隨著智能移動設備和5G 網絡的廣泛使用，互聯網上創造了多種服
務。互聯網上提供的許多服務，例如物聯網、虛擬現實和在線遊戲，都具
有低延遲和高吞吐量的要求。為了實現這一要求，邊緣計算的鄰近性能夠
減少延遲，並提高用戶的體驗質量。長距離網絡會導致更多的數據包擁塞
和數據包丟失。這會影響用戶的體驗質量和滿意度。為了提高用戶體驗
質量，需要一個具有不同類型接入技術（包括有線和無線）的多接入邊
緣計算（MEC）網絡。在本文中，我們對新創建的NTUST 多接入邊緣
計算(MEC) 網絡進行了一些測試。我們想通過使用不同的接入技術以及
我們的移動邊緣計算網絡處理大量用戶和巨大流量的能力來找出多接入
網絡的性能。完成了網絡性能測試、流測試和負載測試。性能測試結果
顯示，5G 加MEC 下行吞吐量746.92Mbps，平均時延16.47ms，而5G
不加MEC 下行吞吐量402.50Mbps，平均時延21.34ms。流媒體測試向
我們展示了帶有MEC 的5G 的平均延遲為28.30 毫秒，而沒有MEC 的
5G 處理流媒體服務的平均延遲為44.80 毫秒。性能和流媒體測試都顯示
了MEC 技術在網絡中的重要性。負載測試表明，當用戶數在10 個以上
時，5G 與MEC 相比WiFi
6 具有更好的性能，這表明5G 與MEC 相比
具有更好的處理大量用戶的能力而不是WiFi
6（802.11 斧頭）

With the widespread use of smart mobile devices and 5G network,
many kinds of service on the internet is created. Many services that is
served on the internet, such as Internet of Things, virtual reality, and online
gaming has a low latency and high throughput requirements. To achieve
this requirements, the proximity of edge computing have the ability to reduce
latency, and improve user’s quality of experience. A long distance
network will result in more packet congestion and packet loss. This will affect
the user’s quality of experience and satisfaction. To improve the quality
of user’s experience, a Multiaccess
Edge Computing(MEC) network
with different kinds of access technologies, including wired and wireless,
is needed. In this paper we do some testing on the newly created NTUST
MEC network. A network performance testing, streaming testing, and load
testing were done. The result of the performance test shows that 5G with
MEC has a downlink throughput of 746.92 Mbps and average latency of
16.47 ms, while 5G without MEC has a downlink throughput of 402.50
Mbps and average latency of 21.34 ms. The streaming test shows us the
that 5G with MEC has an average latency of 28.30 ms, while 5G without
MEC has an average latency of 44.80 ms handling a streaming service.
Both performance and streaming test show the importance of MEC technology
in the network. The load test shows that 5G with MEC have a better
performance rather than WiFi 6 when the number of users is above 10 users,
this demonstrates that 5G with MEC have a better capacity to handle many
users rather than WiFi 6(802.11ax).

[1] Cisco. ”Cisco Annual Internet Report (2018–2023)”.Tech. rep. 2020.URL: https :
/ / www. cisco . com / c / en /us / solutions / collateral / executive perspectives
/
annual internetreport/
whitepaperc11741490.
html.
[2] S. Kitanov and T. Janevski, ”State of the Art: Mobile Cloud Computing,” 2014 Sixth
International Conference on Computational Intelligence, Communication Systems
and Networks, Tetova, 2014, pp. 153158,
doi: 10.1109/CICSyN.2014.41.
[3] M. Satyanarayanan et al., ” An open ecosystem for mobilecloud
convergence,”
in IEEE Communications Magazine, vol. 53, no. 3, pp. 6370,
March 2015, doi:
10.1109/MCOM.2015.7060484.
[4] M. Satyanarayanan, P. Bahl, R. Caceres and N. Davies, ”The Case for VMBased
Cloudlets in Mobile Computing,” in IEEE Pervasive Computing, vol. 8, no. 4, pp.
1423,
Oct.Dec.
2009, doi: 10.1109/MPRV.2009.82.
