摘要
下一代无线网络将是能融合多种无线接入技术来支持用户的无缝移动性，并为移动用户提供高速无线连接的异构无线网络。在异构无线网络中，通过对各无线网络进行联合无线资源管理能够降低网络资源分配的不均衡性并能提高无线资源利用率。因此，研究在异构无线网络环境下用户如何选择合适的网络进行接入，对于提高用户感知、避免网络拥塞和达到网络间的负载均衡具有重要的意义。
随着无线通信技术的发展，由于系统的异构性和对多业务的支持，使得系统负载的不确定和动态特性非常突出。这便使得具有不需建立准确的系统数学模型、能够简化对不确定和动态变化系统的控制等优势的模糊逻辑及神经网络等人工智能技术在异构无线网络资源管理方面具有非常广阔的应用发展空间。
本文针对异构无线网络现有的基于模糊逻辑及神经网络的接入选择方法未能合理考虑网络负载状况的问题，提出了一种基于径向基函数模糊神经网络的接入选择方法（RBF-FNN）。该方法考虑了网络的已占用资源数及用户的信号强度，并结合预判决预处理过程降低了算法开销。模糊神经网络的参数强化学习调整过程以可接入网络的接入阻塞率相等为目标，使该算法对网络负载程度具有很好的动态适应性，并实现了智能化的接入判决。算法仿真结果表明，该方法能有效均衡异构无线网络间的负载，保障业务的QoS，并且相对于负载均衡算法（MLB算法）降低了网络的接入阻塞率。
为了降低算法复杂度，本文提出了一种基于PSO（粒子群优化）模糊神经元的接入选择方法。该方法设计了一个模糊神经元并将其作为接入判决控制器的主体，并结合具有全局寻优能力的PSO算法对模糊神经元的参数初值进行设定，以提高参数学习调整速度及算法精度。由于PSO模糊神经元结构简单，在接入选择过程中减少了一定的计算量，算法复杂度得以降低。仿真结果表明PSO模糊神经元算法与RBF-FNN算法性能相仿，接入阻塞率、丢包率及平均负载均衡程度等指标相近，两种算法性能指标均优于MLB算法。PSO模糊神经元算法在有效降低计算复杂度的同时仍保证了算法的性能及实用性。
本文的研究工作和成果为基于负载均衡的异构无线网络接入选择算法的研究提供了参考。
The next-generation wireless communication systems will be the heterogeneouswireless networks which integrate a variety of radio access technologies to support theusers' seamless mobility and provide high-speed wireless connectivity for mobile users. Inheterogeneous wireless networks, the joint radio resource management of wirelessnetworks can reduce the unbalancing of network resource allocation and improve theutilization of radio resource. Therefore, it is of great significance to research on selectingthe appropriate access networks for users to improve users’ satisfaction, avoid networkcongestion and balance the load between networks.
With the development of wireless communication technology, the heterogeneity ofsystems and support for multi-service make the uncertain and dynamic characteristics ofthe system load very prominent. The artificial intelligence technologies, such as fuzzy logicand neural network, have no need to establish accurate system model and can simplify thecontrol of uncertain and dynamic systems. So the artificial intelligence technologies have avery broad space for application and development in the radio resource management ofheterogeneous wireless networks.
Aiming at working out the problem that fuzzy logic and neural network based accessselection algorithm didn’t consider the load state reasonably in heterogeneous wirelessnetworks, a RBF (Radial Basis Function) fuzzy neural network based access selectionalgorithm (RBF-FNN) is proposed. The algorithm takes the amount of the networkresources and users’ signal strength into consideration and adopts pre-decision andpretreatment process to reduce the algorithm overhead. The algorithm executes factorsreinforcement learning for the fuzzy neural network with the objective of the equalblocking probability of accessible networks to adapt for load state dynamically andachieved the intelligent access judgment. The simulation results show that the algorithmcan balance the load of heterogeneous wireless networks effectively and guarantee thequality of service, as well as decrease the blocking probability compared to the maximumload balance based algorithm (MLB algorithm).
In order to reduce the algorithm complexity, a PSO (Particle SwarmOptimization)-fuzzy neuron based access selection algorithm is proposed. The algorithmtakes a fuzzy neuron as the main part of the access judgment controller, and combines withPSO algorithm with global optimization capability to set initial parameters value, so as to improve the precision of parameter learning. Simulations show that the performance ofPSO fuzzy neuron algorithm is similar to that of RBF-FNN algorithm, among which theaccess blocking probability, packet outage probability and the level of load balance areclose. The performances of proposed two algorithms are better than MLB algorithm. PSOfuzzy neuron algorithm can reduce algorithm complexity while ensure the performance andpracticality.
