Posts by Collection

projects

Home Automation System

Published:

Here, the objective was to control the lighting system using a smartphone application.

  • 8051 Microcontroller acts as the controller unit of the project where Kiel u Vision 5 provided its coding interface.
  • HC05 bluetooth module establishes the communication channel between phone and controller.
  • Comparator IC LM324 converts the analog form of the signal to digital form required by the microcontroller
  • Motor driver IC L293d is the small current amplifier which takes in low current control signals from the microcontroller and converts it to higher current signal for the lighting system.






Seq2Seq Architecture based DL chatbot

Published:

This is a Proof-of-Concept Project on Seq2Seq Neural Architecture.

  • Trained on Movie-lens dataset having conversations between different people by building a Seq2Seq neural architecture.
  • It is trained on 100 epochs with a batch size of 64, and number of layers =3. The encoding and decoding embedding size are of 512 each.
  • Dropout regularization used to remove any kind of overfitting and the losses are optimized using Adam optimizer.
  • All the sentences in a batch, whether they are questions/ answers must have the same length. Hence ‘PAD’ tokens used.


Autonomous Self-Driving Car Simulation

Published:

  • Graphics creation using Kivy modules in Python. A car with 3 sensors in front used in the simulation.
  • Deep Q-Learning reinforcement techniques used with specific reward policies where the taxi runs downtown to the airport and back.
  • Sand used for its simulation so that the taxi can learn through experiences stored in a batch of 100.
  • Reward = -1 given to the taxi when it crashes into the sand or reaches outskirts of the city, Reward = -0.2 given when it moves further away from the destination, Reward = +0.1 given when it approaches in correct direction of the destination, Reward =+1 given when it reaches the goal.




Microgrid Energy Management System Optimization

Published:

Winner of the Smart India Hackathon, track set by Mathworks. Later on, the work got accepted in IEEE IEMRE’21. Renewable Energy and Demand Forecasting in integrated smart grid.

  • Designed an integrated microgrid model in Simulink.
  • Load consumption and energy generation were predicted using ensemble learning algorithms and LSTM cells of Recurrent neural networks (RNN) with R2 values of 0.95 for solar, 0.82 for wind, 0.91 for load and 0.95 for price.
  • Linear-Programming based optimization was used for the scheduling of the sources to meet the load demand, minimizing the cost of distribution and storage of power.






Islanding Detection using PMUs and A3C Permalink

Published:

This is a part of my Bachelor’s Thesis:

  • An inbuilt IEEE 34 node bus system is procured where renewable energy sources (PV, Wind and battery) are added at the distribution end in Simulink.
  • Focus is made to work on deep reinforcement learning (A3C) classification framework to identify whether islanding has occurred or not.






publications

Renewable Energy and Demand Forecasting in an Integrated Smart Grid

IEEE International Conference on Innovations in Energy Management and Renewable Resources (IEMRE), 2021

V. V. S. Lanka, M. Roy, S. Suman and S. Prajapati, "Renewable Energy and Demand Forecasting in an Integrated Smart Grid," 2021 Innovations in Energy Management and Renewable Resources(52042), 2021, pp. 1-6, doi: 10.1109/IEMRE52042.2021.9386524.


A Deep Learning Framework for Enhancing Maritime Coastal Security

IEEE 2nd International Conference for Emerging Technology (INCET), 2021

M. Roy, A. Gautam and A. Sugandhi, "A Deep Learning Framework for Enhancing Maritime Coastal Security," 2021 2nd International Conference for Emerging Technology (INCET), 2021, pp. 1-6, doi: 10.1109/INCET51464.2021.9456235.


Reliable Energy Consumption Modeling for an Electric Vehicle Fleet

ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS), 2022

Millend Roy, Akshay Nambi, Anupam Sobti, Tanuja Ganu, Shivkumar Kalyanaraman, Shankar Akella, Jaya Subha Devi, and S A Sundaresan. 2022. "Reliable Energy Consumption Modeling for an Electric Vehicle Fleet," ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS), Association for Computing Machinery, New York, NY, USA, 29–44, doi: 10.1145/3530190.3534803.


A Data Driven Fault Detection Approach with an Ensemble Classifier based Smart Meter in Modern Distribution System

Sustainable Energy, Grids and Networks Journal, 2023

To maintain the continuity of the power supply, a fast and accurate fault detection strategy is required to isolate the fault. In view of this, the paper presents a data driven fault detection approach with an ensemble classifier based smart meter in modern distribution system. To achieve this, a random forest (RF) based fault detection algorithm is programmed within the smart meter. Read more

Soham Dutta, Sourav Kumar Sahu, Millend Roy, Swarnali Dutta, A data driven fault detection approach with an ensemble classifier based smart meter in modern distribution system, Sustainable Energy, Grids and Networks, Volume 34, 2023, 101012, ISSN 2352-4677, https://doi.org/10.1016/j.segan.2023.101012.