[5] M. Simsek, A. Aijaz, M. Dohler, J. Sachs and G. Fettweis, ”5GEnabled
Tactile
Internet,” in IEEE Journal on Selected Areas in Communications, vol. 34, no. 3, pp.
460473,
March 2016, doi: 10.1109/JSAC.2016.2525398.
[6] J. G. Andrews et al., ” What Will 5G Be?,” in IEEE Journal on Selected Areas
in Communications, vol. 32, no. 6, pp. 10651082,
June 2014, doi: 10.1109/
JSAC.2014.2328098.
[7] ”IMT Vision Framework
and overall objectives of thefuture development of IMT
for 2020 and beyond”. Tech.rep. ITUR
(Radiocommunication Sector of ITU),
Sept.2015.
[8] Tim Verbelen, Pieter Simoens, Filip De Turck, and Bart Dhoedt. 2012. ”
Cloudlets: bringing the cloud to the mobile user”. In Proceedings of the third
ACM workshop on Mobile cloud computing and services (MCS ’12). Association
for Computing Machinery, New York, NY, USA, 29–36. DOI:https://doi.org/
10.1145/2307849.2307858
[9] Y. Jararweh, A. Doulat, A. Darabseh, M. Alsmirat, M. AlAyyoub
and E. Benkhelifa,
”SDMEC: Software Defined System for Mobile Edge Computing,” 2016 IEEE
International Conference on Cloud Engineering Workshop (IC2EW), Berlin, 2016,
pp. 8893,
doi: 10.1109/IC2EW.2016.45.
[10] N. Abbas, Y. Zhang, A. Taherkordi and T. Skeie, ”Mobile Edge Computing: A Survey,”
in IEEE Internet of Things Journal, vol. 5, no. 1, pp. 450465,
Feb. 2018, doi:
10.1109/JIOT.2017.2750180.
[11] T. X. Tran, A. Hajisami, P. Pandey and D. Pompili, ”Collaborative Mobile Edge
Computing in 5G Networks: New Paradigms, Scenarios, and Challenges,” in IEEE
Communications Magazine, vol. 55, no. 4, pp. 5461,
April 2017, doi: 10.1109/
MCOM.2017.1600863.
[12] L. Cominardi, T. Deiss, M. Filippou, V. Sciancalepore, F. Giust and D. Sabella, ”
MEC Support for Network Slicing: Status and Limitations from a Standardization
Viewpoint,” in IEEE Communications Standards Magazine, vol. 4, no. 2, pp. 2230,
June 2020, doi: 10.1109/MCOMSTD.001.1900046.
[13] Y. C. Hu, M. Patel, D. Sabella, N. Sprecher and V. Young, ”Mobile Edge Computing
A
keytechnology towards 5G”. Tech. rep. ETSI (EuropeanTelecommunications
Standards Institute), Sept. 2015.
[14] N. Nikaein, X. Vasilakos and A. Huang, ”LLMEC:
Enabling Low Latency Edge Applications,”
2018 IEEE 7th International Conference on Cloud Networking (CloudNet),
Tokyo, 2018, pp. 17,
doi: 10.1109/CloudNet.2018.8549500.
[15] A. Huang, N. Nikaein, T. Stenbock, A. Ksentini and C. Bonnet, ” Low latency
MEC framework for SDNbased
LTE/ LTEA
networks,” 2017 IEEE International
Conference on Communications (ICC), Paris, 2017, pp. 16,
doi: 10.1109/
ICC.2017.7996359.
[16] Huawei et al.”MobileEdge
Computing –Introductory
Technical White Paper”.
Tech. rep. Sept. 2014.URL: https : / / portal . etsi . org / portals / 0 / tbpages /mec /
docs / mobile edgecomputingintroductorytechnicalwhitepaperv1
[17] M. Chen and Y. Hao, ”Task Offloading for Mobile Edge Computing in Software
Defined UltraDense
Network,” in IEEE Journal on Selected Areas in Communications,
vol. 36, no. 3, pp. 587597,
March 2018, doi: 10.1109/JSAC.2018.2815360.
