine the optimal locations and sizes of DG units. The results demonstrate that the optimal allocation of one, two, and three DG units, achieved from proposed method, reduces network active power losses by 50.37%, 58.62%, and 65.16%, respectively, and also significantly enhances the voltage profile across all buses. When the obtained results are compared with the results of several existing studies, it is found that the proposed method allows for larger DG capacities and maintains better voltage profiles throughout the RDN.

eess.SY↗

arXiv2026

Fault Detection in Electrical Distribution System using Autoencoders

In recent times, there has been considerable interest in fault detection within electrical power systems, garnering attention from both academic researchers and industry professionals. Despite the development of numerous fault detection methods and their adaptations over the past decade, their practical application remains highly challenging. Given the probabilistic nature of fault occurrences and parameters, certain decision-making tasks could be approached from a probabilistic standpoint. Protective systems are tasked with the detection, classification, and localization of faulty voltage and current line magnitudes, culminating in the activation of circuit breakers to isolate the faulty line. An essential aspect of designing effective fault detection systems lies in obtaining reliable data for training and testing, which is often scarce. Leveraging deep learning techniques, particularly the powerful capabilities of pattern classifiers in learning, generalizing, and parallel processing, offers promising avenues for intelligent fault detection. To address this, our paper proposes an anomaly-based approach for fault detection in electrical power systems, employing deep autoencoders. Additionally, we utilize Convolutional Autoencoders (CAE) for dimensionality reduction, which, due to its fewer parameters, requires less training time compared to conventional autoencoders. The proposed method demonstrates superior performance and accuracy compared to alternative detection approaches by achieving an accuracy of 97.62% and 99.92% on simulated and publicly available datasets.

eess.SY↗

arXiv2025

Enhanced Rapid Detection of High-impedance Arc Faults in Medium Voltage Electrical Distribution Networks

High-impedance arc faults in AC power systems have the potential to lead to catastrophic accidents. However, significant challenges exist in identifying these faults because of the much weaker characteristics and variety when grounded with different surfaces. Previous research has concentrated predominantly on arc fault detection in low-voltage systems, leaving a significant gap in medium-voltage applications. In this work, a novel approach has been developed that enables rapid arc fault detection for medium-voltage distribution lines. In contrast to existing black-box feature-based approaches, the Hankel alternative view of the Koopman (HAVOK) analysis developed from nonlinear dynamics has been applied, which not only offers interpretable features but also opens up new application options in the area of arc fault detection. The method achieves a much faster detection speed in 0.45 ms, 99.36\% enhanced compared to harmonic randomness and waveform distortion method, thus making it suitable for real-time applications. It demonstrates the ability to detect arc faults across various scenarios, including different grounding surfaces and levels of system noise, boosting its practical importance for stakeholders in safety-critical industries.

eess.SY↗

arXiv2025

Integrated Optimization and Game Theory Framework for Fair Cost Allocation in Community Microgrids

Fair cost allocation in community microgrids remains a significant challenge due to the complex interactions between multiple participants with varying load profiles, distributed energy resources, and storage systems. Traditional cost allocation methods often fail to adequately address the dynamic nature of participant contributions and benefits, leading to inequitable distribution of costs and reduced participant satisfaction. This paper presents a novel framework integrating multi-objective optimization with cooperative game theory for fair and efficient microgrid operation and cost allocation. The proposed approach combines mixed-integer linear programming for optimal resource dispatch with Shapley value analysis for equitable benefit distribution, ensuring both system efficiency and participant satisfaction. The framework was validated using real-world data across six distinct operational scenarios, demonstrating significant improvements in both technical and economic performance. Results show peak demand reductions ranging from 7.8% to 62.6%, solar utilization rates reaching 114.8% through effective storage integration, and cooperative gains of up to $1,801.01 per day. The Shapley value-based allocation achieved balanced benefit-cost distributions, with net positions ranging from -16.0% to +14.2% across different load categories, ensuring sustainable participant cooperation.

