{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T14:05:53Z","timestamp":1789049153982,"version":"build-2803163510"},"reference-count":31,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Active voltage control in distribution networks depends on a sensing\u2013decision\u2013actuation chain that must remain effective as feeder topology, inverter participation, and telemetry quality change. Most multi-agent reinforcement learning controllers retain feeder-specific observation and action interfaces, and their behavior under imperfect telemetry is rarely tested under whole-graph transfer. This paper proposes GRAS-AVC, which is a zero-shot graph actor\u2013critic framework with a permutation-equivariant shared actor, variable-size twin graph critics, droop-residual actions, and deployment-time AC power-flow risk screening. The 322-bus target feeder contributes no replay, gradient updates, risk fitting, or checkpoint selection. On an independent third-year ten-day test, GRAS-AVC reduces violating bus\u2013time pairs from 7.455% under droop control to 2.723% (63.5% relative reduction). Against a matched edge-conditioned Graph-TD3 backbone, the GRAS actor lowers pooled exposure from 9.239% to 4.027%; after identical screening, GRAS-AVC lowers it from 3.896% to 2.723% while triggering 15.89 percentage points less often. Across information-matched tests spanning reconstructed missing telemetry, graph-correlated errors, gross bad data, a one-step delay, compound stress, and 50 paired announced reconfigurations, the frozen system maintains 63.1\u201363.6% droop-relative reductions and improves bus\u2013time exposure in every seed. A selector-model audit records no false acceptance across 40 exact-and-bounded-mismatch condition\u2013seed evaluations. GRAS-AVC therefore couples topology-aware policy inference with auditable physical screening for scalable sensing-to-control operation in DER-rich distribution networks.<\/jats:p>","DOI":"10.3390\/s26185752","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T13:04:57Z","timestamp":1789045497000},"page":"5752","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Telemetry-Robust Safe Zero-Shot Graph Multi-Agent Reinforcement Learning for Active Voltage Control Across Distribution Feeders"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2869-6322","authenticated-orcid":false,"given":"Boyin","family":"Jin","sequence":"first","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"given":"Siqi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8734-8920","authenticated-orcid":false,"given":"Shang","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9621-4158","authenticated-orcid":false,"given":"Hualong","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1109\/JPROC.2011.2116750","article-title":"Options for Control of Reactive Power by Distributed Photovoltaic Generators","volume":"99","author":"Turitsyn","year":"2011","journal-title":"Proc. IEEE"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Farivar, M., Clarke, C.R., Low, S.H., and Chandy, K.M. (2011, January 17\u201320). Inverter VAR Control for Distribution Systems with Renewables. Proceedings of the 2011 IEEE International Conference on Smart Grid Communications, Brussels, Belgium.","DOI":"10.1109\/SmartGridComm.2011.6102366"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/TSG.2013.2248175","article-title":"Distributed Optimal Power Flow for Smart Microgrids","volume":"4","author":"Zhu","year":"2013","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1109\/JPHOTOV.2014.2364125","article-title":"Optimal Dispatch of Residential Photovoltaic Inverters Under Forecasting Uncertainties","volume":"5","author":"Dhople","year":"2015","journal-title":"IEEE J. Photovolt."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4120","DOI":"10.1109\/TPWRS.2020.3000652","article-title":"A Multi-Agent Deep Reinforcement Learning Based Voltage Regulation Using Coordinated PV Inverters","volume":"35","author":"Cao","year":"2020","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4137","DOI":"10.1109\/TSG.2021.3072251","article-title":"Data-Driven Multi-Agent Deep Reinforcement Learning for Distribution System Decentralized Voltage Control with High Penetration of PVs","volume":"12","author":"Cao","year":"2021","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_7","unstructured":"Wang, J., Xu, W., Gu, Y., Song, W., and Green, T.C. (2021, January 6\u201314). Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks. Proceedings of the Advances in Neural Information Processing Systems, Virtual."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2980","DOI":"10.1109\/TSG.2021.3060027","article-title":"Online Multi-Agent Reinforcement Learning for Decentralized Inverter-Based Volt-VAR Control","volume":"12","author":"Liu","year":"2021","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xu, F., Liu, S., Qing, Y., Zhou, Y., Wang, Y., and Song, M. (2024, January 25\u201329). Temporal Prototype-Aware Learning for Active Voltage Control on Power Distribution Networks. