{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:52Z","timestamp":1763202892262,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Commun. Soc."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/ojcoms.2024.3429284","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T17:47:58Z","timestamp":1721152078000},"page":"4902-4919","source":"Crossref","is-referenced-by-count":4,"title":["Self-Optimized Agent for Load Balancing and Energy Efficiency: A Reinforcement Learning Framework With Hybrid Action Space"],"prefix":"10.1109","volume":"5","author":[{"given":"Bishoy","family":"Salama Attia","sequence":"first","affiliation":[{"name":"Electronics and Communications Engineering, The American University in Cairo, New Cairo, Egypt"}]},{"given":"Aamen","family":"Elgharably","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Alexandria University, Alexandria, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3830-1151","authenticated-orcid":false,"given":"Mariam","family":"Nabil Aboelwafa","sequence":"additional","affiliation":[{"name":"Computer, Communications and Autonomous Systems Department, NewGiza University, 6th of October City, Egypt"}]},{"given":"Ghada","family":"Alsuhli","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8547-5010","authenticated-orcid":false,"given":"Karim","family":"Banawan","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Alexandria University, Alexandria, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2279-592X","authenticated-orcid":false,"given":"Karim G.","family":"Seddik","sequence":"additional","affiliation":[{"name":"Electronics and Communications Engineering, The American University in Cairo, New Cairo, Egypt"}]}],"member":"263","reference":[{"volume-title":"Ericsson Mobility Report Q2 2022","year":"2022","key":"ref1"},{"key":"ref2","article-title":"Load balancing optimization in LTE\/LTE-a cellular networks: A review","author":"Mishra","year":"2014","journal-title":"arXiv:1412.7273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2550338"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2014.06.009"},{"volume-title":"Evolved Universal Terrestrial Radio Access Network (E-UTRAN); Self-Configuring and Self-Optimizing Network (SON) Use Cases and Solutions, V9.3.1","year":"2011","key":"ref5"},{"volume-title":"Defining AI native: A key enabler for advanced intelligent telecom networks","year":"2023","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37920-8_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3239220"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.101.2000014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.101.2001120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC46108.2020.9045699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2935010"},{"issue":"1","key":"ref15","first-page":"47","article-title":"Load balancing models based on reinforcement learning for self-optimized macro-femto LTE-advanced heterogeneous network","volume":"9","author":"Musleh","year":"2017","journal-title":"J. Telecommun., Electron. Comput. Eng. (JTEC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2010.5700361"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2017.07.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417360"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC49032.2021.9369525"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC49033.2022.9700651"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5783985"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2586052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC46108.2020.9045149"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-022-03087-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11339"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001736"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3194953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2981657"},{"key":"ref30","article-title":"Discrete and continuous action representation for practical RL in video games","author":"Delalleau","year":"2019","journal-title":"arXiv:1912.11077"},{"key":"ref31","first-page":"735","article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Neunert"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/323"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2021.000394"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.3024778"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2926715"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3934\/mfc.2019020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3508546.3508598"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref40","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"99","author":"Sutton"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref46","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"arXiv:1802.09477"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/PARC52418.2022.9726615"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr52523.2022.9776067"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CCE53527.2021.9633086"},{"issue":"1","key":"ref50","first-page":"16","article-title":"UAV maneuvering decision-making algorithm based on twin delayed deep deterministic policy gradient algorithm","volume":"2","author":"Bai","year":"2022","journal-title":"J. Artif. Intell. Technol."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.10.219"},{"key":"ref52","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"volume-title":"LTE; Evolved Universal Terrestrial Radio Access (E-UTRA); Physical Layer Procedures","year":"2017","key":"ref53"},{"volume-title":"LTE: Evolved Universal Terrestrial Radio Access (E-UTRA): Multiplexing Channel Coding, (Release 10), Version 10.3.0","year":"2011","key":"ref54"},{"volume-title":"5G NR, Radio Resource Control (RRC), Protocol Specification, (Release 15), Version 15.3.0","year":"2018","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2068897.2068948"},{"key":"ref57","article-title":"ns3-gym: Extending OpenAI gym for networking research","author":"Gaw\u0142owicz","year":"2018","journal-title":"arXiv:1810.03943"},{"volume-title":"Stable baselines","year":"2018","author":"Hill","key":"ref58"},{"volume-title":"Simulation of Urban Mobility (SUMO)","year":"2007","author":"Krajzewicz","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1201\/9781315281896-74"}],"container-title":["IEEE Open Journal of the Communications Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782661\/10362961\/10599522.pdf?arnumber=10599522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:01:54Z","timestamp":1725163314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10599522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/ojcoms.2024.3429284","relation":{},"ISSN":["2644-125X"],"issn-type":[{"type":"electronic","value":"2644-125X"}],"subject":[],"published":{"date-parts":[[2024]]}}}