TY - JOUR
T1 - Deep Reinforcement Learning-based Optimization for End-to-end Network Slicing with Control- and User-Plane Separation
AU - Wang , Yunfeng
AU - Zhao , Liqiang
AU - Chu, Xiaoli
AU - Song, Shenghui
AU - Deng, Yansha
AU - Nallanathan, Arumugam
AU - Liang , Kai
N1 - Funding Information:
This work was supported in part by the Key-Area Research and Development Program of Guangdong Province under Grant 2020B0101120003, in part by the National Key RandD Program of China under Grants 2019YFB1804201 and 2019YFE0113200, in part by the key Research and Development Program of Shaanxi under Grant 2022KWZ-09, in part by the National Natural Science Foundation of China under Grants 61771358, 61901317, and 62071352, in part by Joint Education Project between China and Central-Eastern European Countries under Grant 202005, and in part by 111 Project under Grant B08038
Publisher Copyright:
© 1967-2012 IEEE.
PY - 2022/11/1
Y1 - 2022/11/1
N2 - Control- and user-plane separation (CUPS) and network slicing are two key technologies to support increasing network traffic and diverse wireless services. However, the benefit of CUPS in decoupling the network coverage and data service functions has not been fully utilized to facilitate network slicing. In this paper, we present a novel CUPS-based end-to-end (CUPS-E2E) network slicing scheme. First, the base stations (BS) are classified into control BSs (CBS) that provide control plane (CP) coverage and traffic BSs (TBS) that deliver user plane (UP) traffic. Next, upon CBSs and TBSs being virtualized, we define four typical end-to-end (E2E) network slices: one for CP coverage, one for high-throughput services, one for computation-intensive services, and the other for delay-sensitive services. The utilities of the four E2E network slices are defined based on their coverage, throughput, computing capability and delay requirements, respectively. Then, a deep deterministic policy gradient (DDPG)-based algorithm is employed to maximize the long-term sum-utility of the four E2E network slices by jointly optimizing the allocation of communication and computing resources to the four network slices and the activation of virtual TBSs, while meeting the service requirements of all users. Simulation results show that our proposed CUPS-E2E network slicing scheme in conjunction with a DDPG-based sum-utility maximization algorithm can support the CP wide-coverage and massive access requirements as well as the UP high-throughput, computation-intensive and delay-sensitive services simultaneously, and outperforms the existing E2E network slicing schemes in terms of the sum-utility, coverage percentage, throughput and delay.
AB - Control- and user-plane separation (CUPS) and network slicing are two key technologies to support increasing network traffic and diverse wireless services. However, the benefit of CUPS in decoupling the network coverage and data service functions has not been fully utilized to facilitate network slicing. In this paper, we present a novel CUPS-based end-to-end (CUPS-E2E) network slicing scheme. First, the base stations (BS) are classified into control BSs (CBS) that provide control plane (CP) coverage and traffic BSs (TBS) that deliver user plane (UP) traffic. Next, upon CBSs and TBSs being virtualized, we define four typical end-to-end (E2E) network slices: one for CP coverage, one for high-throughput services, one for computation-intensive services, and the other for delay-sensitive services. The utilities of the four E2E network slices are defined based on their coverage, throughput, computing capability and delay requirements, respectively. Then, a deep deterministic policy gradient (DDPG)-based algorithm is employed to maximize the long-term sum-utility of the four E2E network slices by jointly optimizing the allocation of communication and computing resources to the four network slices and the activation of virtual TBSs, while meeting the service requirements of all users. Simulation results show that our proposed CUPS-E2E network slicing scheme in conjunction with a DDPG-based sum-utility maximization algorithm can support the CP wide-coverage and massive access requirements as well as the UP high-throughput, computation-intensive and delay-sensitive services simultaneously, and outperforms the existing E2E network slicing schemes in terms of the sum-utility, coverage percentage, throughput and delay.
UR - http://www.scopus.com/inward/record.url?scp=85135216370&partnerID=8YFLogxK
U2 - 10.1109/TVT.2022.3191882
DO - 10.1109/TVT.2022.3191882
M3 - Article
SN - 0018-9545
VL - 71
SP - 12179
EP - 12194
JO - IEEE Transactions on Vehicular Technology
JF - IEEE Transactions on Vehicular Technology
IS - 11
ER -