{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:39Z","timestamp":1776887859123,"version":"3.51.2"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,6,22]],"date-time":"2018-06-22T00:00:00Z","timestamp":1529625600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002912","name":"Government of Guangdong Province","doi-asserted-by":"publisher","award":["No.2016JGXM_MS_26"],"award-info":[{"award-number":["No.2016JGXM_MS_26"]}],"id":[{"id":"10.13039\/501100002912","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10462-018-9639-x","type":"journal-article","created":{"date-parts":[[2018,6,22]],"date-time":"2018-06-22T11:45:45Z","timestamp":1529667945000},"page":"493-506","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":87,"title":["A survey of dynamic spectrum allocation based on reinforcement learning algorithms in cognitive radio networks"],"prefix":"10.1007","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-7224","authenticated-orcid":false,"given":"Yonghua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zifeng","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pin","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,22]]},"reference":[{"issue":"2","key":"9639_CR1","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/COMST.2015.2401597","volume":"17","author":"A Ahmad","year":"2015","unstructured":"Ahmad A, Ahmad S, Rehmani MH, Hassan NU (2015) A survey on radio resource allocation in cognitive radio sensor networks. IEEE Commun Surv Tutor 17(2):888\u2013917","journal-title":"IEEE Commun Surv Tutor"},{"issue":"1","key":"9639_CR2","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1109\/COMST.2014.2363082","volume":"18","author":"E Ahmed","year":"2014","unstructured":"Ahmed E, Gani A, Abolfazli S, Yao LJ, Khan SU (2014) Channel assignment algorithms in cognitive radio networks: taxonomy, open issues, and challenges. IEEE Commun Surv Tutor 18(1):795\u2013823","journal-title":"IEEE Commun Surv Tutor"},{"issue":"3","key":"9639_CR3","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10462-012-9383-6","volume":"43","author":"HA Al-Rawi","year":"2015","unstructured":"Al-Rawi HA, Ng MA, Yau KLA (2015) Application of reinforcement learning to routing in distributed wireless networks: a review. Artif Intell Rev 43(3):381\u2013416","journal-title":"Artif Intell Rev"},{"key":"9639_CR4","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/1687-1499-2011-36","volume":"1","author":"A Alsarhan","year":"2011","unstructured":"Alsarhan A, Agarwal A (2011) Profit optimization in multi-service cognitive mesh network using machine learning. EURASIP J Wirel Commun Netw 1:36","journal-title":"EURASIP J Wirel Commun Netw"},{"key":"9639_CR5","doi-asserted-by":"crossref","unstructured":"Anifantis E, Karyotis V, Papavassiliou S (2012) A markov random field framework for channel assignment in cognitive radio networks. In: 2012 IEEE international conference on pervasive computing and communications workshops (PERCOM workshops). IEEE, pp 770\u2013775","DOI":"10.1109\/PerComW.2012.6197617"},{"key":"9639_CR6","doi-asserted-by":"crossref","unstructured":"Berthold U, Fu F, Van M der\u00a0Schaar, Jondral FK (2008) Detection of spectral resources in cognitive radios using reinforcement learning. In: New frontiers in dynamic spectrum access networks, pp 1\u20135","DOI":"10.1109\/DYSPAN.2008.82"},{"issue":"3","key":"9639_CR7","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1109\/SURV.2012.100412.00017","volume":"15","author":"M Bkassiny","year":"2013","unstructured":"Bkassiny M, Li Y, Jayaweera SK (2013) A survey on machine-learning techniques in cognitive radios. IEEE Commun Surv Tutor 15(3):1136\u20131159","journal-title":"IEEE Commun Surv Tutor"},{"issue":"2","key":"9639_CR8","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu L, Babuska R, De Schutter B (2008) A comprehensive survey of multiagent reinforcement learning. IEEE Trans Syst Man Cybern Part C Appl Rev 38(2):156\u2013172","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"9639_CR9","doi-asserted-by":"crossref","unstructured":"Chen