<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">kaz44</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Университета Шакарима. Серия технические науки</journal-title><trans-title-group xml:lang="en"><trans-title>Bulletin of Shakarim University. Technical Sciences</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2788-7995</issn><issn pub-type="epub">3006-0524</issn><publisher><publisher-name>«Шәкәрім университеті» КеАҚ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.53360/2788-7995-2026-3(23)-31</article-id><article-id custom-type="elpub" pub-id-type="custom">kaz44-2870</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>АВТОМАТИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ (ОРИГИНАЛЬНАЯ СТАТЬЯ)</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>AUTOMATION AND INFORMATION TECHNOLOGY (ORIGINAL ARTICLE)</subject></subj-group></article-categories><title-group><article-title>УПРАВЛЕНИЕ МОЩНОСТЬЮ ВОСХОДЯЩЕГО КАНАЛА НА ОСНОВЕ SAC В 5G NR: ГЛУБОКОЕ ОБУЧЕНИЕ С ПОДКРЕПЛЕНИЕМ ДЛЯ СОВМЕСТНОЙ ОПТИМИЗАЦИИ ПРОПУСКНОЙ СПОСОБНОСТИ И ЭНЕРГОЭФФЕКТИВНОСТИ</article-title><trans-title-group xml:lang="en"><trans-title>SAC-BASED UPLINK POWER CONTROL IN 5G NR: DEEP REINFORCEMENT LEARNING FOR JOINT THROUGHPUT AND ENERGY EFFICIENCY OPTIMIZATION</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0009-4946-4926</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Айбагаров</surname><given-names>С.</given-names></name><name name-style="western" xml:lang="en"><surname>Aibagarov</surname><given-names>S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Серик Айбагаров – студент, младший научный сотрудник, кафедра компьютерных наук</p><p>Республика Казахстан, г. Алматы, 050040, проспект Аль-Фараби, 71</p></bio><bio xml:lang="en"><p>Serik Aibagarov – Bachelor student, Junior Reseacher, Computer Science department Almaty</p><p>71 Al-Farabi Ave., Almaty, Republic of Kazakhstan, 050040</p></bio><email xlink:type="simple">awer1307dot@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-3266-2126</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Марламбеков</surname><given-names>Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Marlambekov</surname><given-names>D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Думан Марламбеков – докторант, младший научный сотрудник, кафедра компьютерных наук</p><p>Республика Казахстан, г. Алматы, 050040, проспект Аль-Фараби, 71</p></bio><bio xml:lang="en"><p>Duman Marlambekov – PhD student, Junior Reseacher, Computer Science department</p><p>71 Al-Farabi Ave., Almaty, Republic of Kazakhstan, 050040</p></bio><email xlink:type="simple">marlambekov_duman@live.kaznu.kz</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4699-0436</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Муханбет</surname><given-names>А.</given-names></name><name name-style="western" xml:lang="en"><surname>Mukhanbet</surname><given-names>A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аксултан Муханбет – Студент докторантуры, научный сотрудник, кафедра компьютерных наук</p><p>Республика Казахстан, г. Алматы, 050040, проспект Аль-Фараби, 71</p></bio><bio xml:lang="en"><p>Aksultan Mukhanbet – PhD student, Researcher, Computer Science department</p><p>71 Al-Farabi Ave., Almaty, Republic of Kazakhstan, 050040</p></bio><email xlink:type="simple">mukhanbetaksultan0414@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Казахский национальный университет имени аль-Фараби</institution><country>Казахстан</country></aff><aff xml:lang="en"><institution>Al-Farabi Kazakh National University</institution><country>Kazakhstan</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>20</day><month>11</month><year>2026</year></pub-date><volume>0</volume><issue>3(23)</issue><fpage>331</fpage><lpage>342</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Айбагаров С., Марламбеков Д., Муханбет А., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Айбагаров С., Марламбеков Д., Муханбет А.