arXiv subjects

Ram Rajagopal

Publications and source records attributed to Ram Rajagopal.

At least 19 recordsLinked to original sources

arXiv2026

Optimizing Energy Efficiency and Grid Stability via Public EV Charging Flexibility

This study evaluates the potential of electric vehicle (EV) charging flexibility to enhance both energy efficiency and power grid stability. Using real-world data from public charging stations in Prague, we analyze individual and aggregated charging sessions to explore how optimizing charging times can reduce energy waste, minimize grid imbalances, and support the integration of renewable energy. By aligning EV charging with periods of lower grid demand and higher renewable generation, we demonstrate a significant improvement in energy efficiency, reduc ing the need for costly system support and ancillary services. Our findings suggest that cooperation between power distributors and transmission system operators can unlock new opportunities for maintaining grid stability while promoting sustainable energy use in an increasingly uncertain energy landscape.

math.OC↗

arXiv2026

EasyRider: Mitigating Power Transients in Datacenter-Scale Training Workloads

Large-scale AI model training workloads use thousands of GPUs operating in tightly synchronized loops. During synchronous communication, start-up, shut-down, and checkpointing, GPU power consumption can swing from peak to idle within milliseconds. These large and rapid load swings endanger grid infrastructure as they induce steep power ramp rates, voltage and frequency shifts, and reactive power transients that can damage transformers, converters, and protection equipment. To solve this problem, we introduce EasyRider, a power architecture to mitigate power fluctuations at the rack level. EasyRider uses passive components and actively-controlled auxiliary energy storage to attenuate rack power swings. A software system continually monitors the energy storage system to maximize its lifetime in the presence of frequent charge/discharge cycles. EasyRider filters rack power variations to be within grid safety requirements without requiring software modifications to AI training frameworks or wasting energy. We evaluate EasyRider on a 400VDC-rated prototype system against published workload traces and our own GPU testbed, demonstrating its effectiveness across heterogeneous power levels and workload power profiles.

cs.AR↗

arXiv2026

From Servers to Sites: Compositional Power Trace Generation of LLM Inference for Infrastructure Planning

Datacenter operators and electrical utilities rely on power traces at different spatiotemporal scales. Operators use fine-grained traces for provisioning, facility management, and scheduling, while utilities use site-level load profiles for capacity and interconnection planning. Existing datacenter power models do not capture LLM inference workloads, in which GPUs shift rapidly among compute-intensive prefill, lower-power decode, and idle states, and facility demand depends on how these states evolve and synchronize across many devices. We show that LLM inference power can be represented compositionally through two components: workload-driven transitions among operating states and configuration-specific power distributions within those states. Building on this observation, we develop a trace-generation framework that learns from measured traces and synthesizes power profiles for new traffic conditions and serving configurations. These traces aggregate from GPU servers to rack-, row-, and facility-scale load profiles at the temporal granularity required by the study. Across multiple LLMs, tensor-parallel settings, and GPU generations, our framework achieves median absolute energy error below 5% for most configurations while preserving temporal autocorrelation structure. The resulting traces support downstream analyses including oversubscription, power modulation, and utility-facing load characterization, enabling infrastructure evaluations that flat nameplate assumptions and static trace replay cannot support.

cs.DC↗

arXiv2026

Beyond Uptime: Actionable Performance Metrics for EV Charging Site Operators

The transition to electric vehicles (EVs) depends heavily on the reliability of charging infrastructure, yet approximately 1 in 5 drivers report being unable to charge during station visits due to inoperable equipment. While regulatory efforts such as the National Electric Vehicle Infrastructure (NEVI) program have established uptime requirements, these metrics are often simplistic, delayed, and fail to provide the diagnostic granularity needed by Charging Site Operators (CSOs). Despite their pivotal role in maintaining and improving site performance, CSOs have been largely overlooked by existing reporting standards. In this paper, we propose a suite of readily computable, actionable performance metrics-Fault Time, Fault-Reason Time, and Unreachable Time-that decompose charger behavior into operationally meaningful states. Unlike traditional uptime, these metrics are defined over configurable periods and distinguish between hardware malfunctions and network connectivity issues. We demonstrate the implementation of these metrics via an open-source tool that derives performance data from existing infrastructure without requiring hardware modifications. A case study involving 98 chargers at a California academic institution spanning 2018-2024 demonstrates that these metrics reveal persistent "zombie chargers" and high-frequency network instability that remain hidden in standard annual reporting.

eess.SY↗

arXiv2025

Large-Scale Network Utility Maximization via GPU-Accelerated Proximal Message Passing