S, Huang Y, Namuduri K (2011) A factor graph based dynamic spectrum allocation approach for cognitive network. In: Wireless communications and networking conference (WCNC), 2011 IEEE. IEEE, pp 850\u2013855","DOI":"10.1109\/WCNC.2011.5779243"},{"key":"9639_CR10","doi-asserted-by":"crossref","unstructured":"Cheng X, Jiang M (2011) Cognitive radio spectrum assignment based on artificial bee colony algorithm. In: 2011 IEEE 13th international conference on communication technology (ICCT). IEEE, pp 161\u2013164","DOI":"10.1109\/ICCT.2011.6157854"},{"key":"9639_CR11","doi-asserted-by":"crossref","unstructured":"Faganello LR, Kunst R, Both CB, Granville LZ (2013) Improving reinforcement learning algorithms for dynamic spectrum allocation in cognitive sensor networks. In: Wireless communications and networking conference, pp 35\u201340","DOI":"10.1109\/WCNC.2013.6554535"},{"issue":"12","key":"9639_CR12","first-page":"2360","volume":"52","author":"Z Feng","year":"2009","unstructured":"Feng Z, Liang L, Tan L, Zhang P (2009) Q-learning based heterogenous network self-optimization for reconfigurable network with CPC assistance. Sci China (Ser F) 52(12):2360\u20132368","journal-title":"Sci China (Ser F)"},{"key":"9639_CR13","doi-asserted-by":"crossref","unstructured":"Han G, Xiao L, Poor HV (2017) Two-dimensional anti-jamming communication based on deep reinforcement learning. In: IEEE international conference on acoustics, speech and signal processing, pp 2087\u20132091","DOI":"10.1109\/ICASSP.2017.7952524"},{"key":"9639_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-68832-9","volume-title":"Cognitive wireless communication networks","author":"E Hossain","year":"2007","unstructured":"Hossain E, Bhargava V (2007) Cognitive wireless communication networks. Springer, New York"},{"issue":"4","key":"9639_CR15","first-page":"13","volume":"6","author":"JM Iii","year":"2000","unstructured":"Iii JM (2000) Cognitive radio: an integrated agent architecture for software defined radio, Ph.D. dissertation. ResearchGate 6(4):13\u201318","journal-title":"ResearchGate"},{"key":"9639_CR16","unstructured":"Le HST, Ly HD (2008) Opportunistic spectrum access using fuzzy logic for cognitive radio networks. In: Second international conference on communications and electronics, ICCE 2008. IEEE, pp 240\u2013245"},{"issue":"9","key":"9639_CR17","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1109\/TWC.2012.062012.111342","volume":"11","author":"M Levorato","year":"2012","unstructured":"Levorato M, Firouzabadi S, Goldsmith A (2012) A learning framework for cognitive interference networks with partial and noisy observations. IEEE Trans Wirel Commun 11(9):3101\u20133111","journal-title":"IEEE Trans Wirel Commun"},{"key":"9639_CR18","doi-asserted-by":"crossref","unstructured":"Li H, Zhu G, Liang Z, Chen Y (2010) A survey on distributed opportunity spectrum access in cognitive network. In: International conference on wireless communications networking and mobile computing, pp 1\u20134","DOI":"10.1109\/WICOM.2010.5601252"},{"key":"9639_CR19","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1186\/1687-1499-2011-181","volume":"1","author":"Y Li","year":"2011","unstructured":"Li Y, Feng Z, Chen S, Chen Y, Xu D, Zhang P, Zhang Q (2011) Radio resource management for public femtocell networks. EURASIP J Wirel Commun Netw 1:181","journal-title":"EURASIP J Wirel Commun Netw"},{"key":"9639_CR20","first-page":"860","volume":"2","author":"N Lilith","year":"2005","unstructured":"Lilith N, Dogancay K (2005) Distributed reduced-state sarsa algorithm for dynamic channel allocation in cellular networks featuring traffic mobility. IEEE Int Conf Commun 2:860\u2013865","journal-title":"IEEE Int Conf Commun"},{"key":"9639_CR21","doi-asserted-by":"crossref","unstructured":"Lv C, Wang J, Yu F, Dai H (2013) A Q-learning-based dynamic spectrum allocation algorithm. ICCSEE-13","DOI":"10.2991\/iccsee.2013.195"},{"issue":"2","key":"9639_CR22","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s11276-011-0392-1","volume":"18","author":"J