物聯網大數據分析是實現智慧城市的重要關鍵，利用物聯網技術提供智慧交通、醫療保健、水資源和能源管理等應用的解決方案。然而，像是公共安全和緊急回應等低延遲、快速響應應用的要求，是現有物聯網雲端計算無法完整達到需求的。而霧運算是使用前端裝置或串連接終端裝置，以分散式協作架構進行資料儲存、計算或相關分散式控制管理，是能夠彌補物聯網雲端計算即時性受限制的不足。
依現有oneM2M物聯網架構對於前端邊緣節點之間的高解析度影像資料的傳輸時間為251.2~537.2ms，這樣的傳輸效率勢必不能達到低延遲、快速響應應用的要求。我們提出了一種新穎的方法稱之為oneM2M霧運算架構(oneM2M Fog Computing Architecture)，在此架構之下可以跟鄰近霧節點交流協調合作處理作業需求，因此不再受限於節點對任務執行能力或需要轉發任務到雲端執行。
最後，經實作與測試驗證後，本文所提出的運算架構能讓霧和霧節點之間的高解析度影像資料的傳輸時間只需花費16.7~46.2ms，縮短原來oneM2M架構的傳輸時間高達94.1%。總結來說，這樣的方法將最大幅減少總體端到端的延遲，並符合霧霧運算低延遲、快速響應應用的需求。

According to the existing oneM2M IoT architecture, the transmission time of high-resolution image data between edge nodes is 251.2~537.2ms, so the transmission efficiency will not be able bound to meet the requirements of low latency and fast response application. We propose a novel method called the oneM2M fog computing architecture. Under this architecture, it can communicate with adjacent fog nodes to coordinate and collaborate on job requirements, so they are no longer limited to node-to-task execution capabilities or need to forward tasks to the cloud for execution.
Finally, after practical and test verification, The computing architecture proposed in this paper can make the transmission time of high resolution image data between fog and fog nodes only cost 16.7~46.2ms, and shorten the transmission time of the original oneM2M architecture by up to 94.1%. In summary, such an approach would minimize overall end-to-end latency and meet the need for low latency and fast response applications for fog to fog computing.

[1] J. He, J. Wei, K. Chen, Z. Tang, Y. Zhou, and Y. Zhang, “Multitier fog computing with large-scale IoT data analytics for smart cities,” IEEE Internet of Things Journal, vol. 5, no. 2, pp. 677-686, April 2018.
[2] M. Armbrust, A. Fox, R. Griffith, A. D. Joseph, R. Katz, A. Konwinski, G. Lee, D. Patterson, A. Rabkin, I. Stoica, and M. Zaharia, “A view of cloud computing,” Communications of the ACM, vol. 53, no. 4, pp. 50-58, April 2010.
[3] H. Dinh, C. Lee, D. Niyato, and P. Wang, “A survey of mobile cloud computing: architecture, applications, and approaches,” Wireless Communications and Mobile Computing, vol. 13, no. 8, pp. 1587-1611, December 2013.
[4] Cisco, “Fog computing and the Internet of Things: extend the cloud to where the things are,” White Paper, Cisco, 2015.
[5] C. M. S. Magurawalage, K. Yang, L. Hu, and J. Zhang, “Energy-efficient and network-aware offloading algorithm for mobile cloud computing,” Computer Networks, vol. 74, Part B, pp. 22-33, December 2014.
[6] X. Wang, S. Leng, and K. Yang, “Social-aware edge caching in fog radio access networks,” IEEE Access, vol. 5, pp. 8492-8501, April. 2017.
[7] http://www.onem2m.org/technical/published-drafts, accessed 12 August 2018.
[8] F. J. Lin, B. Y. Chen, B. T. Lin, and W. H. Hu, “Charging architecture for M2M communications,” IEEE World Forum on Internet of Things (WF-IoT), pp. 123-128, Reston, VA, 12-14, December, 2016.
[9] Gartner, “Gartner Says 6.4 Billion Connected Things Will Be in Use in 2016, Up 30 Percent from 2015,” http://www.gartner.com/newsroom/id/3165317, accessed 12 August 2018.
[10] C. MacGillivray et al., IDC FutureScape: Worldwide Internet of Things 2017 Predictions, IDC FUTURESCAPE, DOC # US40755816, November 2016.
[11] N. Choi, D. Kim, S. J. Lee, and Y. Yi, “A fog operating system for user-oriented IoT services: challenges and research directions,” IEEE Communications Magazine, vol. 55, no. 8, pp. 44-51, August 2017.
[12] M. Aazam and E. N. Huh, “Fog computing: the cloud-IoT/IoE middleware paradigm,” IEEE Potentials, vol. 35, no. 3, pp. 40-44, May 2016.
[13] W. Masri, I. A. Ridhawi, N. Mostafa, and P. Pourghomi, “Minimizing delay in IoT systems through collaborative fog-to-fog (F2F) communication,” International Conference on Ubiquitous and Future Networks (ICUFN), pp. 1005-1010, Milan, Italy, 4-7 July 2017.
[14] C. C. Byers, “Architectural imperatives for fog computing: use cases, requirements, and architectural techniques for fog-enabled IoT networks,” IEEE Communications Magazine, vol. 55, no. 8, pp. 14-20, August 2017.
[15] A. Saikar, M. Parulekar, A. Badve, S. Thakkar, and A. Deshmukh, “TrafficIntel: smart traffic management for smart cities,” International Conference on Emerging Trends & Innovation in ICT (ICEI), pp. 46-50, Yashada, Pune, India, Feb. 3-5, 2017.
[16] https://www.raspberrypi.org/, accessed 12 August 2018.
[17] https://www.iconspng.com/image/82992/raspberry-pi-3, accessed 12 August 2018.
[18] https://www.raspberrypi.org/products/camera-module-v2/, accessed 12 August 2018.
[19] https://github.com/IoTKETI/Mobius, accessed 12 August 2018.
[20] http://www.tornadoweb.org/en/stable/, accessed 12 August 2018.
[21] https://www.python.org/, accessed 12 August 2018.
[22] https://nodejs.org/, accessed 12 August 2018.
[23] https://www.mysql.com/, accessed 12 August 2018