{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:20:46Z","timestamp":1719361246560},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s11277-024-11255-4","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T16:02:53Z","timestamp":1718640173000},"page":"233-259","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variable Hybrid Action Space Deep Q-Networks for Optimal Power Allocation and User Association in Heterogeneous Networks"],"prefix":"10.1007","volume":"136","author":[{"given":"Aruna","family":"Valasa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjaneyulu","family":"Lokam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chayan","family":"Bhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,17]]},"reference":[{"issue":"3","key":"11255_CR1","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1109\/MNET.001.1900287","volume":"34","author":"W Saad","year":"2020","unstructured":"Saad, W., Bennis, M., & Chen, M. (2020). A vision of 6G wireless systems: applications, trends, technologies, and open research problems. IEEE Network, 34(3), 134\u2013142. https:\/\/doi.org\/10.1109\/MNET.001.1900287","journal-title":"IEEE Network"},{"issue":"7","key":"11255_CR2","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MCOM.001.1900796","volume":"58","author":"M Dryjanski","year":"2020","unstructured":"Dryjanski, M., & Kliks, A. (2020). A hierarchical and modular radio resource management architecture for 5G and beyond. IEEE Communications Magazine, 58(7), 28\u201334. https:\/\/doi.org\/10.1109\/MCOM.001.1900796","journal-title":"IEEE Communications Magazine"},{"issue":"4","key":"11255_CR3","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MWC.2017.1600343","volume":"24","author":"Q Wu","year":"2017","unstructured":"Wu, Q., Li, G. Y., Chen, W., Ng, D. W. K., & Schober, R. (2017). An overview of sustainable green 5G networks. IEEE Wireless Communications, 24(4), 72\u201380. https:\/\/doi.org\/10.1109\/MWC.2017.1600343","journal-title":"IEEE Wireless Communications"},{"issue":"1","key":"11255_CR4","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1109\/LCOMM.2015.2497697","volume":"20","author":"MR Mili","year":"2016","unstructured":"Mili, M. R., Hamdi, K. A., Marvasti, F., & Bennis, M. (2016). Joint optimization for optimal power allocation in OFDMA femtocell networks. IEEE Communications Letters, 20(1), 133\u2013136. https:\/\/doi.org\/10.1109\/LCOMM.2015.2497697","journal-title":"IEEE Communications Letters"},{"issue":"8","key":"11255_CR5","doi-asserted-by":"publisher","first-page":"3933","DOI":"10.1109\/TWC.2019.2919611","volume":"18","author":"R Amiri","year":"2019","unstructured":"Amiri, R., Almasi, M. A., Andrews, J. G., & Mehrpouyan, H. (2019). Reinforcement learning for self-organization and power control of two-tier heterogeneous networks. IEEE Transactions on Wireless Communications, 18(8), 3933\u20133947. https:\/\/doi.org\/10.1109\/TWC.2019.2919611","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"3","key":"11255_CR6","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/COMST.2018.2867268","volume":"21","author":"Y Teng","year":"2019","unstructured":"Teng, Y., Liu, M., Yu, F. R., Leung, V. C. M., Song, M., & Zhang, Y. (2019). Resource allocation for ultra-dense networks: A survey, some research issues and challenges. IEEE Communications Surveys and Tutorials, 21(3), 2134\u20132168. https:\/\/doi.org\/10.1109\/COMST.2018.2867268","journal-title":"IEEE Communications Surveys and Tutorials"},{"issue":"3","key":"11255_CR7","doi-asserted-by":"publisher","first-page":"2582","DOI":"10.1109\/TVT.2017.2768574","volume":"67","author":"T Zhou","year":"2018","unstructured":"Zhou, T., Liu, Z., Zhao, J., Li, C., & Yang, L. (2018). Joint user association and power control for load balancing in downlink heterogeneous cellular networks. IEEE Transactions on Vehicular Technology, 67(3), 2582\u20132593. https:\/\/doi.org\/10.1109\/TVT.2017.2768574","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"11255_CR8","doi-asserted-by":"publisher","unstructured":"Wen, Z., Zhu, G., Ni, M., & Lin, S. (2017). User