Abstract
Internet of Things (IoT) has emerged as a huge paradigm shift by connecting a versatile and massive collection of smart objects to the Internet, coming to play an important role in our daily lives. Data produced by IoT devices can generate a number of computational tasks that cannot be executed locally on the IoT devices. The most common solution is offloading these tasks to external devices with higher computational and storage capabilities, usually provided by centralized servers in remote clouds or on the edge by using the fog computing paradigm. Nevertheless, in some IoT scenarios there are remote or challenging areas where it is difficult to connect an IoT network to a fog platform with appropriate links, especially if IoT devices produce a lot of data that require processing in real-time. To this purpose, in this article, we propose to use unmanned aerial vehicles (UAVs) as fog nodes. Although this idea is not new, this is the first work that considers power consumption of the computing element installed on board UAVs, which is crucial, since it may influence flight mission duration. A System Controller (SC) is in charge of deciding the number of active CPUs at runtime by maximizing an objective function weighing power consumption, job loss probability, and processing latency. Reinforcement Learning (RL) is used to support SC in its decisions. A numerical analysis is carried out in a use case to show how to use the model introduced in the article to decide the computation power of the computing element in terms of number of available CPUs and CPU clock speed, and evaluate the achieved performance gain of the proposed framework.
- A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash. 2015. Internet of things: A survey on enabling technologies, protocols, and applications. In IEEE Commun. Surv. Tutor. 17, 4 (2015), 2347--2376.Google Scholar
Digital Library
- Sisco Systems, Inc. 2019. Cisco's Mobile Visual Networking Index (VNI) Forecast (2017--2022), Retrieved from https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11-738429.pdf.Google Scholar
- P. Mach and Z. Becvar. 2017. Mobile edge computing: A survey on architecture and computation offloading. IEEE Commun. Surveys Tut. 19, 3 (2017), 1628--1656.Google Scholar
Digital Library
- S. Wang et al. 2017. A survey on mobile edge networks: Convergence of computing, caching and communications. IEEE Access 5 (2017), 6757--6779.Google Scholar
Cross Ref
- H. T. Dinh, C. Lee, D. Niyato, and P. Wang. 2013. A survey of mobile cloud computing: Architecture, applications, and approaches. Wirel. Commun. Mobile Comput. 13, 18 (2013), 1587--1611.Google Scholar
Cross Ref
- Alessio Botta, Walter de Donato, Valerio Persico, Antonio Pescapè. 2015. Integration of cloud computing and internet of things: A survey. J. Fut. Gen. Comput. Syst. 18 (2015), 1--54.Google Scholar
- E. K. Markakis et al. 2017. Efficient next generation emergency communications over multi-access edge computing. IEEE Commun. Mag. 55, 11 (2017), 92--97.Google Scholar
Cross Ref
- N. Hassan, S. Gillani, E. Ahmed, I. Yaqoob, and M. Imran. 2018. The role of edge computing in internet of things. IEEE Commun. Mag. 56, 11 (2018), 110--115.Google Scholar
Cross Ref
- M. Jia, J. Cao, and W. Liang. 2017. Optimal cloudlet placement and user to cloudlet allocation in wireless metropolitan area networks. IEEE Trans. Cloud Comput. 5, 4 (2017), 725--37.Google Scholar
Cross Ref
- A. M. M. Ali, N. M. Ahmad, and A. H. M. Amin. 2014. Cloudlet-based cyber foraging framework for distributed video surveillance provisioning. In Proceedings of the 4th World Congress on InfOrmation and Communication Technologies (WICT’14). 199--204.Google Scholar
Cross Ref
