- 期刊
Using the Reinforcement Learning Scheme to the Priority-Based Routing and Call Admission Control in WDM Networks
並列摘要
In order to use Wavelength Division Multiplexing (WDM) networks efficiently, a lightpath is dynamically established upon the arrival of a connection request. Generally, dynamic routing is usually determined by conventional shortest path algorithm. Different link weight assignment results in different routing and network performance. Using reinforcement learning (RL), this paper deals with the problem of call admission control (CAC) and routing in differentiating the services of WDM networks to obtain maximized system revenue. The problem is formulated as a finite-state discrete-time dynamic programming problem that is too complex to be solved exactly. Here we adopt the RL method together with a decomposition approach, to solve this problem and demonstrate that it is able to earn significantly higher revenue than the alternatives.
延伸閱讀
- Goto, K., & Shibata, K. (2010). Emergence of Prediction by Reinforcement Learning Using a Recurrent Neural Network. Journal of Robotics, 2010(), 133-141. https://doi.org/10.1155/2010/437654
- CHT, H. C. (2004). A DSR-based Routing Algorithm for UWB Ad-Hoc Networks [master's thesis, Yuan Ze University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0009-0112200611294604
- 曾博彥（2020）。Recommendation System Based on Reinforcement Learning in User Preference〔碩士論文，淡江大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0002-2909202009564200
- 林玟均（2019）。D2D Resource Allocation Based on Reinforcement Learning with Power Control〔碩士論文，國立宜蘭大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0046-2608201912422700
- Mousavi, A., Araabi, B. N., & Ahmadabadi, M. N. (2014). Context Transfer in Reinforcement Learning Using Action-Value Functions. Computational Intelligence and Neuroscience, (2014), 265-274. https://doi.org/10.1155/2014/428567