association-based interference management in ultra-dense networks. In 2017 IEEE international symposium on antennas and propagation & USNC\/URSI national radio science meeting (pp. 1903\u20131904). IEEE. https:\/\/doi.org\/10.1109\/APUSNCURSINRSM.2017.8072994","DOI":"10.1109\/APUSNCURSINRSM.2017.8072994"},{"issue":"6","key":"11255_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s20061730","volume":"20","author":"D Deng","year":"2020","unstructured":"Deng, D., Li, X., Zhao, M., Rabie, K. M., & Kharel, R. (2020). Deep learning-based secure mimo communications with imperfect CSI for heterogeneous networks. Sensors (Switzerland), 20(6), 1\u201315. https:\/\/doi.org\/10.3390\/s20061730","journal-title":"Sensors (Switzerland)"},{"issue":"4","key":"11255_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app11041884","volume":"11","author":"S Liu","year":"2021","unstructured":"Liu, S., He, J., & Wu, J. (2021). Dynamic cooperative spectrum sensing based on deep multi-user reinforcement learning. Applied Sciences (Switzerland), 11(4), 1\u201316. https:\/\/doi.org\/10.3390\/app11041884","journal-title":"Applied Sciences (Switzerland)"},{"issue":"5","key":"11255_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app11052163","volume":"11","author":"YY Munaye","year":"2021","unstructured":"Munaye, Y. Y., Juang, R. T., Lin, H. P., Tarekegn, G. B., & Lin, D. B. (2021). Deep reinforcement learning based resource management in UAV-assisted iot networks. Applied Sciences (Switzerland), 11(5), 1\u201320. https:\/\/doi.org\/10.3390\/app11052163","journal-title":"Applied Sciences (Switzerland)"},{"issue":"10","key":"11255_CR12","doi-asserted-by":"publisher","first-page":"6255","DOI":"10.1109\/TWC.2020.3001736","volume":"19","author":"F Meng","year":"2020","unstructured":"Meng, F., Chen, P., Wu, L., & Cheng, J. (2020). Power allocation in multi-user cellular networks: Deep reinforcement learning approaches. IEEE Transactions on Wireless Communications, 19(10), 6255\u20136267. https:\/\/doi.org\/10.1109\/TWC.2020.3001736","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"12","key":"11255_CR13","doi-asserted-by":"publisher","first-page":"2710","DOI":"10.1109\/LCOMM.2017.2755021","volume":"21","author":"H Ma","year":"2017","unstructured":"Ma, H., Zhang, H., Wang, X., & Cheng, J. (2017). Backhaul-aware user association and resource allocation for massive MIMO-enabled HetNets. IEEE Communications Letters, 21(12), 2710\u20132713. https:\/\/doi.org\/10.1109\/LCOMM.2017.2755021","journal-title":"IEEE Communications Letters"},{"key":"11255_CR14","doi-asserted-by":"publisher","unstructured":"Hasan, M. K., Shahjalal, M., Islam, M. M., Alam, M. M., Ahmed, M. F., & Jang, Y. M. (2020). The role of deep learning in NOMA for 5G and beyond communications. 2020 international conference on artificial intelligence in information and communication, ICAIIC 2020 (pp. 303\u2013307). https:\/\/doi.org\/10.1109\/ICAIIC48513.2020.9065219","DOI":"10.1109\/ICAIIC48513.2020.9065219"},{"issue":"10","key":"11255_CR15","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/JSAC.2019.2933973","volume":"37","author":"YS Nasir","year":"2019","unstructured":"Nasir, Y. S., & Guo, D. (2019). Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks. IEEE Journal on Selected Areas in Communications, 37(10), 2239\u20132250. https:\/\/doi.org\/10.1109\/JSAC.2019.2933973","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"10","key":"11255_CR16","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/JSAC.2019.2933762","volume":"37","author":"C He","year":"2019","unstructured":"He, C., Hu, Y., Chen, Y., & Zeng, B. (2019). Joint power allocation and channel assignment for NOMA with deep reinforcement learning. IEEE Journal on Selected Areas in Communications, 37(10), 2200\u20132210. https:\/\/doi.org\/10.1109\/JSAC.2019.2933762","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"7","key":"11255_CR17","doi-asserted-by":"publisher","first-page":"5701","DOI":"10.1109\/TVT.2015.2452953","volume":"65","author":"Y