We present a GPU-accelerated proximal message passing algorithm for large-scale network utility maximization (NUM). NUM is a fundamental problem in resource allocation, where resources are allocated across various streams in a network to maximize total utility while respecting link capacity constraints. Our method, a variant of ADMM, requires only sparse matrix-vector multiplies with the link-route matrix and element-wise proximal operator evaluations, enabling fully parallel updates across streams and links. It also supports heterogeneous utility types, including logarithmic utilities common in NUM, and does not assume strict concavity. We implement our method in PyTorch and demonstrate its performance on problems with tens of millions of variables and constraints, achieving 4x to 20x speedups over existing CPU and GPU solvers and solving problem sizes that exhaust the memory of baseline methods. Additionally, we show that our algorithm is robust to congestion and link-capacity degradation. Finally, using a time-expanded transit seat allocation case study, we illustrate how our approach yields interpretable allocations in realistic networks.

math.OC↗

arXiv2025

Extending Load Forecasting from Zonal Aggregates to Individual Nodes for Transmission System Operators

The reliability of local power grid infrastructure is challenged by sustainable energy developments increasing electric load uncertainty. Transmission System Operators (TSOs) need load forecasts of higher spatial resolution, extending current forecasting operations from zonal aggregates to individual nodes. However, nodal loads are less accurate to forecast and require a large number of individual forecasts, which are hard to manage for the human experts assessing risks in the control room's daily operations (operator). In collaboration with a TSO, we design a multi-level system that meets the needs of operators for hourly day-ahead load forecasting. Utilizing a uniquely extensive dataset of zonal and nodal net loads, we experimentally evaluate our system components. First, we develop an interpretable and scalable forecasting model that allows for TSOs to gradually extend zonal operations to include nodal forecasts. Second, we evaluate solutions to address the heterogeneity and volatility of nodal load, subject to a trade-off. Third, our system is manageable with a fully parallelized single-model forecasting workflow. Our results show accuracy and interpretability improvements for zonal forecasts, and substantial improvements for nodal forecasts. In practice, our multi-level forecasting system allows operators to adjust forecasts with unprecedented confidence and accuracy, and to diagnose otherwise opaque errors precisely.

cs.LG↗

arXiv2025

Optimizing Software Defined Battery Systems for Transformer Protection

Residential electric vehicle charging causes large spikes in electricity demand that risk violating neighborhood transformer power limits. Battery energy storage systems reduce these transformer limit violations, but operating them individually is not cost-optimal. Instead of individual optimization, aggregating, or sharing, these batteries leads to cost-optimal performance, but homeowners must relinquish battery control. This paper leverages virtualization to propose battery sharing optimization schemes to reduce electricity costs, extend the lifetime of a residential transformer, and maintain homeowner control over the battery. A case study with simulated home loads, solar generation, and electric vehicle charging profiles demonstrates that joint, or shared, optimization reduces consumer bills by 56% and transformer aging by 48% compared to individual optimization. Hybrid and dynamic optimization schemes that provide owners with autonomy have similar transformer aging reduction but are slightly less cost-effective. These results suggest that controlling shared batteries with virtualization is an effective way to delay transformer upgrades in the face of growing residential electric vehicle charging penetration.

eess.SY↗

arXiv2024

Towards Using Machine Learning to Generatively Simulate EV Charging in Urban Areas

This study addresses the challenge of predicting electric vehicle (EV) charging profiles in urban locations with limited data. Utilizing a neural network architecture, we aim to uncover latent charging profiles influenced by spatio-temporal factors. Our model focuses on peak power demand and daily load shapes, providing insights into charging behavior. Our results indicate significant impacts from the type of Basic Administrative Units on predicted load curves, which contributes to the understanding and optimization of EV charging infrastructure in urban settings and allows Distribution System Operators (DSO) to more efficiently plan EV charging infrastructure expansion.

cs.LG↗

arXiv2024

GPU Accelerated Security Constrained Optimal Power Flow

We propose a GPU accelerated proximal message passing algorithm for solving contingency-constrained DC optimal power flow problems (OPF). We consider a highly general formulation of OPF that uses a sparse device-node model and supports a broad range of devices and constraints, e.g., energy storage and ramping limits. Our algorithm is a variant of the alternating direction method multipliers (ADMM) that does not require solving any linear systems and only consists of sparse incidence matrix multiplies and vectorized scalar operations. We develop a pure PyTorch implementation of our algorithm that runs entirely on the GPU. The implementation is also end-to-end differentiable, i.e., all updates are automatic differentiation compatible. We demonstrate the performance of our method using test cases of varying network sizes and time horizons. Relative to a CPU-based commercial optimizer, our implementation achieves well over 100x speedups on large test cases, solving problems with over 500 million variables in under a minute on a single GPU.