- T. Taleb et al. 2017. Mobile edge computing potential in making cities smarter. IEEE Commun. Mag. 55, 3 (2017), 38--43.Google Scholar
Digital Library
- F. Bonomi, R. Milito, J. Zhu, and S. Addepalli. 2012. Fog computing and its role in the internet of things. In Proceedings of the 1st MCC Workshop on Mobile Cloud Computing. New York, NY. ACM, 2012, 13--16.Google Scholar
Digital Library
- S. Yi, C. Li, and Q. Li, 2015. A survey of fog computing: Concepts, applications and issues. In Proceedings of the Workshop on Mobile Big Data. ACM, 37--42.Google Scholar
- M. Yannuzzi, R. Milito, R. Serral-Graci, D. Montero, and M. Nemirovsky. 2014. Key ingredients in an IoT recipe: Fog computing, cloud computing, and more fog computing. In Proceedings of the IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD’14). 325--329.Google Scholar
- M. Aazam and Eui-Nam Huh. Fog computing micro datacenter based dynamic resource estimation and pricing model for IoT. In Proceedings of the IEEE 29th International Conference on Advanced Information Networking and Applications (AINA’15). 687--694.Google Scholar
- N. Siriphun, S. Kashihara, D. Fall, and A. Khurat. 2018. Distinguishing drone types based on acoustic wave by IoT device. In Proceedings of the 22nd International Computer Science and Engineering Conference (ICSEC’18). 1--4.Google Scholar
- F. Zhou, Y. Wu, H. Sun, and Z. Chu. 2018. UAV-enabled mobile edge computing: Offloading optimization and trajectory design. ArXiv Eprints, Feb. 2018.Google Scholar
- L. Wang and M. Hua. 2017. Optimal bit allocation for UAV-enabled mobile communication. In Proceedings of the IEEE International Conference on Computer and CommunIcations. 474--478.Google Scholar
- G. Lee, W. Saad, and M. Bennis. 2018. Online optimization for UAV-assisted distributed fog computing in smart factories of industry 4.0. In Proceedings of the IEEE Global Communications Conference (GLOBECOM’18). 1--6.Google Scholar
- N. Mohamed, J. Al-Jaroodi, I. Jawhar, H. Noura, and S. Mahmoud. 2017. UAVFog: A UAV-based fog computing for internet of things. In Proceedings of the IEEE SmartWorld, Ubiquitous Intelligence 8 Computing, Advanced 8 Trusted Computed, Scalable Computing 8 Communications, Cloud 8 Big Data Computing, Internet of People, and Smart City Innovation Conference. (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI’17). 1--8.Google Scholar
- H. Ye, G. Y. Li, and B. F. Juang. 2019. Deep reinforcement learning based resource allocation for V2V communications. IEEE Trans. Vehic. Technol. 68, 4 (2019), 3163--3173.Google Scholar
Cross Ref
- M. A. Salahuddin, A. Al-Fuqaha, and M. Guizani. 2016. Reinforcement learning for resource provisioning in the vehicular cloud. IEEE Wirel. Commun. 23, 4 (2016), 128--135.Google Scholar
Digital Library
- Y. He, N. Zhao, and H. Yin. 2018. Integrated networking, caching and computing for connected vehicles: A deep reinforcement learning approach. IEEE Trans. Vehic. Technol. 67, 1 (2018), 44--55.Google Scholar
Cross Ref
- W. Wang et al. 2018. A network traffic flow prediction with deep learning approach for large-scale metropolitan area network. In Proceedings of the IEEE/IFIP Network Operations and Management Symposium. 1--9.Google Scholar
Cross Ref
- Akshay Agrawal. 2016. CS221 Final Report, July 24, 2016. Retrieved from https://www.debugmind.com/xavier.pdf. Last access: August 2020.Google Scholar
- R. Ghasem Aghaei, M. A. Rahman, W. Gueaieb, and A. El Saddik. 2007. Ant-colony-based reinforcement learning algorithm for routing in wireless sensor networks. In Proceedings of the IEEE Instrumentation and Measurement Technology Conference (IMTC’07). 1--6.Google Scholar
- S. Wang et al. 2018. Deep reinforcement learning for dynamic multichannel access in wireless networks. IEEE Trans. Cog. Commun. Netw. 4 (Feb. 2018).Google Scholar