Chen","year":"2016","unstructured":"Chen, Y., Li, J., Chen, W., Lin, Z., & Vucetic, B. (2016). Joint user association and resource allocation in the downlink of heterogeneous networks. IEEE Transactions on Vehicular Technology, 65(7), 5701\u20135706. https:\/\/doi.org\/10.1109\/TVT.2015.2452953","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"1","key":"11255_CR18","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1109\/TVT.2016.2533559","volume":"66","author":"Q Han","year":"2017","unstructured":"Han, Q., Yang, B., Miao, G., Chen, C., Wang, X., & Guan, X. (2017). Backhaul-aware user association and resource allocation for energy-constrained HetNets. IEEE Transactions on Vehicular Technology, 66(1), 580\u2013593. https:\/\/doi.org\/10.1109\/TVT.2016.2533559","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"11255_CR19","doi-asserted-by":"publisher","unstructured":"Amiri, R., Mehrpouyan, H., Fridman, L., Mallik, R. K., Nallanathan, A., & Matolak, D. (2018). A machine learning approach for power allocation in HetNets considering QoS. In IEEE international conference on communications (Vol. 2018-May, pp. 1\u20137). IEEE. https:\/\/doi.org\/10.1109\/ICC.2018.8422864","DOI":"10.1109\/ICC.2018.8422864"},{"key":"11255_CR20","unstructured":"Ahmed, K. I., & Hossain, E. (2019). A deep Q-learning method for downlink power allocation in multi-cell networks. Retrieved from http:\/\/arxiv.org\/abs\/1904.13032"},{"key":"11255_CR21","doi-asserted-by":"publisher","unstructured":"Xu, Z., Wang, Y., Tang, J., Wang, J., & Gursoy, M. C. (2017). A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs. In 2017 IEEE International Conference on Communications (ICC) (pp. 1\u20136). IEEE. https:\/\/doi.org\/10.1109\/ICC.2017.7997286","DOI":"10.1109\/ICC.2017.7997286"},{"issue":"1","key":"11255_CR22","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1109\/TWC.2017.2769644","volume":"17","author":"Y Wei","year":"2018","unstructured":"Wei, Y., Yu, F. R., Song, M., & Han, Z. (2018). User scheduling and resource allocation in HetNets with hybrid energy supply: An actor-critic reinforcement learning approach. IEEE Transactions on Wireless Communications, 17(1), 680\u2013692. https:\/\/doi.org\/10.1109\/TWC.2017.2769644","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"11255_CR23","doi-asserted-by":"publisher","unstructured":"Li, D., Zhang, H., Long, K., Huangfu, W., Dong, J., & Nallanathan, A. (2019). User association and power allocation based on Q-learning in ultra dense heterogeneous networks. In 2019 IEEE global communications conference, GLOBECOM 2019\u2014proceedings. https:\/\/doi.org\/10.1109\/GLOBECOM38437.2019.9013455","DOI":"10.1109\/GLOBECOM38437.2019.9013455"},{"key":"11255_CR24","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Kang, C., Ma, T., Teng, Y., & Guo, D. (2018). Power allocation in multi-cell networks using deep reinforcement learning. In IEEE vehicular technology conference, 2018-Augus (pp. 1\u20136). https:\/\/doi.org\/10.1109\/VTCFall.2018.8690757","DOI":"10.1109\/VTCFall.2018.8690757"},{"issue":"11","key":"11255_CR25","doi-asserted-by":"publisher","first-page":"2581","DOI":"10.1109\/TMC.2019.2928811","volume":"19","author":"L Huang","year":"2020","unstructured":"Huang, L., Bi, S., & Zhang, Y. J. A. (2020). Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks. IEEE Transactions on Mobile Computing, 19(11), 2581\u20132593. https:\/\/doi.org\/10.1109\/TMC.2019.2928811","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"1","key":"11255_CR26","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.jnca.2011.08.007","volume":"35","author":"KLA Yau","year":"2012","unstructured":"Yau, K. L. A., Komisarczuk, P., & Teal, P. D. (2012). Reinforcement learning for context awareness and intelligence in wireless networks: Review, new features and open issues. Journal of Network and Computer Applications, 35(1), 253\u2013267. https:\/\/doi.org\/10.1016\/j.jnca.2011.08.007","journal-title":"Journal of Network and Computer