Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.04640

TuneBench: Benchmarking AI Agents for Power System Dynamic Model Calibration

Andrea Pomarico·Salvatore Tessitore·Giorgio Giannuzzi·Alberto Berizzi
View original source ↗Read source document ↗Export metadata ↓

Abstract

Large Language Model (LLM)-based agents can automate complex engineering workflows by interacting with tools, interpreting feedback, and making iterative decisions. This paper introduces TuneBench, a benchmark for evaluating Agentic AI in power system dynamic model calibration, where controller parameters are adjusted to reproduce target dynamic responses. The benchmark reflects a common Transmission System Operator (TSO) practice, in which equivalent models used for Dynamic Security Assessment (DSA) are calibrated against measurements from grid-code compliance tests when proprietary models are unavailable. Two cases of increasing complexity are considered: the governor and Automatic Voltage Regulator (AVR) of a synchronous generator and the control system of a Battery Energy Storage System (BESS), both tuned against active-power and voltage step tests within a budget of 15 simulations. LLM-based agents are compared with random search and Genetic Algorithm (GA) baselines over 10 independent runs. Only the most advanced models, Opus 5.5 and GPT-6, accurately reproduce all target trajectories, with median R2 above 0.995 in every test and tracking errors up to two orders of magnitude lower than the baselines. The agent logs show that these agents autonomously extract dynamic performance indices, such as settling time and damping, and relate them to specific control parameters, decomposing the tuning problem into physically interpretable sub-problems. The benchmark is publicly available at https://github.com/Power-Agent/PowerAgentBench/tree/main/benchmarks/dynamic/level3.

Explore related subjects

eess.SYcs.SY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Andrea Pomarico, Salvatore Tessitore, Giorgio Giannuzzi, Alberto Berizzi. 2026-11-03. TuneBench: Benchmarking AI Agents for Power System Dynamic Model Calibration. https://arxiv.org/abs/2611.04640

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Reinforcement Learning based Traffic Signal Control for Queue Minimization: From Lane-based to Laneless Traffic

Efficient traffic signal control (TSC) is essential for reducing congestion and delays. Traditional TSC methods struggle to capture the dynamics of laneless, heterogeneous traffic. We propose a reinforcement learning (RL) based adaptive TSC framework whose reward depends only on approach-level queue length, motivated by the difficulty of obtaining per-vehicle measurements in laneless traffic, and evaluate it using SUMO on a conventional lane-based, homogeneous (LBHO) intersection and on a non-orthogonal laneless, heterogeneous (LLHE) intersection. On the LBHO site, the lowest mean configuration has about 23\% lower mean queue length than a Dynamic Webster baseline, and the unselected Full-State configuration about 15\% lower. On the LLHE site, all RL configurations have 66-73\% lower mean queue length than a Dynamic Webster baseline under nominal demand, and 63--74\% lower under two higher-demand scenarios evaluated without retraining. Our algorithm also outperforms actuated control and a RESCO-DQN baseline on mean queue length. We additionally release a laneless, heterogeneous-vehicle SUMO framework integrated with RL based signal control, to our knowledge the first such open implementation on a current SUMO version.

eess.SY↗
arXiv2026

A Deep State-Space Model Compression Method using Upper Bound on Output Error

We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound on the output error between two Deep SSMs and show that the bound can be expressed in terms of the $h^2$-error norms between the layerwise LQO systems. In particular, we show that reducing the $h^2$ approximation errors of the LQO systems placed in shallow layers is effective in reducing the derived upper bound on the output error. Next, we formulate an optimization problem for the derived upper bound and develop a gradient-based MOR method. In the numerical experiments, using the IMDb task from the LRA benchmark, we demonstrate the effectiveness of the proposed upper-bound-based compression method. In particular, we show that the number of trainable parameters can be reduced by approximately 60\% without retraining while maintaining the performance of the original model.

eess.SY↗
arXiv2026

Safe Navigation in Cluttered Environments Via Spline-Based Harmonic Potential Fields

We provide a motion-planning framework for target reaching and obstacle avoidance in cluttered environments. Given a polyhedral decomposition of the feasible space, the agent is guided through a prescribed sequence of cells by a suitable control policy. For each cell, we construct a potential induced by a harmonic function on the unit disk whose Dirichlet boundary condition is represented by a cardinal B-spline curve. A detailed analysis of the curve periodicity, support, and control-point selection provides an explicit analytical construction of these potentials and the associated vector fields. We further characterize inter-cell control continuity and forward invariance of non-exit facets, and introduce a smoothed control law ensuring continuous switching between independently constructed neighboring cells. Numerical results illustrate that the resulting framework safely guides the agent along the prescribed cell sequence from the initial point to the target.

eess.SY↗