Searcharxiv⌕ Search

arXiv subjects

Tanmay Mishra

Publications and source records attributed to Tanmay Mishra.

8 recordsLinked to original sources

Job-Level Workload Allocation for Data Centers Under Flexible Interconnections

Flexible interconnections allow data centers to connect to the grid sooner without upgrading the grid infrastructure, if they accept limits on their grid power during periods of grid stress. When a limit is reached, the data center must slow some of its computing jobs. This choice sets the cost of flexibility, because the work done by a job is worth far more than the energy it uses. This paper models how jobs respond when their power is reduced, and proposes a real-time method that shares the available power among jobs according to their value. It also gives grid planners a simple measure of how much power a data center can reduce, and for how long. A one-year case study of a 100-MW data center shows that the proposed method lowers the cost of meeting grid limits, and that on-site generation and storage lower it further.

eess.SY↗

Battery Energy Storage Sizing in PV Ramp-Rate Smoothing using Constraint-Aware Reinforcement Learning-Based Controller

This paper presents a constraint-aware reinforcement learning (CARL) controller for battery energy storage system (BESS) sizing and photovoltaic (PV) ramp-rate smoothing. Rapid PV power fluctuations caused by cloud transitions can introduce operational and stability challenges in power systems. To mitigate these impacts, grid codes impose ramp-rate limits (RRL) on PV power injected to the grid. BESSs can support such grid codes by absorbing or supplying power during rapid variations. However, the extent to which BESSs can reduce PV-induced variability depends on (i) the BESS power and energy capacities; and (ii) the adopted controller. Thus, BESS sizing and controller design are coupled. Conventional moving-average control can increase battery usage due to filter-induced lag, while ramp-rate control is reactive and does not account for the long-term impact of actions on battery state of charge and future ramp events. Optimization-based methods can reduce BESS requirements by anticipating future PV variations, but their performance depends on accurate PV forecasts. To address these limitations, the CARL controller learns a causal state-feedback policy from historical PV data without requiring forecasts during deployment. Ramp-rate, converter-power, and state-of-charge constraints are incorporated into a causal feasibility interval that guarantees feasible actions by definition. A full-horizon input-convex neural network (ICNN)-based optimization is developed as a noncausal benchmark for the minimum achievable BESS requirements. Evaluation using three real-world PV datasets shows that, at a 10\%/min ramp-rate limit, CARL reduces peak BESS power by 8.7--10.4\% and energy capacity by 47.5--62.6\% relative to conventional ramp-rate control while maintaining the grid-codes compliance.

eess.SY↗

Towards Input-Convex Neural Network Modeling for Battery Optimization in Power Systems

Battery energy storage systems (BESS) play an increasingly vital role in integrating renewable generation into power grids due to their ability to dynamically balance supply. Grid-tied batteries typically employ power converters, where part-load efficiencies vary non-linearly. While this non-linearity can be modeled with high accuracy, it poses challenges for optimization, particularly in ensuring computational tractability. In this paper, we consider a non-linear BESS formulation based on the Energy Reservoir Model (ERM). A data-driven approach is introduced with the input-convex neural network (ICNN) to approximate the nonlinear efficiency with a convex function. The epigraph of the convex function is used to engender a convex program for battery ERM optimization. This relaxed ICNN method is applied to two battery optimization use-cases: PV smoothing and revenue maximization, and it is compared with three other ERM formulations (nonlinear, linear, and mixed-integer). Specifically, ICNN-based methods appear to be promising for future battery optimization with desirable feasibility and optimality outcomes across both use-cases.

eess.SY↗

Maximizing Power Flexibility of Hybrid Energy Systems for Capacity Market

Hybrid Energy Systems (HES), integrating generation sources, energy storage, and controllable loads, are well-positioned to provide real-time grid flexibility. However, quantifying this maximum flexibility is challenging due to renewable generation uncertainty and the complexity of power allocation across multiple assets in real time. This paper presents a rule-based framework for characterizing HES flexibility and systematically allocating power among its constituent assets. The flexibility envelope defines the dynamic power boundary within which the HES can inject or absorb power without violating operational constraints. Shaped in real time by capacity bids, available solar generation, and power allocation protocol, it enables reliable and predictable HES participation in regulation markets. Depending on the operational objective, the framework supports both symmetric and asymmetric flexibility cases. Further, the proposed power-allocation rule is benchmarked against an optimal dispatch, providing a performance reference under realistic conditions. Finally, state of charge drift correction control is presented to ensure sustained battery operation and system reliability. This work, therefore, offers a rigorous and practical framework for integrating HES into capacity markets through effective flexibility characterization.

