Rishav Sen

Rishav Sen

Ph.D Candidate @ Vanderbilt University

Publications

You can also find my articles on my Google Scholar profile.

Accepted (Forthcoming)

P-V2B: A Neuro-Symbolic Framework for Leveraging User Persistence in Vehicle-to-Building Charging

Accepted to 17th ACM/IEEE International Conference on Cyber-Physical Systems, 2026

P-V2B is a neuro-symbolic control framework that learns how EV users return to a building each day and uses that persistence to plan charging across multiple days. By combining Monte Carlo MPC with a learned long-horizon value function, it turns routine commuting patterns into a strategic energy buffer that reduces monthly demand peaks and lowers building energy costs while meeting every driver’s required charge.

Impact: Reduces monthly peak demand charges by 3.5% vs. online baselines with guaranteed zero charge-level violations under severe load noise.

Recommended citation: R. Sen, F. Liu, J. P. Talusan, A. Pettet, Y. Suzue, A. Mukhopadhyay, and A. Dubey, P-V2B: A Neuro-Symbolic Framework for Leveraging User Persistence in Vehicle-to-Building Charging, 17th ACM/IEEE International Conference on Cyber-Physical Systems, 2026.

CONSENT: A Negotiation Framework for Leveraging User Flexibility in Vehicle-to-Building Charging under Uncertainty

Accepted to 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), 2026

Developed a strategy-proof, MPC-driven negotiation framework (with real user survey) that leverages EV user flexibility to reduce building energy costs (by 6%) and improve user charging affordability (by 22%) under real-world uncertainty, using data and support from Nissan Motor Corp.

Impact: Deployed and validated with real Nissan data; the first V2B negotiation mechanism proven both strategy-proof and practically effective at scale.

Recommended citation: R. Sen, F. Liu, J. P. Talusan, A. Pettet, Y. Suzue, M. Bailey, A. Mukhopadhyay, and A. Dubey, CONSENT: A Negotiation Framework for Leveraging User Flexibility in Vehicle-to-Building Charging under Uncertainty, 2026.
Download Paper

MoveOD: Synthesizing Origin-Destination Commute Distribution from US Census Data

Accepted to 17th ACM/IEEE International Conference on Cyber-Physical Systems(ICCPS 2026), 2026

[2nd Best Poster at INFORMS 2025 Annual Meeting] A novel framework for synthesizing realistic origin-destination commute distribution patterns from US Census data, enabling data-driven transportation planning and traffic simulation with real-world population movement patterns.

Impact: Provides city planners with a free, open-source tool to generate calibrated mobility demand data without expensive travel surveys.

Recommended citation: R. Sen, A. Dubey, A. Mukhopadhyay, S. Samaranayake, and A. Laszka, MoveOD: Synthesizing Origin-Destination Commute Distribution from US Census Data, 2025.
Download Paper

Conference Papers

Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems

Published in 16th ACM/IEEE International Conference on Cyber-Physical Systems(ICCPS 2025), 2025

Vehicle-to-Building (V2B) systems optimize EV charging and discharging to cut costs, but complexity arises from pricing, planning, and user constraints; we model it as an MDP and use online search with heuristics, achieving state-of-the-art results in real-world tests using data from an EV manufacturer. Developed in collaboration with the V2X team at Nissan Advanced Technical Center - Silicon Valley.

Impact: Achieved state-of-the-art cost performance on real building data from Nissan, outperforming RL and rule-based baselines in both cost reduction and robustness to uncertainty.

Recommended citation: R. Sen, Y. Zhang, F. Liu, J. P. Talusan, A. Pettet, Y. Suzue, A. Mukhopadhyay, and A. Dubey, Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems, 2025.
Download Paper

Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewards

Published in 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), 2025

[Best Paper Award Finalist] Introduces an RL framework combining DDPG and MILP-guided policy shaping to balance feasibility and long-term cost reduction, validated with field-scale building data (≥ 12% compared to real world costs), in collaboration with the V2X team at Nissan Motor Corp.

Impact: Demonstrated ≥12% cost reduction over real-world baselines; recognized as a Best Paper Award Finalist (Top 5% of AAMAS 2025 submissions).

Recommended citation: F. Liu, R. Sen, J. P. Talusan, A. Pettet, A. Kandel, Y. Suzue, A. Mukhopadhyay, and A. Dubey, Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewards, 2025.
Download Paper

Grid-Aware Charging and Operational Optimization for Mixed-Fleet Public Transit

Published in 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

This study presents a robust hierarchical MILP model that optimizes charging and trip assignments for mixed bus fleets (electric and internal combustion engine buses), cutting costs and enhancing sustainability using real-world data from Chattanooga, Tennessee.

Impact: Reduced energy costs by 14% and GHG emissions by 10 tons on the Chattanooga (CARTA) transit system — directly informing the city’s electric fleet transition strategy.

Recommended citation: R. Sen, A. Sivagnanam, A. Laszka, A. Mukhopadhyay, and A. Dubey, Grid-Aware Charging and Operational Optimization for Mixed-Fleet Public Transit, in 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024.
Download Paper | Download Slides

OPTIMUS: Discrete Event Simulator for Vehicle-to-Building Charging Optimization

Published in 2024 IEEE International Conference on Smart Computing (SMARTCOMP), 2024

A comprehensive discrete event simulator for optimizing vehicle-to-building charging operations, enabling detailed analysis of charging strategies and their impact on building energy systems.