</copyright-holder><copyright-holder xml:lang="en">Aibagarov S., Marlambekov D., Mukhanbet A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://tech.vestnik.shakarim.kz/jour/article/view/2870">https://tech.vestnik.shakarim.kz/jour/article/view/2870</self-uri><abstract><p>В статье исследуется применение Soft Actor-Critic (SAC) для управления мощностью восходящего канала в сетях 5G NR. Разработан совместимый с Gymnasium симулятор для 10 пользователей на основе модели 3GPP TR 38.901 UMa NLOS. Агент SAC совместно определяет непрерывные мощности передачи в диапазоне [0, 30] дБм. Три независимо обученные политики SAC оценивались на 100 общих сценариях и сравнивались с Full Power, Equal Power и упрощенным 3GPPinspired Fractional Power Control. При использовании стандартной сетевой метрики энергоэффективности SAC достигает 14,866 Мбит/с/Дж при средней мощности 9,905 дБм и пропускной способности 2,540 Мбит/с. Энергоэффективность статистически выше, чем у Full Power и упрощенного FPC, однако отличие от Equal Power после поправки на множественные сравнения статистически незначимо. Анализ чувствительности весов функции вознаграждения показывает, что изменение приоритетов смещает компромисс между пропускной способностью и энергоэффективностью и не выявляет единственной доминирующей конфигурации.</p></abstract><trans-abstract xml:lang="en"><p>In this paper, the application of the Soft Actor-Critic (SAC) approach to uplink power control in 5G New Radio networks is investigated. A Gymnasium-compatible simulator for a 10-user uplink cell is constructed using the 3GPP TR 38.901 Urban Macro NLOS path-loss model with stochastic shadowing and Rayleigh fading at 3.5 GHz. The SAC agent observes SINR, transmit power, and path loss for all users and jointly selects continuous transmit powers in the range [0, 30] dBm. The training reward combines throughput (0.50), an energy-efficiency term (0.25), SINR quality (0.15), and fairness (0.10). Three SAC policies are trained for 500,000 timesteps and evaluated on 100 common scenarios against Full Power, Equal Power, and a simplified 3GPP-inspired Fractional Power Control (FPC) baseline. Using the standard network-level energyefficiency metric, SAC achieves 14.866 Mbit/J at a mean transmit power of 9.905 dBm and a mean throughput of 2.540 Mbps. Network energy efficiency is significantly higher than Full Power and simplified FPC, while its difference from Equal Power is not statistically significant after multiplicity correction. A reward-weight sensitivity study confirms that changing objective priorities shifts the learned throughput-energy-efficiency operating point rather than yielding one universally dominant configuration.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>5G NR</kwd><kwd>управление мощностью восходящего канала</kwd><kwd>алгоритм «мягкий актер-критик»</kwd><kwd>энергоэффективность</kwd><kwd>SINR</kwd><kwd>индекс справедливости Джейна</kwd><kwd>модель канала 3GPP</kwd><kwd>глубокое обучение с подкреплением</kwd></kwd-group><kwd-group xml:lang="en"><kwd>5G NR</kwd><kwd>uplink power control</kwd><kwd>soft actor-critic</kwd><kwd>energy efficiency</kwd><kwd>SINR</kwd><kwd>Jain's fairness index</kwd><kwd>3GPP channel model</kwd><kwd>deep reinforcement learning</kwd></kwd-group><funding-group><funding-statement xml:lang="en">This research was funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant № BR24993211).</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Shen Z. Adaptive resource allocation in multiuser OFDM systems with proportional rate constraints / Z. Shen, J.G. Andrews, B.L. Evans // IEEE Transactions on Wireless Communications. – 2005. – Vol. 4, № 6. – P. 2726-2737. https://doi.org/10.1109/TWC.2005.858010.</mixed-citation><mixed-citation xml:lang="en">Shen Z. Adaptive resource allocation in multiuser OFDM systems with proportional rate constraints / Z. Shen, J.G. Andrews, B.L. Evans // IEEE Transactions on Wireless Communications. – 2005. – Vol. 4, № 6. – P. 2726-2737. https://doi.org/10.1109/TWC.2005.858010.