Abstract
A smart city improves operational efficiency and comfort of living by harnessing techniques such as the Internet of Things (IoT) to collect and process data for decision-making. To better support smart cities, data collected by IoT should be stored and processed appropriately. However, IoT devices are often task-specialized and resource-constrained, and thus, they heavily rely on online resources in terms of computing and storage to accomplish various tasks. Moreover, these cloud-based solutions often centralize the resources and are far away from the end IoTs and cannot respond to users in time due to network congestion when massive numbers of tasks offload through the core network. Therefore, by decentralizing resources spatially close to IoT devices, mobile edge computing (MEC) can reduce latency and improve service quality for a smart city, where service requests can be fulfilled in proximity. As the service demands exhibit spatial-temporal features, deploying MEC servers at optimal locations and allocating MEC resources play an essential role in efficiently meeting service requirements in a smart city. In this regard, it is essential to learn the distribution of resource demands in time and space. In this work, we first propose a spatio-temporal Bayesian hierarchical learning approach to learn and predict the distribution of MEC resource demand over space and time to facilitate MEC deployment and resource management. Second, the proposed model is trained and tested on real-world data, and the results demonstrate that the proposed method can achieve very high accuracy. Third, we demonstrate an application of the proposed method by simulating task offloading. Finally, the simulated results show that resources allocated based upon our models’ predictions are exploited more efficiently than the resources are equally divided into all servers in unobserved areas.
- Nasir Abbas, Yan Zhang, Amir Taherkordi, and Tor Skeie. 2018. Mobile edge computing: a survey. IEEE Internet Things J. 5, 1 (2018), 450–465. DOI:DOI:https://doi.org/10.1109/JIOT.2017.2750180Google ScholarCross Ref
- Laha Ale, Ning Zhang, Huici Wu, Dajiang Chen, and Tao Han. 2019. Online proactive caching in mobile edge computing using bidirectional deep recurrent neural network. IEEE Internet Things J. 6, 3 (2019). DOI:DOI:https://doi.org/10.1109/JIOT.2019.2903245Google ScholarCross Ref
- Khandoker Shuvo Bakar and Sujit K. Sahu. 2015. spTimer : Spatio-temporal Bayesian modeling. J. Statist. Softw. 63, 15 (2015).Google ScholarCross Ref
- Árpád Baricz. 2010. Turán type inequalities for modified Bessel functions. Bull. Austral. Math. Soc. 82, 2 (2010), 254–264. DOI:DOI:https://doi.org/10.1017/S000497271000002XGoogle ScholarCross Ref
- Gianni Barlacchi, Marco De Nadai, Roberto Larcher, Antonio Casella, Cristiana Chitic, Giovanni Torrisi, Fabrizio Antonelli, Alessandro Vespignani, Alex Pentland, and Bruno Lepri. 2015. A multi-source dataset of urban life in the city of Milan and the province of Trentino. Sci. Data 2 (2015), 1–15. DOI:DOI:https://doi.org/10.1038/sdata.2015.55Google Scholar
- Mathieu Bouet and Vania Conan. 2018. Mobile edge computing resources optimization: A geo-clustering approach. IEEE Trans. Netw. Serv. Manag. 15, 2 (2018), 787–796. DOI:DOI:https://doi.org/10.1109/TNSM.2018.2816263Google ScholarCross Ref
- Xiaofei Cao and Sanjay Madria. 2019. Efficient geospatial data collection in iot networks for mobile edge computing. IEEE 18th International Symposium on Network Computing and Applications. 1–10. Google ScholarCross Ref
- Roberto Casadei and Mirko Viroli. 2019. Coordinating computation at the edge: A decentralized, self-organizing, spatial approach. In Fourth International Conference on Fog and Mobile Edge Computing (FMEC’19). 60–67. DOI:DOI:10.1109/FMEC.2019.8795355Google ScholarCross Ref
