Application of Dynamic Management of 5G Network Slice Resource Based on Reinforcement Learning in Smart Grid
With the rapid development of power grid, the types of power services are becoming more and more diversified, resulting in different service demands. As one of the important technologies of 5G, network slice is used to accommodate different services on th
- PDF / 706,234 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 275 Views
Abstract. With the rapid development of power grid, the types of power services are becoming more and more diversified, resulting in different service demands. As one of the important technologies of 5G, network slice is used to accommodate different services on the same physical network. After a brief analysis of smart grid background, this paper makes a deep research on the network slice. Each service in smart grid has its own requirements of bandwidth, reliability and delay tolerance. In order to ensure the QoS of Smart Grid, a dynamic optimization scheme of network slicing resources based on reinforcement learning is proposed. This algorithm adjusts the network slice resource dynamically, we can predict the traffic by considering the change of traffic in future network slice, and then deduce the partition of network resource in the future. The reinforcement learning algorithm is then used to make the state of network resource partitioning at future moments influence the current partitioning policy to get the best current policy. Based on this algorithm, the fast response to the change of network demand can be guaranteed in the process of resource allocation, and it is verified by simulation. Keywords: Smart grid
5G Network slice Resource allocation
1 Introduction With the development of 5G network, it can not only bring better bandwidth experience, but also shoulder another important mission: enabling vertical industry [1]. The ultra-high bandwidth, ultra-low delay and ultra-large scale connection will change the operation mode and operation mode of the core business of the vertical industry, overall promote of traditional vertical industry operating efficiency and intelligent level of decision-making. As one of the key technologies of 5G, network slicing has been paid more and more attention. Based on intel virtualization technology, a 5G physical network is logically cut into virtual end to end networks. The network slices are isolated from each other, and the congestion, overload and configuration adjustment of any network slice will not affect other network slices. 5G network slicing enables the operators to build agile and flexible networks to cater to multiple use-cases in different industry verticals [2]. The explosive growth of communication demand from all kinds of grid equipment, power terminals and power users has forced the world power grid to transform from the © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021 Q. Liu et al. (Eds.): CENet 2020, AISC 1274, pp. 1485–1492, 2021. https://doi.org/10.1007/978-981-15-8462-6_169
1486
G. Zhao et al.
traditional grid to the smart grid. Due to the different needs of grid use cases, an ultrareliable and low End-to-End (E2E) delay, flexible and low-cost network is needed [3]. And the 5G network slice just has corresponding ability to match. According to the classification of 5G application scenarios, power services can be divided into three categories: mobile application services, control s
Data Loading...