The research work and results of this paper could provide references for the researchon load balancing based access selection algorithms in heterogeneous wireless networks.
引文
[1]周文安,付秀花,王志辉等译.无线通信原理与应用[M].电子工业出版社,2009.
[2]贺听,李斌.异构无线网络切换技术[M].北京邮电大学出版社,2008.
[3]庄浩.异构无线网络中接纳控制机制的研究[D].北京邮电大学硕士学位论文,2010.
[4]王亚楠.异构无线网络中网络选择与联合呼叫接纳控制的研究[D].北京邮电大学硕士学位论文,2010.
[5] Safwat Ahmed M., Mouftah Hussein.4G Network Technologies for MobileTelecommunications[J]. IEEE network,2005,19(5):3-4.
[6] Jamalipour Abbas, Valaee Shahrokh. Toward Seamless Internetworking of WirelessLAN and Cellular Networks[J]. IEEE Wireless Communications,2005,12(3):6-7.
[7] Wu Gang, Havinga Paul J.M., Mizuno Mitsuhiko. Wireless Internet overHeterogeneous Wireless Networks[C]. IEEE Global Telecommunications Conference,2001:1759-1765.
[8]李军.异构无线网络融合理论与技术实现[M].电子工业出版社,2005.
[9]李斌.基于IP流分流的异构无线网络负载均衡方法研究[D].吉林大学硕士学位论文,2011.
[10]孙卓.异构无线网络中的接入选择机制研究[D].北京邮电大学博士学位论文,2007.
[11]Berggren F., Bria A., Badia L., Karla I., Litjens R., Magnusson P., Meago F., Tang H.,Veronesi R.. Multi-radio Resource Management for Ambient Networks[C]. IEEEPIMRC,2005:942-946.
[12]赵嵩.基于多因素动态判决的异构无线网络接入选择方法研究[D].吉林大学硕士学位论文,2011.
[13]Ormond O., Perry P., Murphy J.. Network Selection Decision in WirelessHeterogeneous Networks[C]. IEEE16th International Symposium on Personal, Indoorand Mobile Radio Communications,2005:2680-2684.
[14]Chingyao Huang, Hung-Hui Juan, Meng-Shiang Lin, Chung-Ju Chang. RadioResource Management of Heterogeneous Services in Mobile WiMax Systems[J]. IEEEWireless communications,2007,14(1):20-26.
[15]伍仁勇.支持QoS的无线移动网络呼叫接入控制和智能资源分配研究[D].华中科技大学博士学位论文,2006.
[16]Yuhong Li, Xiaoli Guo, Yisan Li, Xiuli Zheng. A Utility-Based Network SelectionMechanism in Heterogeneous Wireless Networks[C]. International Conference onWireless Networks and Information Systems,2009:201-204.
[17]Ho Chan, Pingyi Fan, Zhigang Cao. A Utility-based Network Selection Sheme forMultiple Services in Heterogeneous Networks[C]. International Conference onWireless Networks, Communications and Mobile Computing,2005:1175-1180.
[18]黄开枝,贺晓珺,张鹏,罗兴国.异构无线网络中基于信任度的接入选择算法[J].计算机工程,2011,37(4):4-9.
[19]唐伦.陈前斌,苏晨.一种基于竞标机制的异构无线网络选择模型[J].中国科技论文在线,2008,3(1):16-21.
[20]Niyato D., Hossain E.. Dynamics of Network Selection in Heterogeneous WirelessNetworks: An Evolutionary Game Approach[J]. IEEE Transactions on VehicularTechnology,2009,58(4):2008-2017.
[21]Zhao Song, Shi Wenxiao, Fan Shaoshuai, Wang Nan. A GRA-based Network SelectionMechanism in Heterogeneous Wireless Networks[C]. International Conference onComputer, Mechatronics, Control and Electronic Engineering,2010:215-218.
[22]石文孝,赵嵩,范绍帅,孙超.基于多目标决策的异构无线网络接入选择算法[J].吉林大学学报(工学版),2011,41(3):795-799.
[23]李军,房雅丁,宋梅,宋俊德.异构网络中一种基于灰度关联的动态接入选择策略[J].北京邮电大学学报,2006:174-177.
[24]孙琳俊.异构无线网络选择算法的仿真研究[J].计算机仿真,2011,28(8):107-111.
[25]Song Q., Jamalipour A.. Network Selection in an Integrated Wireless LAN and UMTSEnvironment Using Mathematical Modeling and Computing Techniques[J]. IEEEWireless Communications,2005,2(3):42-48.