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain.","DOI":"10.1145\/3637528.3671790"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"119530","DOI":"10.1016\/j.apenergy.2022.119530","article-title":"A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems","volume":"323","author":"Lee","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"121743","DOI":"10.1016\/j.apenergy.2023.121743","article-title":"Physical-assisted multi-agent graph reinforcement learning enabled fast voltage regulation for PV-rich active distribution network","volume":"351","author":"Chen","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3875","DOI":"10.1109\/TPWRS.2016.2632156","article-title":"A Review on Distribution System State Estimation","volume":"32","author":"Primadianto","year":"2017","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Carere, F., Bragatto, T., Geri, A., Sangiovanni, S., and Laracca, M. (2026). Uncertainty Effects on Smart Grid Services for Low-Voltage Distribution Networks. Sensors, 26.","DOI":"10.3390\/s26061800"},{"key":"ref_14","first-page":"1437","article-title":"A Comprehensive Survey on Safe Reinforcement Learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref_15","unstructured":"Achiam, J., Held, D., Tamar, A., and Abbeel, P. (2017, January 6\u201311). Constrained Policy Optimization. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"108609","DOI":"10.1016\/j.epsr.2022.108609","article-title":"Decentralized Safe Reinforcement Learning for Inverter-Based Voltage Control","volume":"211","author":"Cui","year":"2022","journal-title":"Electr. Power Syst. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2656","DOI":"10.1109\/TSG.2022.3228636","article-title":"Physics-Shielded Multi-Agent Deep Reinforcement Learning for Safe Active Voltage Control With Photovoltaic\/Battery Energy Storage Systems","volume":"14","author":"Chen","year":"2023","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1109\/TAC.2013.2270317","article-title":"A Distributed Control Strategy for Reactive Power Compensation in Smart Microgrids","volume":"58","author":"Bolognani","year":"2013","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2903","DOI":"10.1109\/TSG.2021.3052998","article-title":"Two-Stage Volt\/VAR Control in Active Distribution Networks With Multi-Agent Deep Reinforcement Learning Method","volume":"12","author":"Sun","year":"2021","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4873","DOI":"10.1109\/TSG.2022.3185975","article-title":"Multi-Agent Deep Reinforcement Learning for Voltage Control with Coordinated Active and Reactive Power Optimization","volume":"13","author":"Hu","year":"2022","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, M., Feng, M., Zhou, W., and Li, H. (2022, January 14\u201318). Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3539480"},{"key":"ref_22","unstructured":"Qu, Y., Ma, J., and Wu, F. (2024, January 3\u20139). Safety Constrained Multi-Agent Reinforcement Learning for Active Voltage Control. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, Jeju-si, Republic of Korea."},{"key":"ref_23","unstructured":"Xu, H., Zheng, J., and Qu, G. (2023). A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/TSG.2023.3277087","article-title":"Multi-Agent Safe Graph Reinforcement Learning for PV Inverters-Based Real-Time Decentralized Volt\/Var Control in Zoned Distribution Networks","volume":"15","author":"Yan","year":"2024","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100835","DOI":"10.1016\/j.egyai.2026.100835","article-title":"Graph neural network-based multi-agent reinforcement learning for active voltage control: Performance and topology robustness","volume":"25","author":"Eze","year":"2026","journal-title":"Energy AI"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2768","DOI":"10.1109\/TSTE.2025.3566469","article-title":"Autonomous Voltage Regulation for Smart Distribution Network with High-Proportion PVs: A Graph Meta-Reinforcement Learning Approach","volume":"16","author":"Ge","year":"2025","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1109\/59.336098","article-title":"State Estimation for Real-Time Monitoring of Distribution Systems","volume":"9","author":"Baran","year":"1994","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.1109\/TFUZZ.2026.3696383","article-title":"Fuzzy Event-Driven Optimal Quantized Control for USVs under Thruster and Positioning Constraints: An Adaptive Dynamic Programming Method","volume":"34","author":"Ning","year":"2026","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4604","DOI":"10.1109\/TPWRS.2018.2790390","article-title":"A Robust State Estimation Framework Considering Measurement Correlations and Imperfect Synchronization","volume":"33","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Shi, Y., Feng, M., Wang, M., Zhou, W., and Li, H. (June, January 29). Multi-Agent Reinforcement Learning with Safety Layer for Active Voltage Control. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, London, UK.","DOI":"10.65109\/QNVL3268"},{"key":"ref_31","unstructured":"Fujimoto, S., van Hoof, H., and Meger, D. (2018, January 10\u201315). Addressing Function Approximation Error in Actor-Critic Methods. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5752\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T13:05:58Z","timestamp":1789045558000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":31,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185752"],"URL":"https:\/\/doi.org\/10.3390\/s26185752","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]}}}