eess.SY↗

arXiv2025

Demand Response Optimization MILP Framework for Microgrids with DERs

The integration of renewable energy sources in microgrids introduces significant operational challenges due to their intermittent nature and the mismatch between generation and demand patterns. Effective demand response (DR) strategies are crucial for maintaining system stability and economic efficiency, particularly in microgrids with high renewable penetration. This paper presents a comprehensive mixed-integer linear programming (MILP) framework for optimizing DR operations in a microgrid with solar generation and battery storage systems. The framework incorporates load classification, dynamic price thresholding, and multi-period coordination for optimal DR event scheduling. Analysis across seven distinct operational scenarios demonstrates consistent peak load reduction of 10\% while achieving energy cost savings ranging from 13.1\% to 38.0\%. The highest performance was observed in scenarios with high solar generation, where the framework achieved 38.0\% energy cost reduction through optimal coordination of renewable resources and DR actions. The results validate the framework's effectiveness in managing diverse operational challenges while maintaining system stability and economic efficiency.

eess.SY↗

arXiv2025

A Comprehensive Metric for Resilience Evaluation of Power Distribution Systems under Cyber Attacks

Power distribution systems (PDS) serve as the backbone of our modern society, ensuring electricity reaches homes, businesses, and critical infrastructure. However, the increasing digitization and interconnectivity of these systems have exposed them to cyber threats. This study presents a comprehensive approach to evaluate and enhance the resilience of PDS under cyber attacks using the Common Vulnerability Scoring System (CVSS) and complex network parameters. By systematically assessing vulnerabilities and computing resilience once critical CVSS thresholds are reached, this work identifies key resilience metrics including the critical loads service requirements. The proposed methodology improves system resilience through strategic tie-line switching, which is validated on the modified IEEE 33-bus system. Four case studies are conducted, illustrating the performance of the proposed methodology under various cyber attack scenarios. The results demonstrate the effectiveness of the approach in quantifying and enhancing resilience, offering a valuable tool for PDS operators to mitigate risks and ensure continuous service delivery to critical loads during the exploitation of cyber threats.

eess.SP↗

arXiv2025

CuRLA: Curriculum Learning Based Deep Reinforcement Learning for Autonomous Driving

In autonomous driving, traditional Computer Vision (CV) agents often struggle in unfamiliar situations due to biases in the training data. Deep Reinforcement Learning (DRL) agents address this by learning from experience and maximizing rewards, which helps them adapt to dynamic environments. However, ensuring their generalization remains challenging, especially with static training environments. Additionally, DRL models lack transparency, making it difficult to guarantee safety in all scenarios, particularly those not seen during training. To tackle these issues, we propose a method that combines DRL with Curriculum Learning for autonomous driving. Our approach uses a Proximal Policy Optimization (PPO) agent and a Variational Autoencoder (VAE) to learn safe driving in the CARLA simulator. The agent is trained using two-fold curriculum learning, progressively increasing environment difficulty and incorporating a collision penalty in the reward function to promote safety. This method improves the agent's adaptability and reliability in complex environments, and understand the nuances of balancing multiple reward components from different feedback signals in a single scalar reward function. Keywords: Computer Vision, Deep Reinforcement Learning, Variational Autoencoder, Proximal Policy Optimization, Curriculum Learning, Autonomous Driving.

cs.RO↗

arXiv2024

Advancements in Arc Fault Detection for Electrical Distribution Systems: A Comprehensive Review from Artificial Intelligence Perspective