- H. Bayat-Yeganeh, V. Shah-Mansouri, and H. Kebriaei. 2018. A multi-state Q-learning based CSMA MAC protocol for wireless networks. Wirel. Netw. 24, 4 (2018), 1251--1264.Google Scholar
Digital Library
- U. S. Shanthamallu, A. Spanias, C. Tepedelenlioglu, and M. Stanley. 2017. A brief survey of machine learning methods and their sensor and IoT applications. In Proceedings of the 8th International Conference on Information, Intelligence, Systems 8 Applications (IISA’17). 1--8.Google Scholar
- P. S. Pandey. 2017. Machine learning and IoT for prediction and detection of stress. In Proceedings of the 17th International Conference on Computational Science and Its Applications (ICCSA’17). 1--5.Google Scholar
Cross Ref
- L. Li and A. Ghasemi. 2019. IoT-enabled machine learning for an algorithmic spectrum decision process. IEEE Internet Things J. 6, 2 (2019), 1911--1919.Google Scholar
Cross Ref
- H. Li, K. Ota, and M. Dong. 2018. Learning IoT in edge: Deep learning for the internet of things with edge computing. IEEE Netw. 32, 1 (2018), 96--101.Google Scholar
Cross Ref
- D. Nemirovsky, T. Arkose, N. Markovic, M. Nemirovsky, O. Unsal, and A. Cristal. 2017. A machine learning approach for performance prediction and scheduling on heterogeneous CPUs. In Proceedings of the 29th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD’17). 121--128.Google Scholar
- Y. Yan, B. Zhang, and J. Guo. 2016. An adaptive decision making approach based on reinforcement learning for self-managed cloud applications. In Proceedings of the IEEE International Conference on Web Services (ICWS’16). 720--723.Google Scholar
- A. Y. Zomaya, M. Clements, and S. Olariu. 1998. A framework for reinforcement-based scheduling in parallel processor systems. IEEE Trans. Parallel Distrib. Syst. 9, 3 (1998), 249--260.Google Scholar
Digital Library
- G. Tesauro. 2007. Reinforcement learning in autonomic computing: A manifesto and case studies. IEEE Internet Comput. 11, 1 (2007), 22--30.Google Scholar
Digital Library
- R. Li et al. 2018. Deep reinforcement learning for resource management in network slicing. IEEE Access 6 (2018), 74429--74441.Google Scholar
Cross Ref
- I. Stojmenovic and S. Wen. 2014. The fog computing paradigm: Scenarios and security issues. In Proceedings of the IEEE Federated Conference on Computer Science and Information Systems (FedCSIS’14).Google Scholar
- S. Yi, C. Li, and Q. Li. 2015. A survey of fog computing: Concepts, applications and issues. In Proceedings of the ACM Workshop on Mobile Big Data. 37--42.Google Scholar
- M. A. Hassan, M. Xiao, Q. Wei, and S. Chen. 2015. Help your mobile applications with fog computing. In Proceedings of the Fog Networking for 5G and IoT Workshop.Google Scholar
- Ivan Stojmenovic, Sheng Wen, Xinyi Huang, and Hao Luan. 2016. An overview of fog computing and its security issues. Concurr. Comput.: Pract. Exper. 28, 10 (2016), 2751--3020.Google Scholar
Digital Library
- C. Dsouza, G. J. Ahn, and M. Taguinod. 2014. Policy-driven security management for fog computing: Preliminary framework and a case study. In Proceedings of the IEEE 15th International Conference on Information Reuse and Integration (IRI’14). 16--23.Google Scholar
- C. C. Byers. 2017. Architectural imperatives for fog computing: Use cases, requirements, and architectural techniques for fog-enabled IoT networks. IEEE Commun. Mag. 55, 8 (2017), 14--20.Google Scholar
Digital Library
- D. Georgakopoulos et al. 2016. Internet of things and edge cloud computing roadmap for manufacturing. IEEE Cloud Comput. 3, 4 (2016), 66--73.Google Scholar
Cross Ref
- P. Patel, M. I. Ali, and A. Sheth. 2017. On using the intelligent edge for IoT analytics. IEEE Intell. Syst. 32, 5 (2017), 64--69.Google Scholar