Applications"},{"issue":"9","key":"11255_CR27","doi-asserted-by":"publisher","first-page":"3996","DOI":"10.1109\/TCOMM.2016.2593468","volume":"64","author":"A Asheralieva","year":"2016","unstructured":"Asheralieva, A., & Miyanaga, Y. (2016). An autonomous learning-based algorithm for joint channel and power level selection by D2D pairs in heterogeneous cellular networks. IEEE Transactions on Communications, 64(9), 3996\u20134012. https:\/\/doi.org\/10.1109\/TCOMM.2016.2593468","journal-title":"IEEE Transactions on Communications"},{"key":"11255_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440","author":"E Ghadimi","year":"2017","unstructured":"Ghadimi, E., Davide Calabrese, F., Peters, G., & Soldati, P. (2017). A reinforcement learning approach to power control and rate adaptation in cellular networks. IEEE International Conference on Communications. https:\/\/doi.org\/10.1109\/ICC.2017.7997440","journal-title":"IEEE International Conference on Communications"},{"issue":"2","key":"11255_CR29","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1109\/TWC.2020.3031436","volume":"20","author":"T Zhang","year":"2021","unstructured":"Zhang, T., Zhu, K., & Wang, J. (2021). Energy-efficient mode selection and resource allocation for D2D-enabled heterogeneous networks: A deep reinforcement learning approach. IEEE Transactions on Wireless Communications, 20(2), 1175\u20131187. https:\/\/doi.org\/10.1109\/TWC.2020.3031436","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"2","key":"11255_CR30","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1109\/TVT.2019.2961405","volume":"69","author":"Z Li","year":"2020","unstructured":"Li, Z., & Guo, C. (2020). Multi-agent deep reinforcement learning based spectrum allocation for D2D underlay communications. IEEE Transactions on Vehicular Technology, 69(2), 1828\u20131840. https:\/\/doi.org\/10.1109\/TVT.2019.2961405","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"12","key":"11255_CR31","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.3390\/e24121722","volume":"24","author":"M Sun","year":"2022","unstructured":"Sun, M., Jin, Y., Wang, S., & Mei, E. (2022). Joint deep reinforcement learning and unsupervised learning for channel selection and power control in D2D networks. Entropy, 24(12), 1363\u20131378. https:\/\/doi.org\/10.3390\/e24121722","journal-title":"Entropy"},{"issue":"8","key":"11255_CR32","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.3390\/s20082361","volume":"20","author":"H Park","year":"2020","unstructured":"Park, H., & Lim, Y. (2020). Reinforcement learning for energy optimization with 5G communications in vehicular social networks. Sensors, 20(8), 2361. https:\/\/doi.org\/10.3390\/s20082361","journal-title":"Sensors"},{"issue":"7","key":"11255_CR33","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1109\/TMC.2020.3044282","volume":"21","author":"Z Xu","year":"2022","unstructured":"Xu, Z., Tang, J., Yin, C., Wang, Y., Xue, G., Wang, J., & Gursoy, M. C. (2022). ReCARL: Resource allocation in cloud RANs with deep reinforcement learning. IEEE Transactions on Mobile Computing, 21(7), 2533\u20132545. https:\/\/doi.org\/10.1109\/TMC.2020.3044282","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"11255_CR34","doi-asserted-by":"publisher","unstructured":"Lu, Y., Lu, H., Cao, L., Wu, F., & Zhu, D. (2018). Learning deterministic policy with target for power control in wireless networks. In 2018 IEEE global communications conference, GLOBECOM 2018\u2014Proceedings, (pp. 1\u20137). https:\/\/doi.org\/10.1109\/GLOCOM.2018.8648056","DOI":"10.1109\/GLOCOM.2018.8648056"},{"issue":"6","key":"11255_CR35","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1109\/LWC.2020.2970696","volume":"9","author":"A Khalili","year":"2020","unstructured":"Khalili, A., Akhlaghi, S., Tabassum, H., & Ng, D. W. K. (2020). Joint user association and resource allocation in the uplink of heterogeneous networks. IEEE Wireless Communications Letters, 9(6), 804\u2013808. https:\/\/doi.org\/10.1109\/LWC.2020.2970696","journal-title":"IEEE Wireless Communications