This comprehensive review paper provides a thorough examination of current advancements and research in the field of arc fault detection for electrical distribution systems. The increasing demand for electricity, coupled with the increasing utilization of renewable energy sources, has necessitated vigilance in safeguarding electrical distribution systems against arc faults. Such faults could lead to catastrophic accidents, including fires, equipment damage, loss of human life, and other critical issues. To mitigate these risks, this review article focuses on the identification and early detection of arc faults, with a particular emphasis on the vital role of artificial intelligence (AI) in the detection and prediction of arc faults. The paper explores a wide range of methodologies for arc fault detection and highlights the superior performance of AI-based methods in accurately identifying arc faults when compared to other approaches. A thorough evaluation of existing methodologies is conducted by categorizing them into distinct groups, which provides a structured framework for understanding the current state of arc fault detection techniques. This categorization serves as a foundation for identifying the existing constraints and future research avenues in the domain of arc fault detection for electrical distribution systems. This review paper provides the state of the art in arc fault detection, aiming to enhance safety and reliability in electrical distribution systems and guide future research efforts.

eess.SY↗

arXiv2024

Detection of High-Impedance Low-Current Arc Faults at Electrical Substations

Arcing faults in low voltage (LV) distribution systems associated with arc-flash risk and potentially significant equipment damage are notoriously difficult to detect under some conditions. Especially so when attempting to detect using sensing at the line, high voltage side of a substation transformer. This paper presents an analytics-based physics-aware approach to detect high-impedance, low-current arcing faults from the primary side of the substation transformer at current thresholds, below normal operating events, along with transformer inrush currents. The proposed methodology leverages the Hankel Alternative View Of Koopman Operator approach to differentiate arcing faults from standard operations, while the Series2Graph method is employed to identify the time of fault occurrence and duration. Unlike prior studies that detect such faults at the device or secondary transformer side, this work demonstrates successful fault detection at the primary side of the distribution substation transformer for faults occurring on the secondary side. The approach addresses the practical challenges of differentiating primary side expected and acceptable transients from similar magnitude LV arcing fault currents that may occur on the secondary side. The results demonstrate the efficacy of the proposed method in accurately identifying fault occurrence and duration, minimizing the risk of false positives during similar characteristic events, thus improving the reliability and operational efficiency of power distribution systems. This approach can benefit both traditional and smart power grids that employ similar transformer configurations.

eess.SY↗

arXiv2024

Fault Classification in Electrical Distribution Systems using Grassmann Manifold

Electrical fault classification is vital for ensuring the reliability and safety of power systems. Accurate and efficient fault classification methods are essential for timely and effective maintenance. In this paper, we propose a novel approach for effective fault classification through Grassmann manifolds, which is a non-Euclidean space that captures the intrinsic structure of high-dimensional data and offers a robust framework for feature extraction. We use simulated data for electrical distribution systems with various types of electrical faults. The proposed method involves transforming the measurement fault data into Grassmann manifold space using techniques from differential geometry. This transformation aids in uncovering the underlying fault patterns and reducing the computational complexity of subsequent classification steps. To achieve fault classification, we employ a machine learning technique optimized for the Grassmann manifold. The support vector machine classifier is adapted to operate within the Grassmann manifold space, enabling effective discrimination between different fault classes. The results illustrate the efficacy of the proposed Grassmann manifold-based approach for electrical fault classification which showcases its ability to accurately differentiate between various fault types.

eess.SY↗

arXiv2024

Efficient Fault Detection and Categorization in Electrical Distribution Systems Using Hessian Locally Linear Embedding on Measurement Data

Faults on electrical power lines could severely compromise both the reliability and safety of power systems, leading to unstable power delivery and increased outage risks. They pose significant safety hazards, necessitating swift detection and mitigation to maintain electrical infrastructure integrity and ensure continuous power supply. Hence, accurate detection and categorization of electrical faults are pivotal for optimized power system maintenance and operation. In this work, we propose a novel approach for detecting and categorizing electrical faults using the Hessian locally linear embedding (HLLE) technique and subsequent clustering with t-SNE (t-distributed stochastic neighbor embedding) and Gaussian mixture model (GMM). First, we employ HLLE to transform high-dimensional (HD) electrical data into low-dimensional (LD) embedding coordinates. This technique effectively captures the inherent variations and patterns in the data, enabling robust feature extraction. Next, we perform the Mann-Whitney U test based on the feature space of the embedding coordinates for fault detection. This statistical approach allows us to detect electrical faults providing an efficient means of system monitoring and control. Furthermore, to enhance fault categorization, we employ t-SNE with GMM to cluster the detected faults into various categories. To evaluate the performance of the proposed method, we conduct extensive simulations on an electrical system integrated with solar farm. Our results demonstrate that the proposed approach exhibits effective fault detection and clustering across a range of fault types with different variations of the same fault. Overall, this research presents an effective methodology for robust fault detection and categorization in electrical systems, contributing to the advancement of fault management practices and the prevention of system failures.