math.OC↗

arXiv2024

Scalable and Interactive Electricity Grid Expansion Planning

Large scale grid expansion planning studies are essential to rapidly and efficiently decarbonizing the electricity sector. These studies help policy makers and grid participants understand which renewable generation, storage, and transmission assets should be built and where they will be most cost effective or have the highest emissions impact. However, these studies are often either too computationally expensive to run repeatedly or too coarsely modeled to give actionable decision information. In this study, we present an implicit gradient descent algorithm to solve expansion planning studies at scale, i.e., problems with many scenarios and large network models. Our algorithm is also interactive: given a base plan, planners can modify assumptions and data then quickly receive an updated plan. This allows the planner to study expansion outcomes for a wide variety of technology cost, weather, and electrification assumptions. We demonstrate the scalability of our tool, solving a case with over a hundred million variables. Then, we show that using warm starts can speed up subsequent runs by as much as 100x. We highlight how this can be used to quickly conduct storage cost uncertainty analysis.

math.OC↗

arXiv2024

Fast Grid Emissions Sensitivities using Parallel Decentralized Implicit Differentiation

Marginal emissions rates -- the sensitivity of carbon emissions to electricity demand -- are important for evaluating the impact of emissions mitigation measures. Like locational marginal prices, locational marginal emissions rates (LMEs) can vary geographically, even between nearby locations, and may be coupled across time periods because of, for example, storage and ramping constraints. This temporal coupling makes computing LMEs computationally expensive for large electricity networks with high storage and renewable penetrations. Recent work demonstrates that decentralized algorithms can mitigate this problem by decoupling timesteps during differentiation. Unfortunately, we show these potential speedups are negated by the sparse structure inherent in power systems problems. We address these limitations by introducing a parallel, reverse-mode decentralized differentiation scheme that never explicitly instantiates the solution map Jacobian. We show both theoretically and empirically that parallelization is necessary to achieve non-trivial speedups when computing grid emissions sensitivities. Numerical results on a 500 node system indicate that our method can achieve greater than 10x speedups over centralized and serial decentralized approaches.

eess.SY↗

arXiv2024

Designing model predictive control strategies for grid-interactive water heaters for load shifting applications

Model predictive control (MPC) strategies allow residential water heaters to shift load in response to dynamic price signals. Crucially, the performance of such strategies is sensitive to various algorithm design choices. In this work, we develop a framework for implementing model predictive controls on residential water heaters for load shifting applications. We use this framework to analyze how four different design factors affect control performance and thermal comfort: (i) control model fidelity, (ii) temperature sensor configuration, (iii) water draw estimation methodology, and (iv) water draw forecasting methodology. We propose new methods for estimating water draw patterns without the use of a flow meter. MPC strategies are compared under two different time-varying price signals through simulations using a high-fidelity tank model and real-world draw data. Results show that control model fidelity and the number of temperature sensors have the largest impact on electricity costs, while the water draw forecasting methodology has a significant impact on thermal comfort and the frequency of runout events. Results provide practical insight into effective MPC design for water heaters in home energy management systems.

eess.SY↗

arXiv2024

Designing forecasting software for forecast users: Empowering non-experts to create and understand their own forecasts

Forecasts inform decision-making in nearly every domain. Forecasts are often produced by experts with rare or hard to acquire skills. In practice, forecasts are often used by domain experts and managers with little forecasting expertise. Our study focuses on how to design forecasting software that empowers non-expert users. We study how users can make use of state-of-the-art forecasting methods, embed their domain knowledge, and how they build understanding and trust towards generated forecasts. To do so, we co-designed a forecasting software prototype using feedback from users and then analyzed their interactions with our prototype. Our results identified three main considerations for non-expert users: (1) a safe stepwise approach facilitating causal understanding and trust; (2) a white box model supporting human-reasoning-friendly components; (3) the inclusion of domain knowledge. This paper contributes insights into how non-expert users interact with forecasting software and by recommending ways to design more accessible forecasting software.

cs.HC↗

arXiv2024

Gradient Methods for Scalable Multi-value Electricity Network Expansion Planning

We consider multi-value expansion planning (MEP), a general bilevel optimization model in which a planner optimizes arbitrary functions of the dispatch outcome in the presence of a partially controllable, competitive electricity market. The MEP problem can be used to jointly plan various grid assets, such as transmission, generation, and battery storage capacities; examples include identifying grid investments that minimize emissions in the absence of a carbon tax, maximizing the profit of a portfolio of renewable investments and long-term energy contracts, or reducing price inequities between different grid stakeholders. The MEP problem, however, is in general nonconvex, making it difficult to solve exactly for large real-world systems. Therefore, we propose a fast stochastic implicit gradient-based heuristic method that scales well to large networks with many scenarios. We use a strong duality reformulation and the McCormick envelope to provide a lower bound on the performance of our algorithm via convex relaxation. We test the performance of our method on a large model of the U.S. Western Interconnect and demonstrate that it scales linearly with network size and number of scenarios and can be efficiently parallelized on large machines. We find that for medium-sized 16 hour cases, gradient descent on average finds a 5.3x lower objective value in 16.5x less time compared to a traditional reformulation-based approach solved with an interior point method. We conclude with a large example in which we jointly plan transmission, generation, and storage for a 768 hour case on 100 node system, showing that emissions penalization leads to additional 40.0% reduction in carbon intensity at an additional cost of $17.1/MWh.