Impact: Provides a validated digital twin for stress-testing V2B demand-response strategies under edge-case stochastic inputs; used internally by Nissan and academic partners for resilience benchmarking.

Recommended citation: J. P. Talusan, R. Sen, A. K. Ava Pettet, Y. Suzue, L. Pedersen, A. Mukhopadhyay, and A. Dubey, OPTIMUS: Discrete Event Simulator for Vehicle-to-Building Charging Optimization, in 2024 IEEE International Conference on Smart Computing (SMARTCOMP), 2024.
Download Paper | Download Slides

Calibrating real-world city traffic simulation model using vehicle speed data

Published in 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023

Developed data-driven calibration methods for city-scale traffic simulation models using real-world vehicle speed data, significantly improving accuracy and reliability of traffic predictions for urban planning.

Impact: Improved simulation fidelity for Nashville and Chattanooga city models, enabling more reliable infrastructure and transportation policy evaluation before real-world deployment.

Recommended citation: S. Khaleghian, H. Neema, M. Sartipi, T. Tran, R. Sen, and A. Dubey, Calibrating real-world city traffic simulation model using vehicle speed data, in 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023.
Download Paper

BTE-Sim: Fast simulation environment for public transportation

Published in 2022 IEEE International Conference on Big Data, 2022

Public transit is vital for cities but often stagnates due to static design. BTE-Sim, a fast, multi-layered transit simulation, analyzes population demand, traffic, and road networks to optimize routes, evaluate changes, and improve efficiency with low computation time.

Impact: Achieved dramatically lower computation time than existing multi-agent simulations, enabling rapid iteration on transit route design for Chattanooga and Nashville.

Recommended citation: R. Sen, T. Tran, S. Khaleghian, M. Sartipi, H. Neema, and A. Dubey, BTE-Sim: Fast simulation environment for public transportation, 2022 IEEE International Conference on Big Data, 2022.
Download Paper | Download Slides

E-Transit-Bench: Simulation Platform for Analyzing Electric Public Transit Bus Fleet Operations

Published in ACM International Conference on Future Energy Systems (e-Energy), 2022

A comprehensive transportation-grid co-simulation platform analyzing the spatiotemporal interaction between electric bus transit operations and power distribution grid, enabling holistic fleet optimization.

Impact: First platform to jointly simulate electric bus fleets with power grid constraints; adopted by academic partners for resilience studies and cited in subsequent transit electrification research.

Recommended citation: R. Sen, A. K. Bharati, S. Khaleghian, M. Ghosal, M. Wilbur, T. Tran, P. Pugliese, M. Sartipi, H. Neema, and A. Dubey, E-Transit-Bench: Simulation Platform for Analyzing Electric Public Transit Bus Fleet Operations, in Proceedings of the Thirteenth ACM International Conference on Future Energy Systems, New York, NY, USA, 2022, pp. 532–541.
Download Paper | Download Slides

Microcontroller Based Sensor-Array Data Acquisition System for Electronic Nose

Published in 2020 IEEE Calcutta Conference (CALCON), 2020

A microcontroller-based data acquisition system for electronic nose sensor arrays, enabling efficient data collection and processing.

Recommended citation: N. Debabhuti, R. Sen, A. Sengupta, S. Sengupta, P. Sharma, B. Tudu, N. Bandyopadhyay, and R. Bandyopadhyay, Microcontroller Based Sensor-Array Data Acquisition System for Electronic Nose, in 2020 IEEE Calcutta Conference (CALCON), 2020.
Download Paper

Development of the data acquisition system and GUI for QCM sensor based system

Published in 2020 IEEE Calcutta Conference (CALCON), 2020

Development of a data acquisition system and graphical user interface for QCM (Quartz Crystal Microbalance) sensor-based systems.

Recommended citation: N. Debabhuti, A. Sengupta, P. Sharma, R. Sen, B. Tudu, and R. Bandyopadhyay, Development of the data acquisition system and GUI for QCM sensor based system, in 2020 IEEE Calcutta Conference (CALCON), 2020.
Download Paper

Development of an android platform for monitoring QCM sensor-array based Electronic Nose

Published in 2020 IEEE Applied Signal Processing Conference (ASPCON), 2020

An Android-based platform for monitoring QCM sensor-array electronic nose systems for portable odor detection applications.

Recommended citation: N. Debabhuti, A. Sengupta, R. Sen, A. Ghosh, S. Banerjee, P. Sharma, B. Tudu, N. Bandyopadhyay, and R. Bandyopadhyay, Development of an android platform for monitoring QCM sensor-array based Electronic Nose, in 2020 IEEE Applied Signal Processing Conference (ASPCON), 2020.
Download Paper

Low-Cost Air Pollution Monitoring Device Based on Air Quality Index

Published in 2020 IEEE Applied Signal Processing Conference (ASPCON), 2020

Development of a low-cost air pollution monitoring device utilizing Air Quality Index for environmental monitoring applications.

Recommended citation: R. Bajaj, R. Sen, A. Sengupta, A. Sen, S. Karmakar, S. Ghosh, V. Kumar, B. Tudu, N. Bandyopadhyay, and R. Bandyopadhyay, Low-Cost Air Pollution Monitoring Device Based on Air Quality Index, in 2020 IEEE Applied Signal Processing Conference (ASPCON), 2020.
Download Paper