5G網路架構包含無線電接取網路和核心網路，然而多樣的應用不僅需要通信資源，亦需要運算資源，為了滿足5G網路中不同服務的延遲需求，需要透過邊緣和雲端系統來做運算處理。由於將資源合適地分配給各類服務可以減少資源間之相互搶奪，因此可透過網路切片技術將資源隔離來達到此目的。而當有相同資料傳送到邊緣和雲端做運算時，快取可以避免重複運算來提升速度，目前已經有許多相關研究探討通信切片和運算切片，但卻很少研究探討快取切片。
本論文提出了一種在雲端和邊緣系統中快取切片的方法，稱為Cache Slicing with Minimum QoS Violation Probability (CS-MQV)，其目的是為每個切片適當地分配快取資源，使得所有服務的整體QoS違反機率最小。由於工作可在邊緣或雲端進行運算，或者可透過快取直接獲得結果來免於運算，因此需要計算每一切片的工作延遲分佈，之後再利用這些延遲分佈，使用次梯度搜尋演算法來得到最佳快取分配以達到最小化整體QoS違反機率。分析結果顯示，在系統壅塞情況下，CS-MQV演算法相較於快取無切片和快取平分切片，分別可改進59.6%和29.6%的QoS違反機率。

The 5G network architecture includes radio access network (RAN) and core network. However, diverse applications require not only communication resources but also computing resources. In order to satisfy the delay requirements of different services in 5G networks, it is also necessary to proceed computations in the edge and cloud systems. Since properly allocating resources to various services can reduce the mutual preemption of resources, it is possible to achieve this goal by isolating resources with network slicing technology. When the same data is sent to the edge or the cloud for computing, the cache can avoid repeated computation to obtain the responses more quickly. Currently, there have been many related researches on communication slicing and/or computing slicing, but few studies have explored cache slicing.
This thesis proposes an approach of cache slicing in cloud and edge systems, called Cache Slicing with Minimum QoS Violation Probability (CS-MQV), whose purpose is to properly slice each edge’s cache to different types of services for minimizing the overall QoS violation probability for these services. Since the tasks can be computed in the edge or cloud, or the results can be directly obtained in the cache to avoid computations, it is necessary to calculate the task delay distribution of each slice. Next, by utilizing these delay distributions, sub-gradient search algorithms are used to get the optimal cache allocation to minimize the overall QoS violation probability. The analytical results show that in the case of network congestion, CS-MQV can improve the QoS violation probability by 59.6% and 29.6%, compared to cache but no slicing (CNS) and cache slicing with equal partition (CS-EP), respectively.

[1] M. Vaezi and Y. Zhang, "Radio Access Network Evolution," 2017, pp. 67-86.
[2] Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, "A Survey on Mobile Edge Computing: The Communication Perspective," IEEE Communications Surveys & Tutorials, vol. 19, no. 4, pp. 2322-2358, 2017.
[3] T. Taleb, K. Samdanis, B. Mada, H. Flinck, S. Dutta, and D. Sabella, "On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration," IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1657-1681, 2017.
[4] X. Li et al., "Network Slicing for 5G: Challenges and Opportunities," IEEE Internet Computing, vol. 21, no. 5, pp. 20-27, 2017.
[5] H. Zhang, N. Liu, X. Chu, K. Long, A. Aghvami, and V. C. M. Leung, "Network Slicing Based 5G and Future Mobile Networks: Mobility, Resource Management, and Challenges," IEEE Communications Magazine, vol. 55, no. 8, pp. 138-145, 2017.
[6] L. Tang, Q. Tan, Y. Shi, C. Wang, and Q. Chen, "Adaptive Virtual Resource Allocation in 5G Network Slicing Using Constrained Markov Decision Process," IEEE Access, vol. 6, pp. 61184-61195, 2018.
[7] K. Han et al., "Application-Driven End-to-End Slicing: When Wireless Network Virtualization Orchestrates With NFV-Based Mobile Edge Computing," IEEE Access, vol. 6, pp. 26567-26577, 2018.
[8] Y. Wang, Y. Gu, and X. Tao, "Edge Network Slicing With Statistical QoS Provisioning," IEEE Wireless Communications Letters, vol. 8, no. 5, pp. 1464-1467, 2019.
[9] L. Tang, X. Zhang, H. Xiang, Y. Sun, and M. Peng, "Joint resource allocation and caching placement for network slicing in fog radio access networks," in 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2017, pp. 1-6.
[10] D. Nojima et al., "Resource Isolation in RAN Part While Utilizing Ordinary Scheduling Algorithm for Network Slicing," in 2018 IEEE 87th Vehicular Technology Conference (VTC Spring), 2018, pp. 1-5.
[11] S. O. Oladejo and O. E. Falowo, "Latency-Aware Dynamic Resource Allocation Scheme for 5G Heterogeneous Network: A Network Slicing-Multitenancy Scenario," in 2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), 2019, pp. 1-7.
[12] A. D. Domenico, Y. Liu, and W. Yu, "Optimal Computational Resource Allocation and Network Slicing Deployment in 5G Hybrid C-RAN," in ICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2019, pp. 1-6.
[13] D. Sattar and A. Matrawy, "Optimal Slice Allocation in 5G Core Networks," IEEE Networking Letters, vol. 1, no. 2, pp. 48-51, 2019.
[14] H. Chien, Y. Lin, C. Lai, and C. Wang, "End-to-End Slicing With Optimized Communication and Computing Resource Allocation in Multi-Tenant 5G Systems," IEEE Transactions on Vehicular Technology, vol. 69, no. 2, pp. 2079-2091, 2020.
[15] Y. K. Tun, M. Alsenwi, S. R. Pandey, C. W. Zaw, and C. S. Hong, "Energy Efficient Multi-Tenant Resource Slicing in Virtualized Multi-Access Edge Computing," in 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS), 2019, pp. 1-4.
[16] S. Zhang, W. Quan, J. Li, W. Shi, P. Yang, and X. Shen, "Air-Ground Integrated Vehicular Network Slicing With Content Pushing and Caching," IEEE Journal on Selected Areas in Communications, vol. 36, no. 9, pp. 2114-2127, 2018.
[17] P. L. Vo, M. N. H. Nguyen, T. A. Le, and N. H. Tran, "Slicing the Edge: Resource Allocation for RAN Network Slicing," IEEE Wireless Communications Letters, vol. 7, no. 6, pp. 970-973, 2018.
[18] Y. D. Lin, Y. C. Lai, and R. H. Hwang, "Offloading Probability Optimization with Delay Distribution in the Three-tier Cloud, Edge, and Fog Systems."