Computation Offloading and Content Caching with Traffic Flow Prediction for Internet of Vehicles in Edge Computing

The development of the Internet of Vehicles (IoV) enables numerous emerging in-vehicle applications to accommodate users with various contents, thus enhancing their traveling experiences. In IoV, content decoding tasks are typically offloaded to edge servers for implementation, as edge computing is an admirable paradigm to provide low-latency services. However, as different vehicular users may request the same contents, processing these contents repeatedly leads to the waste of storage, computation and bandwidth resources. Therefore, fine-grained computation offloading and content caching are demanded in IoV. In this paper, a joint optimization method for computation offloading and content caching based on traffic flow prediction, named COC, is proposed. Firstly, traffic flow covered by each edge server is predicted by a modified deep spatiotemporal residual network (ST-ResNet). Secondly, the non-dominated sorting genetic algorithm III (NSGA-III) is leveraged to realize the many-objective optimization to shorten the execution time and reduce the energy consumption of computation and transmission in IoV. Finally, evaluated by real-world big data from Nanjing China, COC shows a great reduction in execution time and energy consumption of transmission and computation compared to other methods.

[1]  M. Shamim Hossain,et al.  Edge-CoCaCo: Toward Joint Optimization of Computation, Caching, and Communication on Edge Cloud , 2018, IEEE Wireless Communications.

[2]  M. Shamim Hossain,et al.  Heterogeneous Information Network-Based Content Caching in the Internet of Vehicles , 2019, IEEE Transactions on Vehicular Technology.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Kalyanmoy Deb,et al.  An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints , 2014, IEEE Transactions on Evolutionary Computation.

[5]  Xuyun Zhang,et al.  An edge computing-enabled computation offloading method with privacy preservation for internet of connected vehicles , 2019, Future Gener. Comput. Syst..

[6]  Yu Kang,et al.  Deep spatiotemporal residual early-late fusion network for city region vehicle emission pollution prediction , 2019, Neurocomputing.

[7]  Mingwei Zhang,et al.  Data Caching Optimization in the Edge Computing Environment , 2019, 2019 IEEE International Conference on Web Services (ICWS).

[8]  Xinfeng Zhang,et al.  Spatial-temporal residue network based in-loop filter for video coding , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).

[9]  Guangming Cui,et al.  A Game-Theoretical Approach for User Allocation in Edge Computing Environment , 2020, IEEE Transactions on Parallel and Distributed Systems.

[10]  Wei Chen,et al.  GreenDelivery: proactive content caching and push with energy-harvesting-based small cells , 2015, IEEE Communications Magazine.

[11]  Sherali Zeadally,et al.  Integration challenges of intelligent transportation systems with connected vehicle, cloud computing, and internet of things technologies , 2015, IEEE Wireless Communications.

[12]  Feng Xia,et al.  Deep Reinforcement Learning for Vehicular Edge Computing , 2019, ACM Trans. Intell. Syst. Technol..

[13]  Yan Zhang,et al.  Cooperative Content Caching in 5G Networks with Mobile Edge Computing , 2018, IEEE Wireless Communications.

[14]  Feng Xia,et al.  Vehicular Social Networks: Enabling Smart Mobility , 2017, IEEE Communications Magazine.

[15]  Xiuwen Yi,et al.  DNN-based prediction model for spatio-temporal data , 2016, SIGSPATIAL/GIS.

[16]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[17]  Giovanni Pau,et al.  Internet of Vehicles: From intelligent grid to autonomous cars and vehicular fogs , 2014, 2014 IEEE World Forum on Internet of Things (WF-IoT).