- Jienan Chen, Siyu Chen, Qi Wang, Bin Cao, Gang Feng, and Jianhao Hu. 2019. IRAF: A deep reinforcement learning approach for collaborative mobile edge computing IoT networks. IEEE Internet Things J. 6, 4 (2019), 7011–7024. DOI:DOI:https://doi.org/10.1109/JIOT.2019.2913162Google ScholarCross Ref
- Lixing Chen, Jie Xu, Shaolei Ren, and Pan Zhou. 2018. Spatio-temporal edge service placement: A bandit learning approach. IEEE Trans. Wirel. Commun. 17, 12 (2018), 8388–8401. DOI:DOI:https://doi.org/10.1109/TWC.2018.2876823Google ScholarDigital Library
- Bowen Fei, Xiaomin Zhu, Daqian Liu, Junjie Chen, Weidong Bao, and Ling Liu. 2020. Elastic resource provisioning using data clustering in cloud service platform. IEEE Trans. Serv. Comput. (2020). DOI:DOI:https://doi.org/10.1109/tsc.2020.3002755Google ScholarCross Ref
- Ana Juan Ferrer, Joan Manuel Marquès, and Josep Jorba. 2019. Towards the decentralised cloud: Survey on approaches and challenges for mobile, ad hoc, and edge computing. ACM Comput. Surv. 51, 6 (Jan. 2019). DOI:DOI:https://doi.org/10.1145/3243929 Google ScholarDigital Library
- Xin Gao, Xi Huang, Simeng Bian, Ziyu Shao, and Yang Yang. 2020. PORA: Predictive offloading and resource allocation in dynamic fog computing systems. IEEE Internet Things J. 7, 1 (2020), 72–87. DOI:DOI:https://doi.org/10.1109/JIOT.2019.2945066Google ScholarCross Ref
- Andrew Gelman, John Carlin, Hal Stern, and Donald Rubin. 2003. Bayesian Data Analysis (2nd ed.). Holt, Rinehardt and Winston Chapman and Hall/CRC, Boca Raton, FL.Google Scholar
- Andreas Kamilari and O. Ostermann Frank. 2018. Geospatial analysis and the internet of things. ISPRS Int. J. Geo-inf. 7 (2018), 269. DOI:DOI:https://doi.org/10.3390/ijgi7070269Google ScholarCross Ref
- Yann Lecun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436–444. DOI:DOI:https://doi.org/10.1038/nature14539Google Scholar
- Shu Jin Liu and Guo Qing Zhu. 2014. The application of GIS and IOT technology on building fire evacuation. Procedia Eng. 71 (2014), 577–582. DOI:DOI:https://doi.org/10.1016/j.proeng.2014.04.082Google ScholarCross Ref
- Guiyang Luo, Haibo Zhou, Nan Cheng, Quan Yuan, Jinglin Li, Fangchun Yang, and Xuemin Sherman Shen. 2019. Software defined cooperative data sharing in edge computing assisted 5G-VANET. IEEE Trans. Mob. Comput. 1233, c (2019), 1–1. DOI:DOI:https://doi.org/10.1109/tmc.2019.2953163Google ScholarCross Ref
- Zhe Zhang, Marc Armstrong, and Shaowen Wang. 2019. The Internet of Things and fast data streams: prospects for geospatial data science in emerging information ecosystems. Cartog. Geog. Inf. Sci. 46, 1 (2019), 39–56. DOI:DOI:https://doi.org/10.1080/15230406.2018.1503973Google ScholarCross Ref
- Szu Hui Ng and Jun Yin. 2012. Bayesian Kriging analysis and design for stochastic simulations. ACM Trans. Model. Comput. Simul. 22, 3 (Aug. 2012). DOI:DOI:https://doi.org/10.1145/2331140.2331145 Google ScholarDigital Library
- Catia Prandi, Silvia Mirri, Stefano Ferretti, and Paola Salomoni. 2017. On the need of trustworthy sensing and crowdsourcing for urban accessibility in smart city. ACM Trans. Internet Technol. 18, 1 (Oct. 2017). DOI:DOI:https://doi.org/10.1145/3133327 Google ScholarDigital Library
- Carlo Puliafito, Enzo Mingozzi, Francesco Longo, Antonio Puliafito, and Omer Rana. 2019. Fog computing for the internet of things: a survey. ACM Trans. Internet Technol. 19, 2 (2019). DOI:DOI:https://doi.org/10.1145/3301443 Google ScholarDigital Library
- Pascal Sebah and Xavier Gourdon. 2002. Introduction to the gamma function. Amer. J. Sci. Res. 0, 1 (2002), 1–20. Google Scholar
- Shihao Shen, Yiwen Han, Xiaofei Wang, and Yan Wang. 2019. Computation offloading with multiple agents in edge-computing-supported IoT. ACM Trans. Sen. Netw. 16, 1 (Dec. 2019). DOI:DOI:https://doi.org/10.1145/3372025 Google ScholarDigital Library