math.OC↗

arXiv2024

Mapping the Depths: A Stocktake of Underground Power Distribution in United States

A resilient energy infrastructure is crucial for addressing increasing extreme weather and climate risks. The undergrounding of the power system is one approach to building such resiliency. In this study, we introduce Grid Underground Distribution Statistics (GUDS) for the US, the first nationwide comprehensive assessment of underground electricity distribution at a high spatial granularity. In analyzing this dataset, we find regional differences in underground distribution rates, with generally higher rates for east and west coasts and in northern states, and lower rates in the central US. We also observe relationships between underground rates and factors such as household income levels, degree of urbanization, and vulnerability to natural hazards. Notably, regions with higher electricity rates are not associated with greater proportions of underground distribution, highlighting potential equity issues in infrastructure distribution. By presenting this granular information and insights on underground distribution, our study offers valuable guidance for informing planning and decision-making by policymakers, Independent System Operators, utilities, and end-users.

physics.soc-ph↗

arXiv2024

EV-EcoSim: A grid-aware co-simulation platform for the design and optimization of electric vehicle charging infrastructure

To enable the electrification of transportation systems, it is important to understand how technologies such as grid storage, solar photovoltaic systems, and control strategies can aid the deployment of electric vehicle charging at scale. In this work, we present EV-EcoSim, a co-simulation platform that couples electric vehicle charging, battery systems, solar photovoltaic systems, grid transformers, control strategies, and power distribution systems, to perform cost quantification and analyze the impacts of electric vehicle charging on the grid. This python-based platform can run a receding horizon control scheme for real-time operation and a one-shot control scheme for planning problems, with multi-timescale dynamics for different systems to simulate realistic scenarios. We demonstrate the utility of EV-EcoSim through a case study focused on economic evaluation of battery size to reduce electricity costs while considering impacts of fast charging on the power distribution grid. We present qualitative and quantitative evaluations on the battery size in tabulated results. The tabulated results delineate the trade-offs between candidate battery sizing solutions, providing comprehensive insights for decision-making under uncertainty. Additionally, we demonstrate the implications of the battery controller model fidelity on the system costs and show that the fidelity of the battery controller can completely change decisions made when planning an electric vehicle charging site.

eess.SY↗

arXiv2024

CityPulse: Fine-Grained Assessment of Urban Change with Street View Time Series

Urban transformations have profound societal impact on both individuals and communities at large. Accurately assessing these shifts is essential for understanding their underlying causes and ensuring sustainable urban planning. Traditional measurements often encounter constraints in spatial and temporal granularity, failing to capture real-time physical changes. While street view imagery, capturing the heartbeat of urban spaces from a pedestrian point of view, can add as a high-definition, up-to-date, and on-the-ground visual proxy of urban change. We curate the largest street view time series dataset to date, and propose an end-to-end change detection model to effectively capture physical alterations in the built environment at scale. We demonstrate the effectiveness of our proposed method by benchmark comparisons with previous literature and implementing it at the city-wide level. Our approach has the potential to supplement existing dataset and serve as a fine-grained and accurate assessment of urban change.

cs.CV↗

arXiv2023

SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing

Remote sensing imagery, despite its broad applications in helping achieve Sustainable Development Goals and tackle climate change, has not yet benefited from the recent advancements of versatile, task-agnostic vision language models (VLMs). A key reason is that the large-scale, semantically diverse image-text dataset required for developing VLMs is still absent for remote sensing images. Unlike natural images, remote sensing images and their associated text descriptions cannot be efficiently collected from the public Internet at scale. In this work, we bridge this gap by using geo-coordinates to automatically connect open, unlabeled remote sensing images with rich semantics covered in OpenStreetMap, and thus construct SkyScript, a comprehensive vision-language dataset for remote sensing images, comprising 2.6 million image-text pairs covering 29K distinct semantic tags. With continual pre-training on this dataset, we obtain a VLM that surpasses baseline models with a 6.2% average accuracy gain in zero-shot scene classification across seven benchmark datasets. It also demonstrates the ability of zero-shot transfer for fine-grained object attribute classification and cross-modal retrieval. We hope this dataset can support the advancement of VLMs for various multi-modal tasks in remote sensing, such as open-vocabulary classification, retrieval, captioning, and text-to-image synthesis.

cs.CV↗