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Tse D. Fundamentals of Wireless Communication / D. Tse, P. Viswanath. – Cambridge: Cambridge University Press, 2005. – 564 p. https://doi.org/10.1017/CBO9780511807213.</mixed-citation><mixed-citation xml:lang="en">Tse D. Fundamentals of Wireless Communication / D. Tse, P. Viswanath. – Cambridge: Cambridge University Press, 2005. – 564 p. https://doi.org/10.1017/CBO9780511807213.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Tombaz S. Energy- and cost-efficient ultra-high-capacity wireless access / S. Tombaz, A. Västberg, J. Zander // IEEE Wireless Communications. – 2011. – Vol. 18, № 5. – P. 18-24. https://doi.org/10.1109/MWC.2011.6056688.</mixed-citation><mixed-citation xml:lang="en">Tombaz S. Energy- and cost-efficient ultra-high-capacity wireless access / S. Tombaz, A. Västberg, J. Zander // IEEE Wireless Communications. – 2011. – Vol. 18, № 5. – P. 18-24. https://doi.org/10.1109/MWC.2011.6056688.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Zander J. Performance of optimum transmitter power control in cellular radio systems / J. Zander // IEEE Transactions on Vehicular Technology. – 1992. – Vol. 41, № 1. – P. 57-62. https://doi.org/10.1109/25.120145.</mixed-citation><mixed-citation xml:lang="en">Zander J. Performance of optimum transmitter power control in cellular radio systems / J. Zander // IEEE Transactions on Vehicular Technology. – 1992. – Vol. 41, № 1. – P. 57-62. https://doi.org/10.1109/25.120145.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">3GPP TS 38.213. NR; Physical layer procedures for control. Version 17.4.0 [Electronic resource]. – 3rd Generation Partnership Project, 2022. https://www.3gpp.org/dynareport/38213.htm.</mixed-citation><mixed-citation xml:lang="en">3GPP TS 38.213. NR; Physical layer procedures for control. Version 17.4.0 [Electronic resource]. – 3rd Generation Partnership Project, 2022. https://www.3gpp.org/dynareport/38213.htm.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Holtkamp H. Minimizing base station power consumption / H. Holtkamp, G. Auer, S. Bazzi, H. Haas // IEEE Journal on Selected Areas in Communications. – 2014. – Vol. 32, № 2. – P. 297-306. https://doi.org/10.1109/JSAC.2013.131009.</mixed-citation><mixed-citation xml:lang="en">Holtkamp H. Minimizing base station power consumption / H. Holtkamp, G. Auer, S. Bazzi, H. Haas // IEEE Journal on Selected Areas in Communications. – 2014. – Vol. 32, № 2. – P. 297-306. https://doi.org/10.1109/JSAC.2013.131009.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Applications of deep reinforcement learning in communications and networking: A survey / N.C. Luong et al // IEEE Communications Surveys &amp; Tutorials. – 2019. – Vol. 21, № 4. – P. 3133-3174. https://doi.org/10.1109/COMST.2019.2916583.</mixed-citation><mixed-citation xml:lang="en">Applications of deep reinforcement learning in communications and networking: A survey / N.C. Luong et al // IEEE Communications Surveys &amp; Tutorials. – 2019. – Vol. 21, № 4. – P. 3133-3174. https://doi.org/10.1109/COMST.2019.2916583.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Application of machine learning in wireless networks: Key techniques and open issues / Y. Sun et al // IEEE Communications Surveys &amp; Tutorials. – 2019. – Vol. 21, № 4. – P. 3072-3108. https://doi.org/10.1109/COMST.2019.2924243.</mixed-citation><mixed-citation xml:lang="en">Application of machine learning in wireless networks: Key techniques and open issues / Y. Sun et al // IEEE Communications Surveys &amp; Tutorials. – 2019. – Vol. 21, № 4. – P. 3072-3108. https://doi.org/10.1109/COMST.2019.2924243.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Haarnoja T. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor / T. Haarnoja, A. Zhou, P. Abbeel, S. Levine // Proceedings of the 35th International Conference on Machine Learning (ICML 2018). – 2018. – Vol. 80. – P. 1861-1870. https://proceedings.mlr.press/v80/haarnoja18b.html.