Mobile Edge and Fog Computing
▶ Introduction


Fog Computing

Fog Computing In recent years, to provide a better quality of service (QoS) to the end devices, the cloud computing paradigm has shifted towards the edge of the network. Hence, the emergence of Fog enables a highly virtualized computing platform that provides data processing, storage and network service like the cloud.

Figure 1 Proposed Mobile Fog Architecture

The generic advantages of Fog over cloud computing in the case of IoT is that Fog provides low latency and location awareness, mobility, various wireless communication capability and heterogeneity to different mobile IoT devices. Thus, the concept of Fog enables edge computing to different heterogeneous Fog devices or in other words IoT devices to ensure better QoS than its predecessor cloud.
Fig.1 represents a model of mobile cloud computing based on the fog computing model of Cisco Systems, Inc. In this mobile fog computing model, the hierarchical architecture of LTE and WiFi internetworking are used. The access points (AP) and the access point controller (APC) units are considered as the fog nodes of mobile fog. The fog enabled AP and APC are the symbolized as F-AP and F-APC.


Mobile Edge Computing

Figure 2 Mobile Edge Computing Architecture

Mobile Edge Computing (MEC) enables the cloud computing facilities within the edge of the network (e.g. Radio Access Network (RAN)) to improve the network performance, services and user’s experience of the mobile users. Fig.2 shows the example of the MEC architecture, where MEC server can be deployed at the RAN and provides the services such as computational offloading, data offloading, content delivery, big data analysis and so on. Therefore, by using the mobile edge computing technology, the mobile operator can manage the network efficiently and enrich the user’s experience.


Caching in Mobile Edge Computing

Caching in Mobile Edge Computing can be classified into several categories as follows,

  • Reactive Caching: The contents are cached onto the cache space when those contents are start requested by users.
  • Proactive Caching: The contents are pre-downloaded or pre-fetched onto the cache space by prediction mechanism before requested by users.
  • Context-Aware Caching: The contents are cached onto the cache space depending on the contextual information.
  • Social Aware Caching: The contents are cached onto the cache space depending on the requested users’ social relationship.

▶ Research Issues


Fog Computing

  1. Context-aware resource allocation
  2. Mobility management for IoE
  3.  Latency reduction for quality of service (QoS) and edge analytics/stream mining
  4. Offloading computation in mobile Fog

Mobile Edge Computing

  1. Big Data processing in cache-enabled wireless networks
  2. Optimized local content distribution

▶ References

  1. Bonomi, Flavio, et al. "Fog computing and its role in the internet of things." Proceedings of the first edition of the MCC workshop on Mobile cloud computing. ACM, 2012.
  2. Bonomi, Flavio, et al. "Fog computing: A platform for internet of things and analytics." Big Data and Internet of Things: A Roadmap for Smart Environments. Springer International Publishing, 2014. 169-186.
  3. “Mobile-Edge Computing,” Eur. Telecommun. Std. Inst. (ETSI), Sophia-Antipolis Cedex, France, white paper, available:
  4. Bastug, Ejder, Mehdi Bennis, and Mérouane Debbah. "Living on the edge: The role of proactive caching in 5G wireless networks." IEEE Communications Magazine 52.8 (2014): 82-89.
  5. Hu, Haibo, et al. "Proactive caching for spatial queries in mobile environments." 21st International Conference on Data Engineering (ICDE'05). IEEE, 2005.
  6. Bastug, Ejder, et al. "Big data meets telcos: A proactive caching perspective." Journal of Communications and Networks 17.6 (2015): 549-557.
  7. Pu, Lingjun, et al. "Content Retrieval At the Edge: A Social-aware and Named Data Cooperative Framework." (2016).
  8. Zeydan, Engin, et al. "Big data caching for networking: Moving from cloud to edge." arXiv preprint arXiv:1606.01581 (2016).
  9. Fajardo, Jose Oscar, et al. "Introducing Mobile Edge Computing Capabilities through Distributed 5G Cloud Enabled Small Cells." Mobile Networks and Applications (2016): 1-11.
  10. Gomes, Andre S., et al. "Edge caching with mobility prediction in virtualized LTE mobile networks." Future Generation Computer Systems (2016).

▶ Achievements

  1. Md. Golam Rabiul Alam, Tran Hoang Nguyen, Cuong T. Do, Chuan Pham, Sarder Fakhrul Abedin, Anupam Kumar Bairagi, Rim Haw, Choong Seon Hong, "Distributed Reinforcement Learning based Code Offloading in Mobile Fog," 한국정보과학회 제 41회 동계학술발표회(KIISE 2014), 2014.12.18~20(18)
  2. Sarder Fakhrul Abedin, Md Golam Rabiul Alam, Nguyen H. Tran, Choong Seon Hong, "A Fog based System Model for Cooperative IoT Node Pairing using Matching Theory," The 17th Asia-Pacific Network Operations and Management Symposium(APNOMS 2015), Aug 19-21, 2015, Busan, Korea
  3. Tri Nguyen Dang, S. M. Ahsan Kazami, Choong Seon Hong, "A Dynamic Algorithm for Computational Offloading in Fog Computing", 2016년 한국컴퓨터종합학술대회(KCC 2016), 2016.06.29.~07.01.
  4. Md. Golam Rabiul Alam, Yan Kyaw Tun, Choong Seon Hong, "Multi-agent and Reinforcement Learning Based Code Offloading in Mobile Fog" The International Conference on Information Networking(ICOIN 2016), Jan 13-15, 2016, Kota Kinabalu, Malaysia
  5. Oanh Tran Thi Kim, Tri Nguyen Dang, VanDung Nguyen, Nguyen H. Tran, Choong Seon Hong, "A Shared Parking Model in Vehicular Network Using Fog and Cloud Environment," The 17th Asia-Pacific Network Operations and Management Symposium(APNOMS 2015), Aug 19-21, 2015, Busan, Korea
  6. Cuong T. Do, Nguyen H. Tran, Chuan Pham, Md. Golam Rabiul Alam, Jae Hyeok Son, Choong Seon Hong, "A Proximal Algorithm for Joint Resource Allocation and Minimizing Carbon Footprint in Geo-distributed Fog Computing," The International Conference on Information Networking(ICOIN 2015), Jan 12-14(14), 2015, Siem Reap, Cambodia