eess.SY↗

Experimental Multi-site Testbed for Advanced Control and Optimization of Hybrid Energy Systems

This paper presents a hybrid energy system (HES) experimental testbed developed at the University of Vermont, featuring a dual-site architecture that integrates on-campus laboratory facility with an off-campus solar and meteorological station. This supports the prototyping and validation of advanced HES control and optimization strategies. The platform integrates hardware-in-the-loop (HIL) simulations with a reconfigurable set of kVA-scale assets.A unified monitoring and communication architecture supports real-time data acquisition, model validation, and control implementation. The capabilities of the testbed are demonstrated through an HIL experiment in which a battery systems participate in solar PV smoothing.

eess.SY↗

Optimal Bidding and Coordinated Dispatch of Hybrid Energy Systems in Regulation Markets

The increasing integration of renewable energy sources and distributed energy resources (DER) into modern power systems introduces significant uncertainty, posing challenges for maintaining grid flexibility and reliability. Hybrid energy systems (HES), composed of controllable generators, flexible loads, and battery storage, offer a decentralized solution to enhance flexibility compared to single centralized resources. This paper presents a two-level framework to enable HES participation in frequency regulation markets. The upper level performs a chance-constrained optimization to choose capacity bids based on historical regulation signals. At the lower level, a real-time control strategy disaggregates the regulation power among the constituent resources. This real-time control strategy is then benchmarked against an offline optimal dispatch to evaluate flexibility performance. Additionally, the framework evaluates the profitability of overbidding strategies and identifies thresholds beyond which performance degradation may lead to market penalties or disqualification. The proposed framework also compare the impact of imbalance of power capacities on performance and battery state of charge (SoC) through asymmetric HES configurations.

eess.SY↗

Predictive Optimization of Hybrid Energy Systems with Temperature Dependency

Hybrid Energy Systems (HES), amalgamating renewable sources, energy storage, and conventional generation, have emerged as a responsive resource for providing valuable grid services. Subsequently, modeling and analysis of HES has become critical, and the quality of grid services hedges on it. Currently, most HES models are temperature-agnostic. However, the temperature-dependent factors can significantly impact HES performance, necessitating advanced modeling and optimization techniques. With the inclusion of temperature-dependent models, the challenges and complexity of solving optimization problem increases. In this paper, the electro-thermal modeling of HES is discussed. Based on this model, a nonlinear predictive optimization framework is formulated. A simplified model is developed to address the challenges associated with solving nonlinear problems. Further, projection and homotopy approaches are proposed. In the homotopy method, the NLP is solved by incrementally changing the C-rating of the battery. Simulation-based analysis of the algorithms highlights the effects of different battery ratings, ambient temperatures, and energy price variations. Finally, comparative assessments with a temperature-agnostic approach illustrates the effectiveness of electro-thermal methods in optimizing HES.

math.OC↗

A Graphical Approach For Brain Haemorrhage Segmentation

Haemorrhaging of the brain is the leading cause of death in people between the ages of 15 and 24 and the third leading cause of death in people older than that. Computed tomography (CT) is an imaging modality used to diagnose neurological emergencies, including stroke and traumatic brain injury. Recent advances in Deep Learning and Image Processing have utilised different modalities like CT scans to help automate the detection and segmentation of brain haemorrhage occurrences. In this paper, we propose a novel implementation of an architecture consisting of traditional Convolutional Neural Networks(CNN) along with Graph Neural Networks(GNN) to produce a holistic model for the task of brain haemorrhage segmentation.GNNs work on the principle of neighbourhood aggregation thus providing a reliable estimate of global structures present in images. GNNs work with few layers thus in turn requiring fewer parameters to work with. We were able to achieve a dice coefficient score of around 0.81 with limited data with our implementation.

eess.IV↗