An Intelligent Computation Demand Response Framework for IIoT-MEC Interactive Networks

The joint optimization problem of a 5G-inspired IIoT-MEC interactive network aims to maximize revenue of MNOs and minimize IIoT operators’ economic cost is formulated, which is challenging to be solved. This letter proposes a dynamic pricing strategy for IIoT-MEC network to maximize MNOs’ revenue while providing acceptable service prices for IIoT mobile devices (MDs). The dynamic pricing problem is first modeled as a discrete finite Markov decision process (MDP). Then Q-learning algorithm is utilized to solve this problem. The results show that the proposed dynamic pricing strategy can significantly enhance MNOs’ revenue and decrease IIoT operators’ economic cost.

[1]  Hichem Snoussi,et al.  Data-driven prognostic method based on self-supervised learning approaches for fault detection , 2018, J. Intell. Manuf..

[2]  Gang Wang,et al.  Optimizing Network Slice Dimensioning via Resource Pricing , 2019, IEEE Access.

[3]  Kezhi Wang,et al.  Unified Offloading Decision Making and Resource Allocation in ME-RAN , 2017, IEEE Transactions on Vehicular Technology.

[4]  Katrina Jessoe,et al.  Commercial and Industrial Demand Response Under Mandatory Time‐Of‐Use Electricity Pricing , 2015 .

[5]  Ross Macrea,et al.  Greater Manchester and Cheshire East: A Science and Innovation Audit Report sponsored by the Department for Business, Energy & Industrial Strategy , 2016 .

[6]  Haibin Zhang,et al.  Double Auction-Based Resource Allocation for Mobile Edge Computing in Industrial Internet of Things , 2018, IEEE Transactions on Industrial Informatics.

[7]  K. B. Letaief,et al.  A Survey on Mobile Edge Computing: The Communication Perspective , 2017, IEEE Communications Surveys & Tutorials.

[8]  Seung Ho Hong,et al.  A Dynamic pricing demand response algorithm for smart grid: Reinforcement learning approach , 2018, Applied Energy.

[9]  Xu Chen,et al.  In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning , 2018, IEEE Network.

[10]  Weihai Chen,et al.  Industrial IoT in 5G environment towards smart manufacturing , 2018, J. Ind. Inf. Integr..

[11]  Thomas Magedanz,et al.  Application of the Fog computing paradigm to Smart Factories and cyber‐physical systems , 2018, Trans. Emerg. Telecommun. Technol..