Letters"},{"issue":"9","key":"11255_CR36","doi-asserted-by":"publisher","first-page":"9233","DOI":"10.1109\/TVT.2019.2930884","volume":"68","author":"S Jabeen","year":"2019","unstructured":"Jabeen, S., & Ho, P. H. (2019). A benchmark for joint channel allocation and user scheduling in flexible heterogeneous networks. IEEE Transactions on Vehicular Technology, 68(9), 9233\u20139244. https:\/\/doi.org\/10.1109\/TVT.2019.2930884","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"9","key":"11255_CR37","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/JSAC.2017.2720898","volume":"35","author":"H Zhang","year":"2017","unstructured":"Zhang, H., Huang, S., Jiang, C., Long, K., Leung, V. C. M., & Poor, H. V. (2017). Energy efficient user association and power allocation in millimeter-wave-based ultra dense networks with energy harvesting base stations. IEEE Journal on Selected Areas in Communications, 35(9), 1936\u20131947. https:\/\/doi.org\/10.1109\/JSAC.2017.2720898","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"6","key":"11255_CR38","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1109\/TWC.2013.040413.120676","volume":"12","author":"Q Ye","year":"2013","unstructured":"Ye, Q., Rong, B., Chen, Y., Al-Shalash, M., Caramanis, C., & Andrews, J. G. (2013). User association for load balancing in heterogeneous cellular networks. IEEE Transactions on Wireless Communications, 12(6), 2706\u20132716. https:\/\/doi.org\/10.1109\/TWC.2013.040413.120676","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"1","key":"11255_CR39","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1109\/TVT.2017.2737629","volume":"67","author":"T Kim","year":"2018","unstructured":"Kim, T., & Chang, J. M. (2018). QoS-aware energy-efficient association and resource scheduling for HetNets. IEEE Transactions on Vehicular Technology, 67(1), 650\u2013664. https:\/\/doi.org\/10.1109\/TVT.2017.2737629","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"10","key":"11255_CR40","doi-asserted-by":"publisher","first-page":"9896","DOI":"10.1109\/TVT.2018.2859740","volume":"67","author":"Q Ye","year":"2018","unstructured":"Ye, Q., Zhuang, W., Zhang, S., Jin, A. L., Shen, X., & Li, X. (2018). Dynamic radio resource slicing for a two-tier heterogeneous wireless network. IEEE Transactions on Vehicular Technology, 67(10), 9896\u20139910. https:\/\/doi.org\/10.1109\/TVT.2018.2859740","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"3","key":"11255_CR41","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1109\/TWC.2017.2654458","volume":"16","author":"X Luo","year":"2017","unstructured":"Luo, X. (2017). Delay-oriented QoS-aware user association and resource allocation in heterogeneous cellular networks. IEEE Transactions on Wireless Communications, 16(3), 1809\u20131822. https:\/\/doi.org\/10.1109\/TWC.2017.2654458","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"6","key":"11255_CR42","doi-asserted-by":"publisher","first-page":"5284","DOI":"10.1109\/TVT.2016.2615849","volume":"66","author":"A Asheralieva","year":"2017","unstructured":"Asheralieva, A., & Miyanaga, Y. (2017). Optimal contract design for joint user association and intercell interference mitigation in heterogeneous LTE-A Networks with asymmetric information. IEEE Transactions on Vehicular Technology, 66(6), 5284\u20135300. https:\/\/doi.org\/10.1109\/TVT.2016.2615849","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"11255_CR43","doi-asserted-by":"publisher","unstructured":"Liu, J., Tao, X., & Lu, J. (2019). Mobility-aware centralized reinforcement learning for dynamic resource allocation in HetNets. In 2019 IEEE Global Communications Conference, GLOBECOM 2019\u2014Proceedings (pp. 1\u20136). https:\/\/doi.org\/10.1109\/GLOBECOM38437.2019.9013191","DOI":"10.1109\/GLOBECOM38437.2019.9013191"},{"key":"11255_CR44","doi-asserted-by":"publisher","unstructured":"De Domenico, A., &Ktenas, D. (2018). Reinforcement learning for interference-aware cell DTX in heterogeneous networks. In IEEE Wireless Communications and Networking Conference, WCNC (pp. 