Machine Learning Based Adaptive Fault Diagnosis considering Hosting Capacity Amendment in Active Distribution Network

Electric Power Systems Research Journal, 2023

Augmentation of distributed energy resources (DERs) safely in the distribution system termed as hosting capacity (HC) is one of the prominent needs to achieve energy sufficiency with minimum emission. However, any amendment in HC over premeditated injection sets up challenges in the perspective of situational awareness (SA) of networks for precise decision-making related to fault prediction and location. In this work, the author(s) propose histogram-based gradient boost (HGB) algorithm, an accurate machine learning (ML) technique for fault type detection and localization. Read more

Sourav Kumar Sahu, Millend Roy, Soham Dutta, Debomita Ghosh, Dusmanta Kumar Mohanta, "Machine learning based adaptive fault diagnosis considering hosting capacity amendment in active distribution network," Electric Power Systems Research, Volume 216, 2023, 109025, ISSN 0378-7796, https://doi.org/10.1016/j.epsr.2022.109025.

EnCortex: A General, Extensible and Scalable Framework for Decision Management in New-age Energy Systems

Under Review in USENIX NSDI, 2023

EnCortex provides a general, easy-to-use, extensible, and scalable energy decision framework that enables operators to plan, build and execute their real-world scenarios efficiently. We show that using EnCortex, we can define and compose complex new-age scenarios, owing to industry-standard abstractions of energy entities and the modularity of the framework. Read more


talks

IEMRE Conference Proceedings Talk on Renewable Energy and Demand Forecasting in an Integrated Smart Grid

Published:

This is a Conference Proceedings talk where I present how we realistically simulate a microgrid and forecast renewable energies and load demands, along with electricity spot prices. Then, I show the usage of the linear program based scheduler to optimize the total microgrid cost per day.




INCET Conference Proceedings talk on A Deep Learning Framework for Enhancing Maritime Coastal Security

Published:

In this Conference Proceedings talk, I discuss how to tackle maritime coastal security using a deep learning architecture namely faster region based convolutional neural network (Faster R-CNN). We accurately detect vessels in satellite images and output the latitude and longitude coordinates which when merged with AIS data helps identify whether the vessel is registered or not.




Technology and Empowerment Talk on Smart Grid Utilities

Published:

This is an internal talk to Microsoft Research TEM group where I disucuss the challenges faced in the current utility grid structure in India, and how we can move to a better smart-grid archiotectonics keeping the possible hard constraints in mind.




TAB Demo on Project Vasudha

Published:

This is a demo presentation given to the TAB committee on how we are designing Vasudha as a project and seek feedback on how we can improve.


Societal Impact through Cloud and AI technical talk on Project Vasudha

Published:

This is an internal talk to Microsoft Research SCAI group that seeks help or feedback on the current project being worked on. Vasudha, being a collection of projects that offer AI and IoT-enabled technology solutions to drive sustainability goals, here I discuss the portions of work completed uptil date alongside the collaborations with multiple partners which serve as a source of validation and future deployment initiatives.




ACM COMPASS Proceedings Talk on Reliable Energy Consumption Modeling for an Electric Vehicle Fleet

Published:

In this Conference Proceedings talk, I first highlight the challenges in modelling energy consumption and demonstrate the nature of data which is required to understand the energy consumption of electric vehicles under real-world conditions. Then, I discuss our approach and show how it outperforms Deep Learning based modelling for EV energy consumption prediction.




Microsoft Research Fellows’ Graduating Day: Poster Session

Published:

This is an internal poster session in Microsoft Research, where Research Fellows present their journey at MSR to the rest of the Microsoft family.




teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.


Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.


workex

Hem Sheela Model School, Durgapur

Published:


Fiitjee, Durgapur

Published:

<style type="text/css">  .iconDetails {  margin-left:0%; float:left;  height:40px; width:150px;	 }  .container2 {
width:100%;
height:auto;
padding:1%; }   .emphasized { font-style: italic; }

</style>


Indian Institute of Technology (IIT), Delhi

Published:


Hurrey Tech Ventures (R&D), Bangalore

Published:


Microsoft Research Lab India, Bangalore

Published:


Microsoft Research Lab India, Bangalore

Published:


Columbia University in the city of New York

Published: