arXiv subjects

Slaven Peles

Publications and source records attributed to Slaven Peles.

15 recordsLinked to original sources

arXiv2026

Integrating Agentic Artificial Intelligence with High-Performance Computing for Grid Planning

We present AgentiGrid, an agentic artificial intelligence (AI) framework that integrates large language models (LLMs) intelligence and high-performance computing (HPC) to streamline and accelerate the multi-scenario power flow studies. AgentiGrid is an autonomous decision-making agent that proposes parameter modifications, invokes analyses through HPC analysis toolkit ExaGO, interprets results, and determines subsequent actions. ExaGO provides multiple power flow applications that can perform deterministic, stochastic and security constrained optimal power flow analyses. AgentiGrid provides backends to multiple LLMs (OpenAI, Anthropic, Ollama, and Ollama cloud) augmented with context specific and task specific prompts. Key features include interactive mid-search steering, goal-type-aware post-search analysis, and concurrent variant exploration for power flow optimization. A Streamlit-based graphical launcher provides real-time visualization of iteration progress and generates reports in natural language. AgentiGrid is capable of autonomously converging transmission constrained alternating current optimal power flow in under 20 iterations, with near-perfect reliability

eess.SY↗

arXiv2026

Agentic Artificial Intelligence for Power Systems: Strategies to Identify and Close Capability Gaps

The rapid expansion of AI-driven information infrastructure, particularly data centers, is placing unprecedented pressure on power systems and accelerating the pace at which new assets must interconnect with the grid. As bulk transmission expansion rolls out slowly, new loads and generation are increasingly deployed within existing network constraints. Agentic AI is urgently needed to automate the numerous and repetitive connection processes, but its maturity has not been systematically validated on complex tasks and large-scale systems. We replicate the current state of the art in agentic AI for power systems planning and evaluate it against a structured suite of nodal planning problems spanning six levels of task complexity and four grid scales. We find that only the two lowest complexity levels are solvable on some of the test grid sizes, and identify the specific capability upgrades required to close this gap. Adopting stricter testing protocols and reproducible evaluation benchmarks is essential for assessing both genuine progress and the operational readiness of agentic AI.

eess.SY↗

arXiv2026

Hidden Economic Consequences of Adapting to Fast Ramping Datacenter Loads

Artificial intelligence workloads are driving the rapid expansion of datacenter infrastructure, which imposes substantial stress on the US energy system. While high peak electricity prices are an anticipated outcome, measurable under peak hour simulations, the high off peak prices are a significantly underestimated threat. We simulate different ramping conditions on a congestible 5000-bus system, based on a modified IEEE 118-bus grid, to show that, in the presence of fast ramping loads and slow ramping generation, datacenters can aggravate latent load pockets. This results in unexpectedly high system costs during periods outside of datacenter peak. We test the datacenter effects using two distinct load conditions. We find that in the system coincident peak, coupled simulations result in up to 100% loading of slow expensive units, with an average marginal cost increase of 8%. These findings are of extreme importance as they reveal the hidden costs of preventively ramping slow generation in anticipation of datacenter load changes.

eess.SY↗

arXiv2026

Geospatial sensitivity of transmission-constrained ACOPF to generator retirement

The US faces a growing resource adequacy challenge: new loads are being added at unprecedented scale while aging generating assets are being retired. In transmission-constrained grids, it is difficult to determine which units can be safely retired and which cannot be retired and instead require lifetime extensions until new generation can be built. Historically, this analysis was prohibitively time consuming. Transmission-constrained AC optimal power flow (ACOPF) is computationally intensive, and a thorough comparison and prioritization of generators could require hundreds or thousands of scenarios. We present an HPC-enabled framework that enables computation and geospatial mapping of the effects of generator retirement in terms of voltage magnitude and angle effects in the steady state. Specifically, our framework detects the effects of generator retirement using a simple k-nearest-neighbors model and a voltage-class-adjusted neighbor model. We demonstrate the results on over 8,000 generator retirement scenarios for a 70,000-bus transmission-constrained synthetic grid.

eess.SY↗

arXiv2026

HPC-Enabled Generator Importance Assessment for RTO-Scale Resource Adequacy Planning

Modern power systems are increasingly under stress as aging assets approach retirement and load growth outpaces new generation construction. The severity of this challenge varies by region: in the EU, the transmission grid can partially compensate for local generation shortfalls, while in the US, generation tends to be more localized, making retirements harder to offset. Retirement of generation has consequences for system reserves, fuel supply chain, and public health. We present an high-performance computing (HPC) framework for rapidly assessing the grid importance of individual generating units and ranking them by primary fuel type, operating cost, or grid impact. Historically, such studies were computationally intensive and therefore conducted infrequently. This work demonstrates that such assessments can be completed in minutes, enabling planners to evaluate a much broader range of generation portfolio scenarios than was previously possible.

eess.SY↗

arXiv2026

Porting the Nonlinear Optimization Library HiOp to Accelerator-Based Hardware Architectures

While interior point methods have been the centerpiece of nonlinear programming tools used in science and engineering, their reliance on linear solvers that can tackle sparse symmetric indefinite and highly ill-conditioned problems made it difficult to implement them effectively on hardware accelerators. At this time, there are few sparse linear solvers that can be used in this context. Here, we present a novel formulation of an interior point method implemented in our HiOp library, which is designed to be able to run entirely on hardware accelerators. This formulation avoids dependence on sparse solvers altogether, which is achieved by compressing the underlying sparse linear problem into a dense one of manageable size. We demonstrate feasibility of this approach and provide a baseline for future interior point method implementations on hardware accelerators. Our investigation is motivated by problems arising in optimal power flow analysis in power systems engineering and our approach is tailored to the broad class of problems arising in that important domain. We also demonstrate utility of modern programming models based on performance portability libraries, namely, Umpire and RAJA. We discuss trade-offs between performance, portability and development cost in the solution space for this non-linear optimization problem. As a result of this research, we demonstrate for the first time that interior point methods for sparse problems can be efficiently realized on modern computing systems where more than 90% of processing power is in GPUs.

cs.MS↗

arXiv2026

Fast Relax-and-Round Unit Commitment with Economic Horizons

The US energy system is increasingly under pressure to serve expanding data loads and to accommodate a larger number of generating units with varying technologies and own- ership structures. Therefore, developing new unit commitment methods remains a priority for reliable and affordable grid operations. We expand our novel computational method for unit commitment (UC) to include ramping constraints and long- horizon planning and provide a theoretical bound on its error. We introduce a fast novel algorithm to commit hydro-generators. We solve problems with thousands of generators at 5-minute market intervals. We show that our method can solve UC problems with over 20,000 generators in approximately 10 seconds on commodity hardware and that an increased planning horizon leads to sizable operational cost savings. We attain this runtime improvement by introducing a heuristic tailored for UC problems. Our method can be implemented using existing continuous optimization solvers and adapted for different applications. We prove a bound on the error of these solvers and show that it vanishes (in relative terms) as the problem becomes larger. We also introduce a fast and accurate hydro UC algorithm. Combined, these algorithms would allow an operator to make horizon-aware economic decisions for large systems with hydro units.

math.OC↗

arXiv2026

Fast Relax-and-Round Unit Commitment with Sub-hourly Mechanical and Ramp Constraints

We propose a novel computational method for unit commitment UC, which does not require linearized approximation and provides several orders of magnitude performance improvement over current state-of-the-art. The performance improvement is achieved by introducing a heuristic tailored for UC problems. The method can be implemented using existing continuous optimization solvers and adapted for different applications. We demonstrate value of the new method in examples of advanced UC analyses at the scale where use of current state-of-the-art tools is infeasible. We expect that the capability demonstrated in this paper will be critical to address emerging power systems challenges with more volatile large loads, such as data centers, and generation that is composed of larger number of smaller units, including significant behind-the-meter generation.

math.OC↗

arXiv2025

A Fast Relax-and-Round Approach to Unit Commitment for Data Center Own Generation

The rapid growth of data centers increasingly requires data center operators to "bring own generation" to complement the available utility power plants to supply all or part of data center load. This practice sharply increases the number of generators on the bulk power system and shifts operational focus toward fuel costs rather than traditional startup and runtime constraints. Conventional mixed-integer unit commitment formulations are not well suited for systems with thousands of flexible, fast-cycling units. We propose a unit commitment formulation that relaxes binary commitment decisions by allowing generators to be fractionally on, enabling the use of algorithms for continuous solvers. We then use a rounding approach to get a feasible unit commitment. For a 276-unit system, solution time decreases from 10 hours to less than a second, with no accuracy degradation. Our approach scales with no issues to tens of thousands of generators, which allows solving problems on the scale of the major North America interconnections. The bulk of computation is parallel and GPU compatible, enabling further acceleration in future work.

