Papers for

industrial ai infrastructure teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Local ai agents measured for energy and time costs in power electronics

Local AI Agents in Power Electronics Simulation: Deployment, Measurements and Costs

Abstract: Agentic artificial intelligence (AI) is emerging in power electronics, where it drives the simulation loop that engineers used to close largely by hand. In this loop, a converter design, or a study of the network it connects to, is built, run, measured and revised until it satisfies its specification. Such an agent can be served from a cloud API or from an inference device on the premises. For organizations whose designs, customer data or export-controlled material cannot leave the site, and whose simulators are licensed there, local deployment is the natural choice. In such a deployment, the agent becomes an electrical load on the organization's own equipment, i.e., every run consumes power and energy on a local device, generates tokens and takes time. However, existing work focuses mainly on what the agent can achieve with cloud-hosted models. What a local deployment costs in power, energy, tokens and time on real simulation tasks, and what its choices trade against one another, has received little quantitative investigation under comparable conditions. To address this gap, a systematic evaluation framework is presented in this paper. It applies locally served models to agentic power electronics tasks, from the converter level to the system level, and measures their power, energy, token and time costs. Based on these measurements, the capability boundary of a local agent on such tasks and the cost per solved task are characterized. The results are expected to provide practical insight for the use of agentic AI in power electronics and the power systems it serves.

Wed 18 NovArtificial Intelligence
The gist
Designing power electronics often involves testing and tweaking simulations repeatedly. The authors studied how AI agents running on local devices (not cloud servers) perform these tasks, measuring their power use, energy consumption, and run time. They found that these local AI setups come with real costs in electricity and time, which is important for organizations that can't send data to the cloud. Their work gives practical numbers and limits for using AI locally in power electronics design.
Open → 2611.24880v1