[26]Marti A. B., Guerrero J. A.. A Network Selection Mechanism for Next GenerationMobile Communications[C].3rd IET International Conference on IntelligentEnvironments,2007:22-29.
[27]张鹏,黄开枝,贺晓珺,卫红权.基于组合权重的异构无线网络选择算法[J].系统工程与电子技术,2009,31(10):2501-2505.
[28]Lusheng Wang, Binet D.. MADM-based Network Selection in Heterogeneous WirelessNetworks: A Simulation Study[C]. Wireless Communication, Vehicular Technology,Information Theory and Aerospace and Electronic Systems Technology,2009:559-564.
[29]Li Yishan, Li Yuhong, Li Tao. A Game-Theoretic Resource Allocation AlgorithmBased on Utility in IEEE802.11e[C]. Fifth International Conference on InnovativeMobile and Internet Services in Ubiquitous Computing,2011:283-288.
[30]徐晓峰,郑连清.马尔科夫模型在异构无线网络选择中的应用[J].计算机仿真,2011,28(11):134-137.
[31]Rodriguez J., Monteiro V., Bastos J., Gameiro A., Cabral O., Velez F.. ServiceSuitability Based RAT Selection for Beyond3G Systems[C]. IEEE VehicularTechnology Conference,2008:1-5.
[32]李明欣,陈山枝,谢东亮,胡博,时岩.异构无线网络中基于非合作博弈论的资源分配和接入控制[J].软件学报,2010,21(8):2037-2049.
[33]Hyukmin Son, Sanghoon Lee, Soo-Chang Kim, Yeon-Seung Shin. Soft LoadBalancing over Heterogeneous Wireless Networks[J]. IEEE Transactions on VehicularTechnology,2008,57(4):2632-2638.
[34]石文孝,李斌,刘妍,郭磊. IP流分流的异构无线网络负载均衡[J].应用科学学报,2010,28(6):567-572.
[35]Li Bin, Shi Wenxiao, Zhao Ying. A Load Balancing Algorithm Based on Dividing IPFlow for High-speed Traffic over Heterogeneous Wireless Networks[C]. The3rdInternational Congressing Image and Signal Processing,2010:4294-4298.
[36]Hyukmin Son, Sanghoon Lee, Soo-Chang Kim, Yeon-Seung Shin. Soft LoadBalancing Over Heterogeneous Wireless Networks[J]. IEEE Transactions on VehicularTechnology,2008,57(4):2632-2638.
[37]Louha Kuheli, Jun Jung Hyun, Agrawal, Dharma P.. Exploring Load Balancing inHeterogeneous Networks by Rate Distribution[C]. IEEE International Performance,Computing and Communications Conference,2008,7(9):427-432.
[38]E.Z. Tragos, G. Tsiropoulos, G. T. Karetsos, S. A. Kyriazakos. Admission control forQoS support in heterogeneous4G wireless networks[J]. IEEE Network Journal,2008,22(3):30-37.
[39]张楠.异构网络新型接入选择算法研究[D].北京邮电大学硕士学位论文,2010.
[40]孙卓,刘铁军,张倩倩,王文博.异构无线分组网络中的接入选择机制[J].系统仿真学报,2008,20(10):2762-2765.
[41]胡南.无线通信网络接入控制技术研究[D].北京邮电大学博士学位论文,2008.
[42]Mukhopadhyay A. K., Chatterjee S., Saha S., Ghose S, Saha D.. An Efficient CallAdmission Control Scheme on Overlay Networks using Fuzzy Logic[C]. AdvancedNetworks and Telecommunication Systems,2009:1-3.
[43]吕瑶.异构无线网络中负载平衡算法的研究与仿真[D].东北大学硕士学位论文,2009.
[44]徐菲菲.异构无线网络中的智能型呼叫准入控制算法研究与仿真[D].东北大学硕士学位论文,2009.
[45]梁立涛,纪阳,张平.基于模糊层次分析法的异构系统网络选择算法[J].北京邮电大学学报,2007,30(2):71-75.
[46]胡图,景志宏,张秋林.基于可拓模糊层次分析的异构网络选择算法[J].计算机应用,2011.31(9):2326-2329.
[47]张永靖,冯志勇,张平.基于Q学习的自主联合无线资源管理算法[J].电子与信息学报,2008,30(3):676-680.
[48]Giupponil L., Agusti R., Perez R. J., Sallent R O.. A Novel Approach for Joint RadioResource Management based on Fuzzy Neural Methodology[J]. IEEE Transactions onVehicular Technology,2008,57(3):1789-1805.