1\u20136). https:\/\/doi.org\/10.1109\/WCNC.2018.8376993","DOI":"10.1109\/WCNC.2018.8376993"},{"issue":"8","key":"11255_CR45","doi-asserted-by":"publisher","first-page":"5565","DOI":"10.1109\/TII.2019.2933867","volume":"16","author":"H Yang","year":"2020","unstructured":"Yang, H., Alphones, A., Zhong, W. D., Chen, C., & Xie, X. (2020). Learning-Based energy-efficient resource management by heterogeneous RF\/VLC for ultra-reliable low-latency industrial IoT networks. IEEE Transactions on Industrial Informatics, 16(8), 5565\u20135576. https:\/\/doi.org\/10.1109\/TII.2019.2933867","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"9","key":"11255_CR46","doi-asserted-by":"publisher","first-page":"4135","DOI":"10.3390\/app11094135","volume":"11","author":"CK Hsieh","year":"2021","unstructured":"Hsieh, C. K., Chan, K. L., & Chien, F. T. (2021). Energy-efficient power allocation and user association in heterogeneous networks with deep reinforcement learning. Applied Sciences (Switzerland), 11(9), 4135. https:\/\/doi.org\/10.3390\/app11094135","journal-title":"Applied Sciences (Switzerland)"},{"issue":"2","key":"11255_CR47","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1109\/TSC.2022.3186099","volume":"16","author":"A Mohajer","year":"2022","unstructured":"Mohajer, A., Daliri, M. S., Mirzaei, A., Ziaeddini, A., Nabipour, M., & Bavaghar, M. (2022). Heterogeneous computational resource allocation for NOMA: Toward green mobile edge-computing systems. IEEE Transactions on Services Computing, 16(2), 1225\u20131238.","journal-title":"IEEE Transactions on Services Computing"},{"issue":"3","key":"11255_CR48","first-page":"3380","volume":"20","author":"S Dong","year":"2023","unstructured":"Dong, S., Zhan, J., Hu, W., Mohajer, A., Bavaghar, M., & Mirzaei, A. (2023). Energy-efficient hierarchical resource allocation in uplink-downlink decoupled NOMA HetNets. IEEE Transactions on Network and Service Management, 20(3), 3380\u20133395.","journal-title":"IEEE Transactions on Services Computing"},{"issue":"4","key":"11255_CR49","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1109\/JSYST.2022.3154162","volume":"16","author":"A Mohajer","year":"2022","unstructured":"Mohajer, A., Sorouri, F., Mirzaei, A., Ziaeddini, A., Rad, K. J., & Bavaghar, M. (2022). Energy-aware hierarchical resource management and backhaul traffic optimization in heterogeneous cellular networks. IEEE Systems Journal, 16(4), 5188\u20135199.","journal-title":"IEEE Systems Journal"},{"key":"11255_CR50","unstructured":"Hausknecht, M., Stone, P., & Mc, O. P. (2016, July). On-policy vs. off-policy updates for deep reinforcement learning. In Deep reinforcement learning: Frontiers and challenges, IJCAI 2016 Workshop. New York, NY, USA: AAAI Press."},{"key":"11255_CR51","unstructured":"Karandikar, R. L., & Vidyasagar, M. (2021). Convergence of batch asynchronous stochastic approximation with applications to reinforcement learning, 1, 1\u201328. Retrieved from http:\/\/arxiv.org\/abs\/2109.03445"},{"key":"11255_CR52","unstructured":"Zhang, S., & Sutton, R. S. (2017). A deeper look at experience replay. Retrieved from http:\/\/arxiv.org\/abs\/1712.01275"},{"key":"11255_CR53","unstructured":"Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2016). Prioritized experience replay. In 4th International conference on learning representations, ICLR 2016\u2014conference track proceedings (pp. 1\u201321)."}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-024-11255-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-024-11255-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-024-11255-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T17:22:19Z","timestamp":1719336139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-024-11255-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["11255"],"URL":"https:\/\/doi.org\/10.1007\/s11277-024-11255-4","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]},"assertion":[{"value":"25 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Ethical approval was not necessary for this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}