[18] J. Liu, Y. Mao, J. Zhang and K. B. Letaief, ” Delayoptimal
computation task
scheduling for mobileedge
computing systems,” 2016 IEEE International Symposium
on Information Theory (ISIT), Barcelona, 2016, pp. 14511455,
doi: 10.1109/
ISIT.2016.7541539.
[19] F. Wang, J. Xu, X. Wang and S. Cui, ”Joint Offloading and Computing Optimization
in Wireless Powered MobileEdge
Computing Systems,” in IEEE Transactions on
Wireless Communications, vol. 17, no. 3, pp. 17841797,
March 2018, doi: 10.1109/
TWC.2017.2785305.
[20] Q. Zheng, Z. Ping and P. Lin, ”Performance Evaluation of Applications Assisted
with Twotier
MEC Architecture Using High Performance Drives,” 2019 IEEE 4th
International Conference on Cloud Computing and Big Data Analysis (ICCCBDA),
Chengdu, China, 2019, pp. 523528,
doi: 10.1109/ICCCBDA.2019.8725705.
[21] J. Liu, G. Shou, Y. Liu, Y. Hu and Z. Guo, ”Performance Evaluation of Integrated
MultiAccess
Edge Computing and FiberWireless
Access Networks,” in IEEE Access,
vol. 6, pp. 3026930279,
2018, doi: 10.1109/ACCESS.2018.2833619.
[22] C. Quadri, S. Gaito, R. Bruschi, F. Davoli and G. P. Rossi, ”A MEC Approach to
Improve QoE of Video Delivery Service in Urban Spaces,” 2018 IEEE International
Conference on Smart Computing (SMARTCOMP), Taormina, 2018, pp. 2532,
doi:
10.1109/SMARTCOMP.2018.00095.
[23] E. Coronado, Z. Yousaf and R. Riggio, ”LightEdge: Mapping the Evolution of
MultiAccess
Edge Computing in Cellular Networks,” in IEEE Communications
Magazine, vol. 58, no. 4, pp. 2430,
April 2020, doi: 10.1109/MCOM.001.1900690.
[24] U. Fattore, M. Liebsch and C. J. Bernardos, ”UPFlight: An enabler for Avionic
MEC in a droneextended
5G mobile network,” 2020 IEEE 91st Vehicular Technology
Conference (VTC2020Spring),
2020, pp. 17,
doi: 10.1109/ VTC2020Spring48590.2020.9128732.
[25] M. Mortimer. “iperf3 Documentation”. In: (May2018).
[26] ”YouTube User Statistics 2020”. July 2020.URL: https :/ / www. globalmediainsight
. com / blog / youtube users
statistics/.
[27] T. Barnett Jr, S. Jain, U. Andra, T. Khurana, ”Cisco Visual Networking Index
(VNI)
Complete Forecast Update 20172022”.
Dec.2018.URL: https : / / www . cisco . com
/ c / dam / m /enus / network intelligence
/ service provider
/ digital transformation
/ knowledge network
webinars
/ pdfs /1213businessservicesckn.
pdf
[28] Z. M. Jiang and A. E. Hassan, ”A Survey on Load Testing of LargeScale
Software
Systems,” in IEEE Transactions on Software Engineering, vol. 41, no. 11, pp. 10911118,
1 Nov. 2015, doi: 10.1109/TSE.2015.2445340.
[29] F. Huebner, K. S. MeierHellstern,
and P. Reeser, “Performance testing for IP services
and systems,”in Performance Eng., State of the Art and Current Trends. New
York, NY, USA: Springer, 2001, pp. 283–299.
[30] B. H. Lim, J. R. Kim and K. H. Shim, ”Hierarchical Load Testing Architecture using
Large Scale Virtual Clients,” 2006 IEEE International Conference on Multimedia
and Expo, 2006, pp. 581584,
doi: 10.1109/ICME.2006.262475.
[31] R. Abbas, Z. Sultan and S. N. Bhatti, ”Comparative analysis of automated load
testing tools: Apache JMeter, Microsoft Visual Studio (TFS), LoadRunner, Siege,”
2017 International Conference on Communication Technologies (ComTech), 2017,
pp. 3944,
doi: 10.1109/COMTECH.2017.8065747.