{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T04:01:33Z","timestamp":1746936093176,"version":"3.40.5"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,24]]},"DOI":"10.1109\/wcnc61545.2025.10978457","type":"proceedings-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:53:33Z","timestamp":1746813213000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Load Balancing and Energy Efficiency in Cellular Networks with a Scenario-Aware Reinforcement Learning Agent"],"prefix":"10.1109","author":[{"given":"Shorouk R.","family":"Abouamasha","sequence":"first","affiliation":[{"name":"Electronics and Communications Engineering, The American University,Cairo,Egypt"}]},{"given":"Mariam","family":"Aboelwafa","sequence":"additional","affiliation":[{"name":"Computer, Communications and Autonomous Systems Engineering, NewGiza University,Egypt"}]},{"given":"Karim G.","family":"Seddik","sequence":"additional","affiliation":[{"name":"Electronics and Communications Engineering, The American University,Cairo,Egypt"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","doi-asserted-by":"crossref","DOI":"10.3390\/s20030828","article-title":"5g support for industrial iot applications- challenges, solutions, and research gaps","volume":"20","author":"Varga","year":"2020","journal-title":"Sensors"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2740378"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC46108.2020.9045699"},{"key":"ref4","first-page":"47","article-title":"Load balancing models based on reinforcement learning for self-optimized macro- femto lte-advanced heterogeneous network","volume-title":"Journal of Telecommunication, Electronic and Computer Engineering","volume":"9","author":"Musleh","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC49033.2022.9700651"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3429284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5783985"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC46108.2020.9045149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107458"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC49032.2021.9369525"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417360"},{"volume-title":"Deep reinforcement learning with double q-learning","year":"2015","author":"Van Hasselt","key":"ref12"},{"volume-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref13"},{"volume-title":"Roma: Multi-agent reinforcement learning with emergent roles","year":"2020","author":"Wang","key":"ref14"},{"key":"ref15","first-page":"125","author":"Bakker","year":"2004","journal-title":"Hierarchical reinforcement learning with subpolicies specializing for learned subgoals"},{"volume-title":"Hierarchical reinforcement learning with the maxq value function decomposition","year":"1999","author":"Dietterich","key":"ref16"},{"key":"ref17","first-page":"136","article-title":"Evolved universal terrestrial radio access (e-utra); physical layer procedures (3gpp ts 36.213 version 14.6.0 release 14)","author":"LTE","year":"2018","journal-title":"ETSI TS"},{"issue":"212","key":"ref18","first-page":"V10","article-title":"Lte: Evolved universal terrestrial radio access (e-utra)","volume":"136","author":"TSGR","year":"2011","journal-title":"Multiplexing and channel coding (3GPP TS 36.212 version 10.3. 0 Release 10) ETSI TS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3934\/mfc.2019020"},{"key":"ref20","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"Sutton","year":"1999","journal-title":"NIPs"},{"key":"ref21","article-title":"Simulation of urban mobility (sumo)","author":"Krajzewicz","year":"2007","journal-title":"Centre for Applied Informatics (ZAIK) and the Institute of Transport Research at the German Aerospace Centre"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1201\/9781315281896-74"}],"event":{"name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","start":{"date-parts":[[2025,3,24]]},"location":"Milan, Italy","end":{"date-parts":[[2025,3,27]]}},"container-title":["2025 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10978109\/10978116\/10978457.pdf?arnumber=10978457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:05:42Z","timestamp":1746857142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10978457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/wcnc61545.2025.10978457","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]}}}