Cross Ref
- T. Suganuma et al. 2018. Multiagent-based flexible edge computing architecture for IoT. IEEE Netw. 32, 1 (2018), 16--23.Google Scholar
Cross Ref
- P. Mach and Z. Becvar. 2017. Mobile edge computing: A survey on architecture and computation offloading. IEEE Commun. Surv. Tut. 19, 3 (2017), 1628--1656.Google Scholar
Digital Library
- M. Mozaffari, W. Saad, M. Bennis, and M. Debbah. 2016. Unmanned aerial vehicle with underlaid device-to-device communications: Performance and tradeoffs. IEEE Trans. Wirel. Commun. 15, 6 (2016), 3949--3963.Google Scholar
Cross Ref
- Y. Zeng, R. Zhang, and T. J. Lim. 2016. Wireless communications with unmanned aerial vehicles: Opportunities and challenges. IEEE Commun. Mag. 54, 5 (2016), 36--42.Google Scholar
Digital Library
- F. Jiang and A. L. Swindlehurst. 2012. Optimization of UAV heading for the ground-to-air uplink. IEEE J. Select. Areas Commun. 30, 5 (2012), 993--1005.Google Scholar
Cross Ref
- Y. Zeng, R. Zhang, and T. J. Lim. 2016. Throughput maximization for UAV-enabled mobile relaying systems. IEEE Trans. Commun. 64, 12 (2016), 4983--4996.Google Scholar
Cross Ref
- V. V. Chetlur and H. S. Dhillon. 2017. Downlink coverage analysis for a finite 3-D wireless network of unmanned aerial vehicles. IEEE Trans. Commun. 65, 10 (2017), 4543--4558.Google Scholar
- M. Chen, M. Mozaffari, W. Saad, C. Yin, M. Debbah, and C. S. Hong. 2017. Caching in the sky: Proactive deployment of cache-enabled unmanned aerial vehicles for optimized quality-of-experience. IEEE J. Select Areas Commun. 35, 5 (2017), 1046--1061.Google Scholar
Digital Library
- M. Mozaffari, W. Saad, M. Bennis, and M. Debbah. 2017. Mobile unmanned aerial vehicles (UAVs) for energy-efficient internet of things communications. IEEE Trans. Wirel. Commun. 16, 11 (2017), 7574--7589.Google Scholar
Cross Ref
- I. Rubin and R. Zhang. 2007. Placement of UAVs as communication relays aiding mobile Ad Hoc wireless networks. In MILCOM 2007 - IEEE Military Communications Conference, Orlando, FL, USA, 2007. 1--7.Google Scholar
Cross Ref
- S. Rohde and C. Wietfeld. 2012. Interference aware positioning of aerial relays for cell overload and outage compensation. In Proceedings of the IEEE Vehicular Technology Conference. 1--5.Google Scholar
- Y. Wang, W. Peng, Q. Dou, and Z.-h. Gong. 2013. Energy-constrained ferry route design for sparse wireless sensor networks. J. Centr. South Univ. 20, 11 (2013), 3142--3149.Google Scholar
Cross Ref
- I. Jawhar, N. Mohamed, J. Al-Jaroodi, and S. Zhang. 2014. A framework for using unmanned aerial vehicles for data collection in linear wireless sensor networks. J. Intell. Robot. Syst. 74, 1 (2014), 437--453.Google Scholar
Digital Library
- S. Jeong, O. Simeone, and J. Kang. 2017. Mobile cloud computing with a UAV-mounted cloudlet: Optimal bit allocation for communication and computation. IET Commun. 11, 7 (2017), 969--974.Google Scholar
Digital Library
- K. Hong, D. Lillethun, U. Ramachandran, B. Ottenwälder, and B. Koldehofe. 2013. Mobile fog: A programming model for large-scale applications on the internet of things. In Proceedings of the 2nd ACM SIGCOMM Workshop on Mobile Cloud Computing. 15--20.Google Scholar
- H. T. Dinh, C. Lee, D. Niyato, and P. Wang. 2013. A survey of mobile cloud computing: Architecture, applications, and approaches. Wirel. Commun. Mobile Comput. 13, 18 (2013), 1587--1611.Google Scholar
Cross Ref
- A. Ahmed and E. Ahmed. 2016. A survey on mobile edge computing. In Proceedings of the IEEE 10th International Conference on Intelligent Systems and Control (ISCO’16).Google Scholar