math.OC↗

arXiv2024

Interface for Sparse Linear Algebra Operations

The standardization of an interface for dense linear algebra operations in the BLAS standard has enabled interoperability between different linear algebra libraries, thereby boosting the success of scientific computing, in particular in scientific HPC. Despite numerous efforts in the past, the community has not yet agreed on a standardization for sparse linear algebra operations due to numerous reasons. One is the fact that sparse linear algebra objects allow for many different storage formats, and different hardware may favor different storage formats. This makes the definition of a FORTRAN-style all-circumventing interface extremely challenging. Another reason is that opposed to dense linear algebra functionality, in sparse linear algebra, the size of the sparse data structure for the operation result is not always known prior to the information. Furthermore, as opposed to the standardization effort for dense linear algebra, we are late in the technology readiness cycle, and many production-ready software libraries using sparse linear algebra routines have implemented and committed to their own sparse BLAS interface. At the same time, there exists a demand for standardization that would improve interoperability, and sustainability, and allow for easier integration of building blocks. In an inclusive, cross-institutional effort involving numerous academic institutions, US National Labs, and industry, we spent two years designing a hardware-portable interface for basic sparse linear algebra functionality that serves the user needs and is compatible with the different interfaces currently used by different vendors. In this paper, we present a C++ API for sparse linear algebra functionality, discuss the design choices, and detail how software developers preserve a lot of freedom in terms of how to implement functionality behind this API.

cs.MS↗

arXiv2023

Towards Efficient Alternating Current Optimal Power Flow Analysis on Graphical Processing Units

We present a solution of sparse alternating current optimal power flow (ACOPF) analysis on graphical processing unit (GPU). In particular, we discuss the performance bottlenecks and detail our efforts to accelerate the linear solver, a core component of ACOPF that dominates the computational time. ACOPF analyses of two large-scale systems, synthetic Northeast (25,000 buses) and Eastern (70,000 buses) U.S. grids [1], on GPU show promising speed-up compared to analyses on central processing unit (CPU) using a state-of-the-art solver. To our knowledge, this is the first result demonstrating a significant acceleration of sparse ACOPF on GPUs.

cs.CE↗

arXiv2022

Exascale Grid Optimization (ExaGO) toolkit: An open-source high-performance package for solving large-scale grid optimization problems

This paper introduces the Exascale Grid Optimization (ExaGO) toolkit, a library for solving large-scale alternating current optimal power flow (ACOPF) problems including stochastic effects, security constraints and multi-period constraints. ExaGO can run on parallel distributed memory platforms, including massively parallel hardware accelerators such as graphical processing units (GPUs). We present the details of the ExaGO library including its architecture, formulations, modeling details, and its performance for several optimization applications.

eess.SY↗

arXiv2021

Linear solvers for power grid optimization problems: a review of GPU-accelerated linear solvers

The linear equations that arise in interior methods for constrained optimization are sparse symmetric indefinite and become extremely ill-conditioned as the interior method converges. These linear systems present a challenge for existing solver frameworks based on sparse LU or LDL^T decompositions. We benchmark five well known direct linear solver packages using matrices extracted from power grid optimization problems. The achieved solution accuracy varies greatly among the packages. None of the tested packages delivers significant GPU acceleration for our test cases.

math.NA↗

arXiv2015

Sparse Automatic Differentiation for Complex Networks of Differential-Algebraic Equations Using Abstract Elementary Algebra

Most numerical solvers and libraries nowadays are implemented to use mathematical models created with language-specific built-in data types (e.g. real in Fortran or double in C) and their respective elementary algebra implementations. However, the built-in elementary algebra typically has limited functionality and often restricts the flexibility of mathematical models and the analysis types that can be applied to those models. To overcome this limitation, a number of domain-specific languages such as gPROMS or Modelica with more feature-rich built-in data types have been proposed. In this paper, we argue that if numerical libraries and solvers are designed to use abstract elementary algebra rather than the language-specific built-in algebra, modern mainstream languages can be as effective as any domain-specific language. We illustrate our ideas using the example of sparse Jacobian matrix computation. We implement an automatic differentiation method that takes advantage of sparse system structures and is straightforward to parallelize in a distributed memory setting. Furthermore, we show that the computational cost scales linearly with the size of the system.

cs.MS↗

arXiv2000

Analysis of a Parametrically Driven Pendulum

We study in this paper the behavior of a periodically driven nonlinear mechanical system. Bifurcation diagrams are found which locate regions of quasiperiodic, periodic and chaotic behavior within the parameter space of the system. We also conduct a symbolic analysis of the model, which demonstrates that the symbolic dynamics of two-dimensional maps can be applied effectively to the study of ordinary differential equations in order to gain global knowledge about them.

nlin.CD↗