Marinho","year":"2012","unstructured":"Marinho J, Monteiro E (2012) Cognitive radio: survey on communication protocols, spectrum decision issues, and future research directions. Wirel Netw 18(2):147\u2013164","journal-title":"Wirel Netw"},{"issue":"4","key":"9639_CR23","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1109\/98.788210","volume":"6","author":"J Mitola","year":"1999","unstructured":"Mitola J, Maguire GQ (1999) Cognitive radio: making software radios more personal. IEEE Pers Commun 6(4):13\u201318","journal-title":"IEEE Pers Commun"},{"key":"9639_CR24","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. Comput Sci"},{"issue":"5","key":"9639_CR25","first-page":"1676","volume":"48","author":"J Nie","year":"1997","unstructured":"Nie J, Haykin S (1997) A Q-learning-based dynamic channel assignment technique for mobile communication systems. IEEE Trans Veh Technol 48(5):1676\u20131687","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"9639_CR26","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s10462-015-9438-6","volume":"45","author":"J Qadir","year":"2016","unstructured":"Qadir J (2016) Artificial intelligence based cognitive routing for cognitive radio networks. Artif Intell Rev 45(1):25\u201396","journal-title":"Artif Intell Rev"},{"key":"9639_CR27","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.procs.2017.03.076","volume":"107","author":"M Ru","year":"2017","unstructured":"Ru M, Yin S, Qu Z (2017) Power and spectrum allocation in d2d networks based on coloring and chaos genetic algorithm. Procedia Comput Sci 107:183\u2013189","journal-title":"Procedia Comput Sci"},{"issue":"11\u201312","key":"9639_CR28","doi-asserted-by":"publisher","first-page":"2108","DOI":"10.1016\/j.mcm.2010.06.044","volume":"53","author":"HAB Salameh","year":"2011","unstructured":"Salameh HAB (2011) Throughput-oriented channel assignment for opportunistic spectrum access networks. Math Comput Modell 53(11\u201312):2108\u20132118","journal-title":"Math Comput Modell"},{"issue":"11","key":"9639_CR29","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TMC.2010.120","volume":"9","author":"T Shu","year":"2010","unstructured":"Shu T, Krunz M (2010) Exploiting microscopic spectrum opportunities in cognitive radio networks via coordinated channel access. IEEE Trans Mob Comput 9(11):1522\u20131534","journal-title":"IEEE Trans Mob Comput"},{"key":"9639_CR30","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction, vol 1. MIT Press, Cambridge"},{"key":"9639_CR31","doi-asserted-by":"crossref","unstructured":"Tanwongvarl C, Chantaraskul S (2015) Performance comparison of learning techniques for intelligent channel assignment in cognitive wireless sensor networks. In: Seventh international conference on ubiquitous and future networks, pp 503\u2013507","DOI":"10.1109\/ICUFN.2015.7182595"},{"key":"9639_CR32","doi-asserted-by":"crossref","unstructured":"Teng Y, Zhang Y, Niu F, Dai C (2010) Reinforcement learning based auction algorithm for dynamic spectrum access in cognitive radio networks. In: Vehicular technology conference fall, pp 1\u20135","DOI":"10.1109\/VETECF.2010.5594301"},{"issue":"2","key":"9639_CR33","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s11277-012-0611-9","volume":"69","author":"Y Teng","year":"2013","unstructured":"Teng Y, Yu FR, Han K, Wei Y, Zhang Y (2013) Reinforcement-learning-based double auction design for dynamic spectrum access in cognitive radio networks. Wirel Pers Commun 69(2):771\u2013791","journal-title":"Wirel Pers Commun"},{"issue":"3","key":"9639_CR34","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1109\/SURV.2012.121112.00047","volume":"15","author":"EZ Tragos","year":"2013","unstructured":"Tragos EZ, Zeadally S, Fragkiadakis AG, Siris VA (2013) Spectrum assignment in cognitive radio networks: a comprehensive survey. IEEE Commun Surv Tutor 15(3):1108\u20131135","journal-title":"IEEE Commun Surv Tutor"},{"issue":"3","key":"9639_CR35","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1109\/COMST.2016.2539923","volume":"18","author":"W