?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Intelligent+Energy+Management+using+Multi-Agent+Dynamic+Learning+for+Scheduling+Commercial+Electric+Vehicle+Charging+Stations&rft.creator=Chan%2C+Kevin&rft.creator=Asef%2C+Pedram&rft.creator=Benoit%2C+Alexandre&rft.description=For+commercial+electric+vehicles+(CEVs)%2C+an+underexplored+challenge+is+the+complexity+of+demand+and+supply+management%2C+which+is+vital+for+the+efficient+operation+and+broader+adoption+of+CEVs.+By+leveraging+advanced+smart+grid+technologies+and+intelligent+energy+management+systems%2C+the+research+endeavors+to+create+a+cost-effective+software+solution+for+optimizing+the+charging+process.+This+study+deploys+proximal+policy+optimization+(PPO)+multi-agent+deep+reinforcement+learning+(MARL)+within+an+actor-critic+network+architecture.+Agents+are+responsible+for+managing+the+supply+and+demand+of+energy+from+two+grids+welcoming+ten+charging+stations+each+pumping+energy+from+the+integrated+uninterruptible+power+supply+(UPS).+Performance+metrics+are+compared+against+a+dynamic+programming+(DP)+approach%2C+serving+as+a+benchmark.+The+DP+model+excels+when+prior+information+is+readily+available.+In+contrast%2C+PPO+agents+exhibit+remarkable+robustness+and+adaptability+in+environments+lacking+such+information+obtaining+95%25+accuracy.+These+insights+not+only+enrich+the+existing+academic+discourse+but+also+establish+new+performance+benchmarks+for+practical+implementations.&rft.subject=Electric+vehicles%2C+Enegry+Management&rft.publisher=Institute+of+Electrical+and+Electronics+Engineers+(IEEE)&rft.date=2024-11-01&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+of+the+59th+International+Universities+Power+Engineering+Conference.++(pp.+pp.+1-6).++Institute+of+Electrical+and+Electronics+Engineers+(IEEE)+(2024)++++(In+press).++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10196832%2F1%2FV2_IEEE_Conference_Smart_Grid_and_MARL_revision_pa.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10196832%2F&rft.rights=open