</mixed-citation><mixed-citation xml:lang="en">Haarnoja T. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor / T. Haarnoja, A. Zhou, P. Abbeel, S. Levine // Proceedings of the 35th International Conference on Machine Learning (ICML 2018). – 2018. – Vol. 80. – P. 1861-1870. https://proceedings.mlr.press/v80/haarnoja18b.html.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Cui W. Spatial deep learning for wireless scheduling / W. Cui, K. Shen, W. Yu // IEEE Journal on Selected Areas in Communications. – 2019. – Vol. 37, № 6. – P. 1248-1261. https://doi.org/10.1109/JSAC.2019.2904352.</mixed-citation><mixed-citation xml:lang="en">Cui W. Spatial deep learning for wireless scheduling / W. Cui, K. Shen, W. Yu // IEEE Journal on Selected Areas in Communications. – 2019. – Vol. 37, № 6. – P. 1248-1261. https://doi.org/10.1109/JSAC.2019.2904352.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Deep reinforcement learning for radio resource allocation and management in next generation heterogeneous wireless networks: A survey / A. Alwarafy et al // IEEE Open Journal of the Communications Society. – 2022. – Vol. 3. – P. 1967-1986. https://doi.org/10.1109/OJCOMS.2022.3153226.</mixed-citation><mixed-citation xml:lang="en">Deep reinforcement learning for radio resource allocation and management in next generation heterogeneous wireless networks: A survey / A. Alwarafy et al // IEEE Open Journal of the Communications Society. – 2022. – Vol. 3. – P. 1967-1986. https://doi.org/10.1109/OJCOMS.2022.3153226.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">3GPP TR 38.901. Study on channel model for frequencies from 0.5 to 100 GHz. Version 17.0.0 [Electronic resource]. – 3rd Generation Partnership Project, 2022. https://www.3gpp.org/dynareport/38901.htm.</mixed-citation><mixed-citation xml:lang="en">3GPP TR 38.901. Study on channel model for frequencies from 0.5 to 100 GHz. Version 17.0.0 [Electronic resource]. – 3rd Generation Partnership Project, 2022. https://www.3gpp.org/dynareport/38901.htm.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Naparstek O. Deep multi-user reinforcement learning for distributed dynamic spectrum access / O. Naparstek, K. Cohen // IEEE Transactions on Wireless Communications. – 2019. – Vol. 18, № 1. – P. 310-323. https://doi.org/10.1109/TWC.2018.2878578.</mixed-citation><mixed-citation xml:lang="en">Naparstek O. Deep multi-user reinforcement learning for distributed dynamic spectrum access / O. Naparstek, K. Cohen // IEEE Transactions on Wireless Communications. – 2019. – Vol. 18, № 1. – P. 310-323. https://doi.org/10.1109/TWC.2018.2878578.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Ye H. Deep reinforcement learning based resource allocation for V2V communications / H. Ye, G.Y. Li, B.-H.F. Juang // IEEE Transactions on Vehicular Technology. – 2019. – Vol. 68, № 4. – P. 3163-3173. https://doi.org/10.1109/TVT.2019.2897134.</mixed-citation><mixed-citation xml:lang="en">Ye H. Deep reinforcement learning based resource allocation for V2V communications / H. Ye, G.Y. Li, B.-H.F. Juang // IEEE Transactions on Vehicular Technology. – 2019. – Vol. 68, № 4. – P. 3163-3173. https://doi.org/10.1109/TVT.2019.2897134.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Jain R. A quantitative measure of fairness and discrimination for resource allocation in shared computer systems / R. Jain, D.-M. Chiu, W.R. Hawe. – Hudson: Digital Equipment Corporation, 1984. – 38 p. – (DEC Research Report TR-301). https://arxiv.org/abs/cs/9809099.</mixed-citation><mixed-citation xml:lang="en">Jain R. A quantitative measure of fairness and discrimination for resource allocation in shared computer systems / R. Jain, D.-M. Chiu, W.R. Hawe. – Hudson: Digital Equipment Corporation, 1984. – 38 p. – (DEC Research Report TR-301). https://arxiv.org/abs/cs/9809099.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Stable-Baselines3: Reliable reinforcement learning implementations / A. Raffin et al // Journal of Machine Learning Research. – 2021. – Vol. 22, № 268. – P. 1-8. https://jmlr.org/papers/v22/20-1364.html.