publications

2026

1. 

   AlphaSearch: Agentic AI for Price Arbitrage in Energy Systems

   Millend Roy and Vladimir Pyltsov

   In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Republic of Korea, 2026

   Abs DOI Video Code

   Wholesale electricity prices are highly volatile due to fluctuations in weather, renewable generation, demand, and grid conditions. These fluctuations create arbitrage opportunities for energy storage, but realizing this value requires dispatch decisions that account for price uncertainty, battery constraints, and deployment complexity. Existing approaches often require practitioners to separately manage forecasting, optimization, feasibility constraints, and evaluation, making deployment fragmented and hard to interpret. We propose ?search, an agentic AI framework for battery arbitrage that accounts for price uncertainty in wholesale electricity markets. ?search supports and benchmarks heuristic, optimization-based, reinforcement learning, and LLM-assisted decision-making approaches across multiple Independent System Operator (ISO) datasets. We further conduct a series of stress tests to assess the effectiveness of these methods in realistic market settings.

2. 

   PREFER: Personalized Review Summarization with Online Preference Learning

   Millend Roy, Agostino Capponi, and Vineet Goyal

   arXiv preprint arXiv:2605.05911, 2026

   arXiv Code

2025

1. CapOptix: An Options-Framework for Capacity Market Pricing

   Millend Roy, Agostino Capponi, Vladimir Pyltsov, and 2 more authors

   arXiv preprint arXiv:2512.12871, 2025

   arXiv Code

2. 

   Dynamic Incentive Design for Demand Response in Energy System MicroGrids

   Millend Roy, Vladimir Pyltsov, Ruturaj Godse, and 1 more author

   In Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems, , 2025

   Abs DOI Code

   The integration of renewable energy sources into microgrids introduces variability and unpredictability, requiring innovative solutions to balance supply and demand. Demand Response (DR) programs incentivize consumers to adjust energy usage during critical periods, reducing grid stress and improving efficiency. This paper presents a dynamic DR incentive framework that leverages day-ahead forecasts to optimize price discounts while maintaining occupant comfort. Using contextual multi-armed bandits (MAB) and mixed-integer linear programming (MILP), our approach dynamically adapts to fluctuating renewable generation, energy prices, and consumer preferences. Unlike traditional rule-based methods, it optimizes incentives to maximize consumer participation and grid stability while minimizing reliance on costly diesel generators. Simulation results demonstrate significant improvements in financial sustainability and operational efficiency, highlighting the potential of data-driven incentive designs for resilient and adaptive energy systems.

3. 

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

   Millend Roy, Vaibhav Balloli, Anupam Sobti, and 4 more authors

   arXiv preprint arXiv:2503.06959, 2025

   arXiv Code

2023

1. 

   A data driven fault detection approach with an ensemble classifier based smart meter in modern distribution system

   Soham Dutta, Sourav Kumar Sahu, Millend Roy, and 1 more author

   Sustainable Energy, Grids and Networks, 2023

   Abs DOI

   The operation of the distribution grids is constantly being threatened by occurrence of faults. These faults are unpredictable and dangerous. Moreover, the introduction of distributed generations (DGs) in modern distribution networks has made the detection of these faults more complicated. Thus, 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. At first, the magnitude of maximum angular difference between positive and zero sequence component of the current at the DG bus is computed. The computed value is then fed to a trained RF classifier for detecting fault conditions. The greatest advantage of the proposed algorithm is the non-requisite of additional hardware or software kit for fault detection. The algorithm undergoes several test conditions to showcase its effectiveness. The algorithm depicts a high accuracy of 98.95%. The results signify that the algorithm is robust, reliable and accurate with an additional benefit of augmenting situational awareness.

2. 

   Machine learning based adaptive fault diagnosis considering hosting capacity amendment in active distribution network

   Sourav Kumar Sahu, Millend Roy, Soham Dutta, and 2 more authors

   Electric Power Systems Research, 2023

   Abs DOI

   Augmentation of distributed energy resources (DERs) safely in 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 perspective of situational awareness (SA) of networks for precise decision-making related to fault prediction and location. In this work, authors propose histogram-based gradient boost (HGB) algorithm, an accurate machine learning (ML) technique for fault type detection and location. Due to the unique characteristic of noise cancelation, spectral-kurtosis is utilized for extraction of features of the faulted transient signals. For improved competence of the process, optimized feature importance values are considered. In order to study the efficacy of the proposed method, HC of the network is altered, leading to up-gradation of network parameters. These upgraded parameters are used for retraining the proposed ML algorithm for desired SA, with perception, comprehension, projection, and accurate decision making. The authors also considered other ML techniques to showcase a comparative study with the HGB. The entire analysis is tested on reconfigured IEEE-33 bus distribution system developed in Typhoon HIL real-time simulator. The proposed methodology is also meticulously compared with existing literature to establish its excellence.

2022

1. 

   Reliable Energy Consumption Modeling for an Electric Vehicle Fleet

   Millend Roy, Akshay Nambi, Anupam Sobti, and 5 more authors

   In Proceedings of the 5th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies, Seattle, WA, USA, 2022

   Abs DOI

   Accurately predicting the energy consumption of an electric vehicle (EV) under real-world circumstances (such as varying road, traffic, weather conditions, etc.) is critical for a number of decisions like range estimation and route planning. A major concern for electric vehicle owners is the uncertain nature of the battery consumption. This results in the “range anxiety” and reluctance from users for mass adoption of EVs, since they are concerned about untimely drainage of battery. Even at the organizational level, a company running a fleet of electric vehicles must understand the battery consumption profiles accurately for tasks such as route and driver planning, battery sizing, maintenance planning, etc. In this paper, firstly, we 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, through a large and diverse dataset collected over 23,500 hours spanning ≈ 460,000 km with 27 vehicles, we demonstrate our two-stage approach to predict the energy consumption of an EV before the start of the trip. In our energy consumption modelling approach, apart from the primary features recorded directly before the trip, we also construct and predict secondary features through an extensive feature engineering process, both of which are then used to predict the energy consumption. We show that our approach outperforms Deep Learning based modelling for EV energy consumption prediction, and also provides explainable and interpretable models for domain experts. This novel method results in energy consumption modelling with of Mean Absolute Percentage Error (MAPE) on our dataset and significantly outperforms state-of-the-art results in EV energy consumption modeling.

2021

1. 

   A Deep Learning Framework for Enhancing Maritime Coastal Security

   Millend Roy, Abhinav Gautam, and Aayush Sugandhi

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

   DOI

2. 

   Renewable Energy and Demand Forecasting in an Integrated Smart Grid

   Vishnu Vardhan Sai Lanka, Millend Roy, Shikhar Suman, and 1 more author

   In 2021 Innovations in Energy Management and Renewable Resources(52042), 2021

   DOI Code