{"version":"1","article":{"id":"sparse-pmu-power-flow-estimation-ai-2026","slug":"sparse-pmu-power-flow-estimation-ai-2026","language":"en","url":"https://haberpaper.com/en/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=en","title":"AI model tests sensor placement for power-flow estimation","summary":"Researchers affiliated with Laval University evaluated a neural network that estimates power flows with fewer phasor measurement units on the IEEE 30-bus test grid. Results show that where sensors are placed can matter more than using the same number of devices.","category":"energy","region":"world","topics":["ai","electrical-materials"],"published_at":"2026-10-13T20:11:53+03:00","modified_at":"2026-10-13T20:11:53+03:00","publication_basis":"publication-record","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","sources":[{"name":"arXiv, Learning-Based Power Flow Estimation with Sparse PMU Deployment in Power Systems (arXiv:2610.13683)","url":"https://arxiv.org/abs/2610.13683","checkedAt":"2026-10-13","publishedAt":"2026-10-09"}],"translations":[{"language":"tr","url":"https://haberpaper.com/tr/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=tr"},{"language":"en","url":"https://haberpaper.com/en/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=en"},{"language":"ar","url":"https://haberpaper.com/ar/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=ar"},{"language":"fr","url":"https://haberpaper.com/fr/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=fr"},{"language":"es","url":"https://haberpaper.com/es/news/sparse-pmu-power-flow-estimation-ai-2026","api_url":"https://haberpaper.com/api/v1/articles/sparse-pmu-power-flow-estimation-ai-2026?lang=es"}],"data_types":[],"data":null,"data_compilations":[],"data_downloads":[],"content":{"paragraphs":["A preprint posted on arXiv on 9 October by researchers affiliated with Laval University and the University of Michigan-Dearborn aims to estimate branch power flows without requiring synchronized measurements at every bus in a grid. The study tested a neural-network framework using phasor measurement unit (PMU) data on the IEEE 30-bus test system across 50,000 operating scenarios. By changing which buses were monitored, the researchers compared prediction accuracy and PMU count across five deployment layouts.","The paper reports different errors among layouts with the same number of devices, 25 of 30 PMUs: the scenario that removed measurements at generator buses had an RMSE of 4.490 and R² of 0.3232, while the best layout removed five different load-bus measurements and recorded an RMSE of 1.889 and R² of 0.8802. The authors say sensor location mattered independently of device count. This was a simulation on the IEEE test system, not a field trial on a live transmission grid; the paper does not measure deployment costs or operational safety benefits in practice. The work is a preprint that has not yet undergone peer review."],"key_points":[],"sections":[]},"text":"Researchers affiliated with Laval University evaluated a neural network that estimates power flows with fewer phasor measurement units on the IEEE 30-bus test grid. Results show that where sensors are placed can matter more than using the same number of devices.\n\nA preprint posted on arXiv on 9 October by researchers affiliated with Laval University and the University of Michigan-Dearborn aims to estimate branch power flows without requiring synchronized measurements at every bus in a grid. The study tested a neural-network framework using phasor measurement unit (PMU) data on the IEEE 30-bus test system across 50,000 operating scenarios. By changing which buses were monitored, the researchers compared prediction accuracy and PMU count across five deployment layouts.\n\nThe paper reports different errors among layouts with the same number of devices, 25 of 30 PMUs: the scenario that removed measurements at generator buses had an RMSE of 4.490 and R² of 0.3232, while the best layout removed five different load-bus measurements and recorded an RMSE of 1.889 and R² of 0.8802. The authors say sensor location mattered independently of device count. This was a simulation on the IEEE test system, not a field trial on a live transmission grid; the paper does not measure deployment costs or operational safety benefits in practice. The work is a preprint that has not yet undergone peer review.","corrections":[],"editorial_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"energy","url":"https://haberpaper.com/assets/illustrations/energy-1536.webp","width":1536,"height":1024,"alt":"Symbolic energy landscape with solar panels, wind turbines and transmission lines.","language":"en"},"section_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"energy","url":"https://haberpaper.com/assets/illustrations/energy-1536.webp","width":1536,"height":1024,"alt":"Symbolic energy landscape with solar panels, wind turbines and transmission lines.","language":"en"}}}