arXiv subjects

Mayukha Pal

Publications and source records attributed to Mayukha Pal.

42 records · Page 3Linked to original sources

arXiv2023

Data-Driven Approach to form Energy Resilient Smart Microgrids with Identification of Vulnerable Nodes in Active Electrical Distribution Network

With the commitment to climate, globally many countries started reducing brownfield energy production and strongly opting towards green energy resources. However, the optimal allocation of distributed energy resources (DERs) in electrical distribution systems still pertains as a challenging issue to attain the maximum benefits. It happens due to the systems complex behaviour and inappropriate integration of DERs that adversely affects the distribution grid. In this work, we propose a methodology for the optimal allocation of DERs with vulnerable node identification in active electrical distribution networks. A failure or extreme event at the vulnerable node would interrupt the power flow in the distribution network. Also, the power variation in these vulnerable nodes would significantly affect the operation of other linked nodes. Thus, these nodes are found suitable for the optimal placement of DERs. We demonstrate the proposed data-driven approach on a standard IEEE-123 bus test feeder. Initially, we partitioned the distribution system into optimal microgrids using graph theory and graph neural network (GNN) architecture. Further, using Granger causality analysis, we identified vulnerable nodes in the partitioned microgrid; suitable for DERs integration. The placement of DERs on the vulnerable nodes enhanced network reliability and resilience. Improvement in resilience is validated by computing the percolation threshold for the microgrid networks. The results show a 20.45% improvement in the resilience of the system due to the optimal allocation of DERs.

eess.SY↗

arXiv2023

Machine Learning as an Accurate Predictor for Percolation Threshold of Diverse Networks

The percolation threshold is an important measure to determine the inherent rigidity of large networks. Predictors of the percolation threshold for large networks are computationally intense to run, hence it is a necessity to develop predictors of the percolation threshold of networks, that do not rely on numerical simulations. We demonstrate the efficacy of five machine learning-based regression techniques for the accurate prediction of the percolation threshold. The dataset generated to train the machine learning models contains a total of 777 real and synthetic networks. It consists of 5 statistical and structural properties of networks as features and the numerically computed percolation threshold as the output attribute. We establish that the machine learning models outperform three existing empirical estimators of bond percolation threshold, and extend this experiment to predict site and explosive percolation. Further, we compared the performance of our models in predicting the percolation threshold using RMSE values. The gradient boosting regressor, multilayer perceptron and random forests regression models achieve the least RMSE values among considered models.

physics.soc-ph↗

arXiv2023

CerviFormer: A Pap-smear based cervical cancer classification method using cross attention and latent transformer

Purpose: Cervical cancer is one of the primary causes of death in women. It should be diagnosed early and treated according to the best medical advice, as with other diseases, to ensure that its effects are as minimal as possible. Pap smear images are one of the most constructive ways for identifying this type of cancer. This study proposes a cross-attention-based Transfomer approach for the reliable classification of cervical cancer in Pap smear images. Methods: In this study, we propose the CerviFormer -- a model that depends on the Transformers and thereby requires minimal architectural assumptions about the size of the input data. The model uses a cross-attention technique to repeatedly consolidate the input data into a compact latent Transformer module, which enables it to manage very large-scale inputs. We evaluated our model on two publicly available Pap smear datasets. Results: For 3-state classification on the Sipakmed data, the model achieved an accuracy of 93.70%. For 2-state classification on the Herlev data, the model achieved an accuracy of 94.57%. Conclusion: Experimental results on two publicly accessible datasets demonstrate that the proposed method achieves competitive results when compared to contemporary approaches. The proposed method brings forth a comprehensive classification model to detect cervical cancer in Pap smear images. This may aid medical professionals in providing better cervical cancer treatment, consequently, enhancing the overall effectiveness of the entire testing process.

eess.IV↗

arXiv2022

Detection of Malfunctioning Modules in Photovoltaic Power Plants using Unsupervised Feature Clustering Segmentation Algorithm

The energy transition towards photovoltaic solar energy has evolved to be a viable and sustainable source for the generation of electricity. It has effectively emerged as an alternative to the conventional mode of electricity generation for developing countries to meet their energy requirement. Thus, many solar power plants have been set up across the globe. However, in these large-scale or remote solar power plants, monitoring and maintenance persist as challenging tasks, mainly identifying faulty or malfunctioning cells in photovoltaic (PV) panels. In this paper, we use an unsupervised deep-learning image segmentation model for the detection of internal faults such as hot spots and snail trails in PV panels. Generally, training or ground truth labels are not available for large solar power plants, thus the proposed model is highly recommended as it does not require any prior learning or training. It extracts the features from the input image and segments out the faults in the image. Here we use infrared thermal images of the PV panel as input, passed to a convolutional neural network which assigns cluster labels to the pixels. Further, optimize the pixel labels, features and model parameters using backpropagation based on iterative stochastic gradient descent. Then, we compute similarity loss and spatial continuity loss to assign the same label to the pixel with similar features and spatial continuity to reduce noises in the image segmentation process. The effectiveness of the proposed approach was examined on an online available dataset for the recognition of snail trails and hot spot failures in monocrystalline solar panels.

eess.IV↗

arXiv2022

Evaluation of Energy Resilience and Cost Benefit in Microgrid with Peer-to-Peer Energy Trading

Integration of distributed energy resources (DERs) at a residential level has given way to the development of a self-sufficient energy-resilient system and peer-to-peer (P2P) energy trading at a community level. Several researchers have developed models to implement energy trading in the P2P network with DERs that enables prosumers to avail cost benefits. However, the impact of DERs and P2P energy network on the system's resilience is not evaluated with a quantifiable measure. In this work, we use the percolation threshold as a measure to quantify energy resilience, which can be computed using complex network. We consider a standard IEEE-123 node test feeder integrated with renewable energy sources and partitioned into microgrids. The microgrid with the highest percolation threshold value is considered for P2P energy trading analysis. We use cooperative game theory to model the P2P energy trading so that all prosumers take part rationally. The simulation is carried out using time series data of houses with varying load profiles, solar generation, and energy storage capacities. The results show 5.81\% of total cost benefit in a year and 10.67\% improvement in the resilience of the system due to P2P energy trading.

eess.SY↗

arXiv2022

Local Interpretable Model Agnostic Shap Explanations for machine learning models

With the advancement of technology for artificial intelligence (AI) based solutions and analytics compute engines, machine learning (ML) models are getting more complex day by day. Most of these models are generally used as a black box without user interpretability. Such complex ML models make it more difficult for people to understand or trust their predictions. There are variety of frameworks using explainable AI (XAI) methods to demonstrate explainability and interpretability of ML models to make their predictions more trustworthy. In this manuscript, we propose a methodology that we define as Local Interpretable Model Agnostic Shap Explanations (LIMASE). This proposed ML explanation technique uses Shapley values under the LIME paradigm to achieve the following (a) explain prediction of any model by using a locally faithful and interpretable decision tree model on which the Tree Explainer is used to calculate the shapley values and give visually interpretable explanations. (b) provide visually interpretable global explanations by plotting local explanations of several data points. (c) demonstrate solution for the submodular optimization problem. (d) also bring insight into regional interpretation e) faster computation compared to use of kernel explainer.

cs.LG↗