[49]Giupponil L., Agusti R., Perez R. J., Sallent R O.. Fuzzy Neural Control forEconomic-driven Radio Resource Management in Beyond3G Networks[J]. IEEETransactions on Systems,2009,39(2):170-189.
[50]Giupponil L., Agusti R., Perez R. J., Sallent R O.. A Novel Joint Radio ResourceManagement Approach with Reinforcement Learning Mechanisms[C].24th IEEEInternational IEEE Transactions on Systems Performance, Computing, andCommunications Conference,2005:621-626.
[51]夏玮玮,沈连丰.一种基于模糊神经网络的异构网络选择算法[J].东南大学学报(自然科学版),2010,40(4):663-669.
[52]Kuen R. L., Chung J. C., Shung C. B.. A Neural Fuzzy Resource Manager forHierarchical Cellular Systems Supporting Multimedia Services[J]. IEEE Transactionson Vehicular Technology,2003,52(5):1196-1206.
[53]札德著,陈国权译.模糊集合、语言变量及模糊逻辑[M].科学出版社,1982.
[54]汤兵勇,路林吉,王文杰.模糊控制理论与应用记述[M].清华大学出版社,2002.
[55]阎平凡,张长水.人工神经网络与模拟进化计算[M].清华大学出版社,2005.
[56]粟翠兰.基于模糊神经网络融入令牌的ATM网络拥塞控制研究[D].辽宁工程技术大学硕士论文,2001.
[57]Zadeh L. A.. Outline of A New Approach to the Analysis of Complex System andDecision Processes[C]. IEEE Transactions on Systems, Man and Cybernetics,1973,3(l):28-44.
[58]张晓琴.基于模糊神经网络盲均衡算法的研究[D].太原理工大学博士学位论文,2008.
[59]李彬.径向基函数神经网络的学习算法研究[D].山东大学硕士论文,2005.
[60]Kartalopoulos S. V.. Understanding Neural Networks and Fuzzy Logic[M].Wiley-IEEE Press,1996.
[61]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].清华大学出版社,2005.
[62]夏传军.基于遗传算法优化的模糊神经网络垂直切换算法[D].吉林大学硕士学位论文,2011.
[63]罗秋敏.基于模糊神经网络的模糊规则获取方法[D].大连交通大学硕士学位论文,2004.
[64]Nan Wang, Wenxiao Shi, Shaoshuai Fan, Yan Liu. Flow Diversion-based VerticalHandoff Algorithm for Heterogeneous Wireless Networks[J]. Journal of ComputationalInformation Systems,2011,7(13):4863-4870.
[65]Wang Nan, Shi Wenxiao, Fan Shaoshuai, Liu Shuxiang. PSO-FNN-based VerticalHandoff Decision Algorithm in Heterogeneous Wireless Networks[C].20112ndInternational Conference on Challenges in Environmental Science and ComputerEngineering,2011:11-14.
[66]Wang nan, Shi Wenxiao, Fan Shaoshuai. Flow Diversion-based Load BalancingAlgorithm for Vertical Handoff Decision in Heterogeneous Wireless Networks[C].International Conference on Computer, Electrical, and Systems Sciences, andEngineering,2011:460-463.
[67]杜京义.神经网络[M].西安电子科技大学出版社,2007.
[68]石文孝,范绍帅,王柟,夏传军.基于模糊神经网络的异构无线网络接入选择算法[J].通信学报,2010,31(9):151-156.
[69]黄志辉.人工神经网络优化算法研究[D].东南大学硕士学位论文.2009.
[70]石文孝,范绍帅,王柟,赵嵩.基于PSO模糊神经元的异构无线网络接入选择[J].北京邮电大学学报,2011,34(2):58-62.
[71]李刚,范瑜,李国国,刘志明.永磁直线电机运输系统中的模糊增益神经控制[J].北京交通大学学报,2008,32(5):81-88.
[72]汪浩;田作华.用于队列管理的模糊增益神经元自适应控制器[J].北京邮电大学学报,2010,33(2):99-104.
[73]于万霞.基于流量预测的城市单交叉路口多相位交通信号的控制技术[D].河北工业大学博士学位论文,2008.
[74]张晓清.粒子群算法及其在模式识别领域中的应用[D].西安电子科技大学硕士论文,2006.
[75]李海娜.基于PSO-BP神经网络的铝带坯晶粒度软测量建模及优化[D].中南大学硕士学位论文,2009.
[76]王俊国.基于神经网络的建模方法与控制策略研究[D].华中科技大学博士学位论文,2004.