eess.SY↗

arXiv2024

Identification of Surface Defects on Solar PV Panels and Wind Turbine Blades using Attention based Deep Learning Model

The global generation of renewable energy has rapidly increased, primarily due to the installation of large-scale renewable energy power plants. However, monitoring renewable energy assets in these large plants remains challenging due to environmental factors that could result in reduced power generation, malfunctioning, and degradation of asset life. Therefore, the detection of surface defects on renewable energy assets is crucial for maintaining the performance and efficiency of these plants. This paper proposes an innovative detection framework to achieve an economical surface monitoring system for renewable energy assets. High-resolution images of the assets are captured regularly and inspected to identify surface or structural damages on solar panels and wind turbine blades. {Vision transformer (ViT), one of the latest attention-based deep learning (DL) models in computer vision, is proposed in this work to classify surface defects.} The ViT model outperforms other DL models, including MobileNet, VGG16, Xception, EfficientNetB7, and ResNet50, achieving high accuracy scores above 97\% for both wind and solar plant assets. From the results, our proposed model demonstrates its potential for monitoring and detecting damages in renewable energy assets for efficient and reliable operation of renewable power plants.

cs.CV↗

arXiv2024

Energy Sharing among Resources within Electrical Distribution Systems: A Systematic Review

The rapid increase in Electric Vehicle (EV) adoption provides a promising solution for reducing carbon emissions and fossil fuel dependency in transportation systems. However, the increasing numbers of EVs pose significant challenges to the electrical grids. In addition, the number of Distributed Energy Resources (DER) and Microgrids (MGs) is increasing on a global scale to meet the energy demand, consequently changing the energy infrastructure. Recently, energy-sharing methods have been proposed to share excess energy from DERs and EVs in Electric Vehicle Charging Infrastructure (EVCI) and MGs. Accommodating this sharing mechanism with the existing electrical distribution systems is a critical issue concerning the economic, reliability, and resilience aspects. This study examines the ever-changing field of EVCI and the critical role of peer-to-peer (P2P) energy trading in mitigating the problems with grid management that result from unorganized EV charging and intermittency in DER. Also, the possibility of energy sharing in electrical distribution systems for microgrids and EVCI on various energy-sharing methods and algorithms are discussed in detail. Furthermore, the application of market clearing algorithms like game theory, double auction theory, blockchain technology, optimization techniques, machine learning algorithms, and other models from the existing literature are presented. This paper discusses the policies, economic benefits, environmental impacts, societal advantages, and challenges in distribution systems related to sharing in EVCI and MGs. A roadmap for future research and sharing strategies is provided to guide policymakers, researchers, and industry stakeholders toward a sustainable, resilient, and efficient energy market by integrating P2P technology into EVCIs and MGs.

eess.SY↗

arXiv2023

Modelling of the Electric Vehicle Charging Infrastructure as Cyber Physical Power Systems: A Review on Components, Standards, Vulnerabilities and Attacks

The increasing number of electric vehicles (EVs) has led to the growing need to establish EV charging infrastructures (EVCIs) with fast charging capabilities to reduce congestion at the EV charging stations (EVCS) and also provide alternative solutions for EV owners without residential charging facilities. The EV charging stations are broadly classified based on i) where the charging equipment is located - on-board and off-board charging stations, and ii) the type of current and power levels - AC and DC charging stations. The DC charging stations are further classified into fast and extreme fast charging stations. This article focuses mainly on several components that model the EVCI as a cyberphysical system (CPS).