- Richard L. Smith, Stanislav Kolenikov, and Lawrence H. Cox. 2003. Spatiotemporal modeling of PM2.5 data with missing values. J. Geophys. Res. D: Atmos. 108, 24 (2003), 1–12. DOI:DOI:https://doi.org/10.1029/2002jd002914Google ScholarCross Ref
- Banerjee Sudipto, Carlin Bradley P., and Gelfand Alan. 2015. Hierarchical Modeling and Analysis for Spatial Data (2nd ed.). Holt, Rinehardt and Winston Chapman and Hall/CRC, Boca Raton, FL. Google Scholar
- Vale Tolpegin, Stacey Truex, Mehmet Emre Gursoy, and Ling Liu. 2020. Data Poisoning Attacks against Federated Learning Systems. arxiv:cs.LG/2007.08432 (2020).Google Scholar
- Duc A. Tran and Quynh Vo. 2018. A geo-aware server assignment problem for mobile edge computing. Int. J. Parallel, Emerg. Distrib. Syst. 5760 (2018). DOI:DOI:https://doi.org/10.1080/17445760.2018.1509216Google Scholar
- Jing Wang, Jian Tang, Zhiyuan Xu, Yanzhi Wang, Guoliang Xue, Xing Zhang, and Dejun Yang. 2017. Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach. In Proceedings of the IEEE International Conference on Computer Communications. DOI:DOI:https://doi.org/10.1109/INFOCOM.2017.8057090Google ScholarCross Ref
- Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu. 2020. A Framework for Evaluating Gradient Leakage Attacks in Federated Learning. arxiv:cs.LG/2004.10397 (2020).Google Scholar
- Guo Yan, Shangguang Wang, Ao Zhou, Jinliang Xu, Jie Yuan, and Ching-Hsien Hsu. 2019. User allocation-aware edge cloud placement in mobile edge computing. Softw.: Pract. Exper. (02 2019). DOI:DOI:https://doi.org/10.1002/spe.2685Google Scholar
- Quan Yuan, Haibo Zhou, Jinglin Li, Zhihan Liu, Fangchun Yang, and Xuemin Sherman Shen. 2018. Toward efficient content delivery for automated driving services: An edge computing solution. IEEE Netw. 32, 1 (2018), 80–86. DOI:DOI:https://doi.org/10.1109/MNET.2018.1700105Google ScholarCross Ref
- Ning Zhang, Nan Cheng, Amila Tharaperiya Gamage, Kuan Zhang, Jon Mark, and Xuemin Shen. 2015. Cloud assisted HetNets toward 5G wireless networks. IEEE Commun. Mag. 53 (06 2015), 59–65. DOI:DOI:https://doi.org/10.1109/MCOM.2015.7120046Google Scholar
- Qianqian Zhang, Walid Saad, Mehdi Bennis, Xing Lu, Mérouane Debbah, and Wangda Zuo. 2018. Predictive deployment of UAV Base stations in wireless networks: Machine learning meets contract theory. CoRR abs/1811.01149 (2018).Google Scholar
Index Terms
- Spatio-temporal Bayesian Learning for Mobile Edge Computing Resource Planning in Smart Cities
Recommendations
Efficient Computing Resource Sharing for Mobile Edge-Cloud Computing Networks
Both the edge and the cloud can provide computing services for mobile devices to enhance their performance. The edge can reduce the conveying delay by providing local computing services while the cloud can support enormous computing requirements. Their ...
Deviceless edge computing: extending serverless computing to the edge of the network
SYSTOR '17: Proceedings of the 10th ACM International Systems and Storage ConferenceThe serverless paradigm has been rapidly adopted by developers of cloud-native applications, mainly because it relieves them from the burden of provisioning, scaling and operating the underlying infrastructure. In this paper, we propose a novel ...
Security computing resource allocation based on deep reinforcement learning in serverless multi-cloud edge computing
AbstractHandling computationally intensive tasks is challenging for user devices (UDs) with limited computing resources. Serverless cloud edge computing solves this problem and reduces maintenance and management. Its crucial function is to allocate ...
Highlights- We model the problem of allocating resources in serverless cloud edge computing.
- We have designed a security mechanism.
- We propose a DRL-based approach to secure computing resource allocation.
Comments