Abstract
The computing power network is an attractive technology that integrates computing resources and the network to provide converged service and has attracted a great deal of attention. In this paper, we study the problem of task assignment and incentive design in CPN. We first formulate the optimization problem as a multistage Stackelberg game with one leader and multiple followers. In the first stage, the platform determines the optimal assignment of tasks (resource purchase) by solving the problem of utility maximization based on the prices submitted by the resource providers. In the second stage, a multi-agent deep reinforcement learning based algorithm is proposed for each resource provider to optimize its pricing strategy based on the environment information. Finally, extensive simulations have been performed to demonstrate the excellent performance of the proposed algorithm.
Supported by National Key Research and Development Program 2021YFB2900200.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, X., Zhang, B., Li, C.: Platform profit maximization on service provisioning in mobile edge computing. IEEE Trans. Veh. Technol. 70(12), 13364–13376 (2021)
Ma, X., Zhao, J., Gong, Y.: Joint scheduling and resource allocation for efficiency-oriented distributed learning over vehicle platooning networks. IEEE Trans. Veh. Technol. 70(10), 10894–10908 (2021)
Ma, X., Zhao, J., Li, Q., Gong, Y.: Reinforcement learning based task offloading and take-back in vehicle platoon networks. In: 2019 IEEE International Conference on Communications Workshops (ICC Workshops), pp. 1–6. IEEE (2019)
Cen, B., et al.: A configuration method of computing resources for microservice-based edge computing apparatus in smart distribution transformer area. Int. J. Electric. Power Energy Syst. 138, 107935 (2022)
Xia, X., et al.: Data, user and power allocations for caching in multi-access edge computing. IEEE Trans. Parallel Distrib. Syst. 33(5), 1144–1155 (2021)
Deng, X., Li, J., Shi, L., Wei, Z., Zhou, X., Yuan, J.: Wireless powered mobile edge computing: dynamic resource allocation and throughput maximization. IEEE Trans. Mob. Comput. (2020)
Cheng, Z., Min, M., Liwang, M., Huang, L., Gao, Z.: Multiagent DDPG-based joint task partitioning and power control in fog computing networks. IEEE Internet Things J. 9(1), 104–116 (2021)
Tian, L., Yang, M., Wang, S.: An overview of compute first networking. Int. J. Web Grid Serv. 17(2), 81–97 (2021)
Computing power network - Framework and architecture. Tech. Rep (2021)
Tang, X., et al.: Computing power network: The architecture of convergence of computing and networking towards 6G requirement. China Commun. 18(2), 175–185 (2021)
Lei, B., Zhao, Q., Mei, J.: Computing power network: an interworking architecture of computing and network based on IP extension. In: 2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR), pp. 1–6. IEEE (2021)
Liu, J., et al.: Computing power network: a testbed and applications with edge intelligence. In: IEEE INFOCOM 2022-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 1–2. IEEE (2022)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)
Richter, S., Aberdeen, D., Yu, J.: Natural actor-critic for road traffic optimisation. Adv. Neural Inf. Process. Syst. 19 (2006)
Acknowledgements
This work was supported in part by the National Key Research and Development Program 2021YFB2900200.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, X., Lei, B., Ji, G., Wei, M., Zhang, Y., Shen, Q. (2023). Multi-agent Deep Reinforcement Learning-based Incentive Mechanism For Computing Power Network. In: Quan, W. (eds) Emerging Networking Architecture and Technologies. ICENAT 2022. Communications in Computer and Information Science, vol 1696. Springer, Singapore. https://doi.org/10.1007/978-981-19-9697-9_4
Download citation
DOI: https://doi.org/10.1007/978-981-19-9697-9_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9696-2
Online ISBN: 978-981-19-9697-9
eBook Packages: Computer ScienceComputer Science (R0)