- H. Eom, P. S. Juste, R. J. O. Figueiredo, O. Tickoo, R. Illikkal, and R. Iyer. 2013. Machine learning-based runtime scheduler for mobile offloading framework. In Proceedings of the IEEE/ACM 6th International Conference on Utility and Cloud Computing (UCC’13). 17--25.Google Scholar
- H. Eom, R. J. O. Figueiredo, H. Cai, Y. Zhang, and G. Huang. 2015. MALMOS: Machine learning-based mobile offloading scheduler with online training. In Proceedings of the IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud’15). 51--60.Google Scholar
- D. Huang, P. Wang, and D. Niyato. 2012. A dynamic offloading algorithm for mobile computing. IEEE Trans. Wirel. Commun. 11, 6 (2012), 1991--1995.Google Scholar
Cross Ref
- R. Kobayashi and K. Adachi. 2019. Radio and computing resource allocation for minimizing total processing completion time in mobile edge computing. IEEE Access 7 (2019), 141119--141132.Google Scholar
Cross Ref
- G.-Y. Pan, J.-Y. Jou, and B.-C. Lai. 2014. Scalable power management using multilevel reinforcement learning for multiprocessors. ACM Trans. Des. Autom. Electron. Syst. 19, 4 (2014).Google Scholar
Digital Library
- Y. Wang and M. Pedram. 2016. Model-free reinforcement learning and Bayesian classification in system-level power management. IEEE Trans. Comput. 65, 12 (2016), 3713--3726.Google Scholar
Digital Library
- G. Faraci, A. Raciti, S. A. Rizzo, G. Schembra. 2019. Green wireless power transfer system for a drone fleet managed by reinforcement learning in smart industry. Elsevier Appl. Energy. DOI:https://doi.org/10.1016/j.apenergy.2019.114204Google Scholar
- Richard S. Sutton and Andrew G. Barto. 2012. Reinforcement Learning: An Introduction. The MIT Press, Cambridge, MA.Google Scholar
- O. Hashida, Y. Takahashi, and S. Shimogawa. 1991. Switched batch Bernoulli process (SBBP) and the discrete-time SBBP/G/1 queue with application to statistical multiplexer performance. IEEE J. Select. Areas Commun. 9, 3 (1991), 394--401.Google Scholar
Digital Library
- A. Lombardo, G. Morabito, G. Schembra. 2004. Modeling intramedia and intermedia relationships in multimedia network analysis through multiple time-scale statistics. IEEE Trans. Multimedia 6, 1 (2004).Google Scholar
Digital Library
- Y. Zeng, J. Xu, and R. Zhang. 2019. Energy minimization for wireless communication with rotary-wing UAV. IEEE Trans. Wirel. Commun. 18, 4 (2019), 2329--2345.Google Scholar
Cross Ref
- J. C. Charr, R. Couturier, A. Fanfakh, and A. Giersch. 2014. Dynamic frequency scaling for energy consumption reduction in synchronous distributed applications. In 2014 IEEE International Symposium on Parallel and Distributed Processing with Applications, Milan, 2014. 225--230.Google Scholar
Digital Library
Index Terms
Fog in the Clouds: UAVs to Provide Edge Computing to IoT Devices
Recommendations
Cloud, Fog, or Mist in IoT? That Is the Question
Special Issue on Fog, Edge, and Cloud IntegrationInternet of Things (IoT) has been commercially explored as Platforms as a Services (PaaS). The standard solution for this kind of service is to combine the Cloud computing infrastructure with IoT software, services, and protocols also known as CoT (...
A Pattern for Fog Computing
VikingPLoP '16: Proceedings of the 10th Travelling Conference on Pattern Languages of ProgramsFog Computing is a new variety of the cloud computing paradigm that brings virtualized cloud services to the edge of the network to control the devices in the IoT. We present a pattern for fog computing which describes its architecture, including its ...
From Cloud Computing to Fog Computing: Platforms for the Internet of Things (IoT)
This article describes how in recent years, Cloud Computing has emerged as a fundamental computing paradigm that has significantly changed the approach of enterprises as well as end users towards implementation of Internet technology. The key ...






Comments