隨著近年來科技的飛速進步，行動裝置的數量爆炸式增長，裝置也需要處理各式各樣的任務需求。由於一些較大的計算任務超出了本地裝置所能負荷的極限，故產生了運算處理功能更加強大的雲端運算(Cloud Computing)。裝置將運算密集型任務通過骨幹網路(Backbone Network)傳送給雲端伺服器進行處理，再將完成的任務回傳給裝置。雲端運算的運算功能固然非常強大，但如今隨著物聯網的普及，智慧型裝置大幅增加，大量的任務通過同一個骨幹網路傳送到距離很遠的雲端導致的骨幹網路壅塞和過長的傳輸延遲已經無法滿足如今許多任務的低延遲需求，故邊緣運算(Edge Computing)應運而生。其將使用者卸載(Offload)之任務分散到每個區域所屬的邊緣運算伺服器的做法使得運算伺服器更加靠近使用者端，大大縮減了任務的傳輸時間，更加可靠並能夠滿足用戶的低延遲需求。其中，使用者通過行動網路將任務卸載至邊緣運算伺服器並接收其運算後的結果回傳被稱為行動邊緣運算(Mobile Edge Computing) 。
本篇論文提出的Adaptive Migration在多伺服器(Multi-Server)的環境下，邊緣運算伺服器會將移動的行動使用者(Mobile User)所卸載的任務根據使用者目前換手狀態及其他伺服器之負載情況進行評估，決定是否將卸載之任務遷移至其他伺服器，從而達到平衡各伺服器之負載，接收完成更多任務的目的。在本論文所做之模擬中，本論文提出之Adaptive Migration演算法在系統內車輛分布不平衡的情況下大大降低了任務的等待時間，並在伺服器達到飽和後有效地提高了任務的接受率，從而帶給用戶更好的體驗。

With the rapid advancement of technology in recent years, the number of mobile devices has exploded, and the tasks that the devices need to handle are also various. Because some larger computing tasks exceed the limit that the local device can handle, cloud computing with more powerful computing and processing capabilities has emerged. The device transmits computing-intensive tasks to the cloud server through the backbone network for processing, and then transmits the completed tasks back to the device. With the popularization of the Internet of Things, the number of smart devices has increased significantly, although the computing function of cloud computing is very powerful, many of tasks are transmitted to the cloud far away through the same backbone network, resulting in backbone network congestion and excessively long transmission delay can’t meet the low latency requirements of many tasks today, thus, edge computing emerges as the times require. Its method of distributing the tasks offloaded by users to the edge computing servers belonging to each region makes the computing servers closer to the user equipment, greatly reducing the transmission time of tasks, make it more reliable and satisfied users' low-latency requirements. When user offloads the task to the edge computing server through the mobile network and receives the result after operation, it calls mobile edge computing. In the multi-server environment, the Adaptive Migration proposed in this paper, the edge computing Server will evaluate the task unloaded by the Mobile User according to the current position of the User and the load of other servers. Decide whether to move the uninstalled tasks to other servers to balance the load of each server and receive more tasks.

[1] M. De Donno, K. Tange and N. Dragoni, "Foundations and Evolution of Modern Computing Paradigms: Cloud, IoT, Edge, and Fog," in IEEE Access, 2019
[2] Kai Peng, Victor C. M. Leung, Xiaolong Xu, Lixin Zheng, Jiabin Wang, Qingjia Huang, "A Survey on Mobile Edge Computing: Focusing on Service Adoption and Provision", Wireless Communications and Mobile Computing, vol. 2018
[3] [Online]. Available: https://www.bianyuanyun.com/archives/808[Accessed 06 07 2022].
[4] [Online]. Available: https://medium.com/@daniel.lin7157/lte-%E7%B6%B2%E8%B7%AF%E6%9E%B6%E6%A7%8B-bd96c7e684b[Accessed 05 07 2022].
[5] [Online]. Available: https://blog.csdn.net/m0_37495408/article/details/104841243[Accessed 05 07 2022].
[6] [Online]. Available: https://note-on-clouds.blogspot.com/2020/06/lte-handover.html [Accessed 05 07 2022].
[7] P. Panigrahi, "3GLTEinfo," 3GLTEInfo, 6 12 2013. [Online]. Available: https://www.3glteinfo.com/intra-lte-handover-using-s1-interface/. [Accessed 05 07 2022].
[8] P. Panigrahi, "3GLTEinfo," 3GLTEinfo, 4 12 2013. [Online]. Available: https://www.3glteinfo.com/intra-lte-handover-using-x2-interface/. [Accessed 05 07 2022].
[9] M. V. Ngo, T. Luo, H. T. Hoang and T. Q. S. Ouek, "Coordinated Container Migration and Base Station Handover in Mobile Edge Computing," GLOBECOM 2020 - 2020 IEEE Global Communications Conference, 2020
[10] Q. Wei, P. Han and Y. Liu, "Mobility-Aware Multi-Instance VNF Placement in Mobile Edge Computing Networks," 2021 International Wireless Communications and Mobile Computing (IWCMC), 2021, pp. 1303-1308
[11] [Online]. Available: https://www.bianyuanyun.com/archives/808[Accessed 06 07 2022].
[12] M. De Donno, K. Tange and N. Dragoni, "Foundations and Evolution of Modern Computing Paradigms: Cloud, IoT, Edge, and Fog," in IEEE Access, 2019
[13] [Online]. Available: https://www.spiceworks.com/tech/edge-computing/articles/what-is-edge-computing/ [Accessed 10 02 2022].
[14] Kai Peng, Victor C. M. Leung, Xiaolong Xu, Lixin Zheng, Jiabin Wang, Qingjia Huang, "A Survey on Mobile Edge Computing: Focusing on Service Adoption and Provision", Wireless Communications and Mobile Computing, vol. 2018
[15] Y. -T. Chen and W. Liao, "Mobility-Aware Service Function Chaining in 5G Wireless Networks with Mobile Edge Computing," ICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2019
[16] N. Aljeri and A. Boukerche, "Load Balancing and QoS-Aware Network Selection Scheme in Heterogeneous Vehicular Networks," ICC 2020 - 2020 IEEE International Conference on Communications (ICC), 2020
[17] Z. Liang, Y. Liu, T. -M. Lok and K. Huang, "Service Migration for Multi-Cell Mobile Edge Computing," GLOBECOM 2020 - 2020 IEEE Global Communications Conference, 2020
[18] M. V. Ngo, T. Luo, H. T. Hoang and T. Q. S. Ouek, "Coordinated Container Migration and Base Station Handover in Mobile Edge Computing," GLOBECOM 2020 - 2020 IEEE Global Communications Conference, 2020
[19] Y. -T. Chen and W. Liao, "Mobility-Aware Service Function Chaining in 5G Wireless Networks with Mobile Edge Computing," ICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2019