eess.SY↗

arXiv2023

Advancements in Enhancing Resilience of Electrical Distribution Systems: A Review on Frameworks, Metrics, and Technological Innovations

This comprehensive review paper explores power system resilience, emphasizing its evolution, comparison with reliability, and conducting a thorough analysis of the definition and characteristics of resilience. The paper presents the resilience frameworks and the application of quantitative power system resilience metrics to assess and quantify resilience. Additionally, it investigates the relevance of complex network theory in the context of power system resilience. An integral part of this review involves examining the incorporation of data-driven techniques in enhancing power system resilience. This includes the role of data-driven methods in enhancing power system resilience and predictive analytics. Further, the paper explores the recent techniques employed for resilience enhancement, which includes planning and operational techniques. Also, a detailed explanation of microgrid (MG) deployment, renewable energy integration, and peer-to-peer (P2P) energy trading in fortifying power systems against disruptions is provided. An analysis of existing research gaps and challenges is discussed for future directions toward improvements in power system resilience. Thus, a comprehensive understanding of power system resilience is provided, which helps in improving the ability of distribution systems to withstand and recover from extreme events and disruptions.

eess.SY↗

arXiv2023

Planning of Fast Charging Infrastructure for Electric Vehicles in a Distribution System and Prediction of Dynamic Price

The increasing number of electric vehicles (EVs) has led to the need for installing public electric vehicle charging stations (EVCS) to facilitate ease of use and to support users who do not have the option of residential charging. The public electric vehicle charging infrastructures (EVCIs) must be equipped with a good number of EVCSs, with fast charging capability, to accommodate the EV traffic demand, which would otherwise lead to congestion at the charging stations. The location of these fast-charging infrastructures significantly impacts the distribution system (DS). We propose the optimal placement of fast-charging EVCIs at different locations in the distribution system, using multi-objective particle swarm optimization (MOPSO), so that the power loss and voltage deviations are kept at a minimum. Time-series analysis of the DS and EV load variations are performed using MATLAB and OpenDSS. We further analyze the cost benefits of the EVCIs under real-time pricing conditions and employ an autoregressive integrated moving average (ARIMA) model to predict the dynamic price. The simulated test system without any EVCI has a power loss of 164.36 kW and squared voltage deviations of 0.0235 p.u. Using the proposed method, the results obtained validate the optimal location of 5 EVCIs (each having 20 EVCSs with a 50kWh charger rating) resulting in a minimum power loss of 201.40 kW and squared voltage deviations of 0.0182 p.u. in the system. Significant cost benefits for the EVCIs are also achieved, and an R-squared value of dynamic price predictions of 0.9999 is obtained. This would allow the charging station operator to make promotional offers for maximizing utilization and increasing profits.

eess.SY↗

arXiv2023

A Resilient Power Distribution System using P2P Energy Sharing

The adoption of distributed energy resources (DERs) such as solar panels and wind turbines is transforming the traditional energy grid into a more decentralized system, where microgrids are emerging as a key concept. Peer-to-Peer (P2P) energy sharing in microgrids enhances the efficiency and flexibility of the overall system by allowing the exchange of surplus energy and better management of energy resources. This work analyzes the impact of P2P energy sharing for three cases - within a microgrid, with neighbouring microgrids, and all microgrids combined together in a distribution system. A standard IEEE 123 node test feeder integrated with renewable energy sources is partitioned into microgrids. For P2P energy sharing between microgrids, the results show significant benefits in cost, reduced energy dependence on the grid, and a significant improvement in the system's resilience. We also predicted the energy requirement for a microgrid to evaluate energy resilience for the control and operation of the microgrid. Overall, the analysis provides valuable insights into the performance and sustainability of microgrids with P2P energy sharing.

eess.SY↗