Wang","year":"2016","unstructured":"Wang W, Kwasinski A, Niyato D, Han Z (2016) A survey on applications of model-free strategy learning in cognitive wireless networks. IEEE Commun Surv Tutor 18(3):1717\u20131757","journal-title":"IEEE Commun Surv Tutor"},{"key":"9639_CR36","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TVT.2017.2782726","volume":"67","author":"L Xiao","year":"2017","unstructured":"Xiao L, Li Y, Dai C, Dai H, Poor HV (2017) Reinforcement learning-based NOMA power allocation in the presence of smart jamming. IEEE Trans Veh Technol 67:3377\u20133389","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"9639_CR37","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s11277-010-0007-7","volume":"57","author":"M Yang","year":"2011","unstructured":"Yang M, Grace D (2011) Cognitive radio with reinforcement learning applied to multicast downlink transmission with power adjustment. Wirel Pers Commun 57(1):73\u201387","journal-title":"Wirel Pers Commun"},{"key":"9639_CR38","unstructured":"Yang R, Ye F, et\u00a0al (2010) Non-cooperative spectrum allocation based on game theory in cognitive radio networks. In: 2010 IEEE fifth international conference on bio-inspired computing: theories and applications (BIC-TA). IEEE, pp 1134\u20131137"},{"issue":"1","key":"9639_CR39","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.jnca.2011.08.007","volume":"35","author":"KLA Yau","year":"2012","unstructured":"Yau KLA, Komisarczuk P, Teal PD (2012) Reinforcement learning for context awareness and intelligence in wireless networks: review, new features and open issues. J Netw Comput Appl 35(1):253\u2013267","journal-title":"J Netw Comput Appl"},{"issue":"4","key":"9639_CR40","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/S1005-8885(11)60286-0","volume":"19","author":"L Yi","year":"2012","unstructured":"Yi L, Hong J (2012) Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas. J China Univer Posts Telecommun 19(4):80\u201385","journal-title":"J China Univer Posts Telecommun"},{"key":"9639_CR41","doi-asserted-by":"crossref","unstructured":"Yu L, Liu C, Liu Z, Hu W (2010) Heuristic spectrum assignment algorithm in distributed cognitive networks. In: 2010 6th International conference on wireless communications networking and mobile computing (WiCOM). IEEE, pp 1\u20135","DOI":"10.1109\/WICOM.2010.5600806"},{"issue":"3","key":"9639_CR42","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1109\/SURV.2012.110112.00125","volume":"15","author":"Y Zhang","year":"2013","unstructured":"Zhang Y, Lee C, Niyato D, Wang P (2013) Auction approaches for resource allocation in wireless systems: a survey. IEEE Commun Surv Tutor 15(3):1020\u20131041","journal-title":"IEEE Commun Surv Tutor"},{"key":"9639_CR43","doi-asserted-by":"crossref","unstructured":"Zhao C, Zou M, Shen B, Kim B, Kwak K (2008) Cooperative spectrum allocation in centralized cognitive networks using bipartite matching. In: Global telecommunications conference, IEEE GLOBECOM 2008. IEEE, pp 1\u20136","DOI":"10.1109\/GLOCOM.2008.ECP.575"},{"issue":"3","key":"9639_CR44","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1109\/MSP.2007.361604","volume":"24","author":"Q Zhao","year":"2007","unstructured":"Zhao Q, Sadler BM (2007) A survey of dynamic spectrum access. IEEE Signal Process Mag 24(3):79\u201389","journal-title":"IEEE Signal Process Mag"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-018-9639-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-018-9639-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-018-9639-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T01:38:12Z","timestamp":1569289092000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-018-9639-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,22]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9639"],"URL":"https:\/\/doi.org\/10.1007\/s10462-018-9639-x","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,22]]},"assertion":[{"value":"22 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}