</mixed-citation><mixed-citation xml:lang="en">Stable-Baselines3: Reliable reinforcement learning implementations / A. Raffin et al // Journal of Machine Learning Research. – 2021. – Vol. 22, № 268. – P. 1-8. https://jmlr.org/papers/v22/20-1364.html.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Sutton R.S. Reinforcement Learning: An Introduction / R.S. Sutton, A.G. Barto. – 2nd ed. – Cambridge, MA: MIT Press, 2018. – 552 p. http://incompleteideas.net/book/the-book-2nd.html.</mixed-citation><mixed-citation xml:lang="en">Sutton R.S. Reinforcement Learning: An Introduction / R.S. Sutton, A.G. Barto. – 2nd ed. – Cambridge, MA: MIT Press, 2018. – 552 p. http://incompleteideas.net/book/the-book-2nd.html.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Human-level control through deep reinforcement learning / V. Mnih et al // Nature. – 2015. – Vol. 518, № 7540. – P. 529-533. https://doi.org/10.1038/nature14236.</mixed-citation><mixed-citation xml:lang="en">Human-level control through deep reinforcement learning / V. Mnih et al // Nature. – 2015. – Vol. 518, № 7540. – P. 529-533. https://doi.org/10.1038/nature14236.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Proximal policy optimization algorithms / J. Schulman et al // arXiv. – 2017. – arXiv:1707.06347. https://doi.org/10.48550/arXiv.1707.06347.</mixed-citation><mixed-citation xml:lang="en">Proximal policy optimization algorithms / J. Schulman et al // arXiv. – 2017. – arXiv:1707.06347. https://doi.org/10.48550/arXiv.1707.06347.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Machine learning paradigms for next-generation wireless networks / C. Jiang et al // IEEE Wireless Communications. – 2017. – Vol. 24, № 2. – P. 98-105. https://doi.org/10.1109/MWC.2016.1500356WC.</mixed-citation><mixed-citation xml:lang="en">Machine learning paradigms for next-generation wireless networks / C. Jiang et al // IEEE Wireless Communications. – 2017. – Vol. 24, № 2. – P. 98-105. https://doi.org/10.1109/MWC.2016.1500356WC.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Eskandari M. Network slicing in O-RAN-enabled cell-free massive MIMO: A DRL-based power control / M. Eskandari, M. Rahmani Ghourtani, A.G. Burr // Proceedings of the 2025 IEEE Wireless Communications and Networking Conference (WCNC). – Milan: IEEE, 2025. https://doi.org/10.1109/WCNC61545.2025.10978801.</mixed-citation><mixed-citation xml:lang="en">Eskandari M. Network slicing in O-RAN-enabled cell-free massive MIMO: A DRL-based power control / M. Eskandari, M. Rahmani Ghourtani, A.G. Burr // Proceedings of the 2025 IEEE Wireless Communications and Networking Conference (WCNC). – Milan: IEEE, 2025. https://doi.org/10.1109/WCNC61545.2025.10978801.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Anbazhagan S. Adaptive power-saving mode control in NB-IoT networks using soft actor-critic reinforcement learning for optimal power management / S. Anbazhagan, R.K. Mugelan // Scientific Reports. – 2025. – Vol. 15, Art. 34618. https://doi.org/10.1038/s41598-025-18214-4.</mixed-citation><mixed-citation xml:lang="en">Anbazhagan S. Adaptive power-saving mode control in NB-IoT networks using soft actor-critic reinforcement learning for optimal power management / S. Anbazhagan, R.K. Mugelan // Scientific Reports. – 2025. – Vol. 15, Art. 34618. https://doi.org/10.1038/s41598-025-18214-4.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Base station power control strategy in ultra-dense networks via deep reinforcement learning / Q. Chen et al // Physical Communication. – 2025. – Vol. 71, Art. 102655. https://doi.org/10.1016/j.phycom.2025.102655.</mixed-citation><mixed-citation xml:lang="en">Base station power control strategy in ultra-dense networks via deep reinforcement learning / Q. Chen et al // Physical Communication. – 2025. – Vol. 71, Art. 102655. https://doi.org/10.1016/j.phycom.2025.102655.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
