Dynamics of Network Selection in Heterogeneous Wireless Networks: An Evolutionary Game Approach

سال انتشار: 1395
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 493

فایل این مقاله در 10 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ACCSI22_067

تاریخ نمایه سازی: 13 شهریور 1396

چکیده مقاله:

Next-generation wireless networks will integratemultiple wireless access technologies to provide seamless mobilityto mobile users with high-speed wireless connectivity. This willgive rise to a heterogeneous wireless access environment wherenetwork selection becomes crucial for load balancing to avoidnetwork congestion and performance degradation. We study thedynamics of network selection in a heterogeneous wireless networkusing the theory of evolutionary games. The competition amonggroups of users in different service areas to share the limitedamount of bandwidth in the available wireless access networksis formulated as a dynamic evolutionary game, and the evolutionaryequilibrium is considered to be the solution to this game.We present two algorithms, namely, population evolution andreinforcement-learning algorithms for network selection. Althoughthe network-selection algorithm based on population evolutioncan reach the evolutionary equilibrium faster, it requiresa centralized controller to gather, process, and broadcast informationabout the users in the corresponding service area. Incontrast, with reinforcement learning, a user can gradually learn(by interacting with the service provider) and adapt the decisionon network selection to reach evolutionary equilibrium withoutany interaction with other users. Performance of the dynamic evolutionarygame-based network-selection algorithms is empiricallyinvestigated. The accuracy of the numerical results obtained fromthe game model is evaluated by using simulations.

کلیدواژه ها:

نویسندگان

Dusit Niyato

School of Computer Engineering, Nanyang Technological University, Singapore ۶۳۹۷۹۸