@article {1800, title = {Making Serverless Not So Cold in Edge Clouds: A Cost-Effective Online Approach}, journal = {IEEE Transactions on Mobile Computing}, year = {2024}, month = {01/2024}, pages = {https://doi.org/10.1109/tmc.2024.3355118}, author = {Ke Xiao and Song Yang and Fan Li and Liehuang Zhu and Xu Chen and Xiaoming Fu} } @article {1773, title = {Leveraging Deep Reinforcement Learning with Attention Mechanism for Virtual Network Function Placement and Routing}, journal = {IEEE Transactions on Parallel and Distributed Systems}, volume = {34}, year = {2023}, month = {04/2023}, pages = {1186-1201}, author = {Nan He and Song Yang and Fan Li and Stojan Trajanovski and Liehuang Zhu and Yu Wang and Xiaoming Fu} } @article {1759, title = {Adaptive and Efficient Qubit Allocation Using Reinforcement Learning in Quantum Networks}, journal = {IEEE Network}, volume = {36}, year = {2022}, month = {09/2022}, pages = {48-54}, abstract = {

Quantum entanglement brings high-speed and inherently privacy-preserving transmission for information communication in quantum networks. The qubit scarcity is an important issue that cannot be ignored in quantum networks due to the limited storage capacity of quantum device, the short lifespan of qubits, etc. In this article, we first formulate the qubit competition problem as the Cooperative-Qubit-Allocation-Problem (CQAP) by taking into account both the waiting time and the fidelity of end-to-end entanglement with the given transmission link set. We then model the CQAP as a Markov Decision Process (MDP) and adopt Reinforcement Learning (RL) algorithm to self-adaptively and cooperatively allocate qubits among quantum repeaters. Further, we introduce Active Learning (AL) algorithm to improve the efficiency of RL algorithm by reducing its trialerror times. Simulation results demonstrate that our proposed algorithm outperforms the benchmark algorithms, with 23.5 ms reduction on average waiting time and 19.2 improvement on average path maturity degree, respectively.

}, keywords = {Quantum entanglement, quantum networks, qubit allocation, reinforcement learning}, author = {Yanan Gao and Song Yang and Fan Li and Xiaoming Fu} } @article {1753, title = {Caching-Enabled Computation Offloading in Multi-Region MEC Network via Deep Reinforcement Learning}, journal = {IEEE Internet of Things Journal}, volume = {9}, year = {2022}, month = {11/2022}, pages = {21086 - 21098}, doi = {10.1109/JIOT.2022.3176289}, author = {Song Yang and Jintian Liu and Fei Zhang and Fan Li and Xu Chen and Xiaoming Fu} } @article {1749, title = {Delay-Sensitive and Availability-Aware Virtual Network Function Scheduling for NFV}, journal = {IEEE Transactions on Services Computing}, volume = {15}, year = {2022}, month = {01/2022}, pages = {188-201}, doi = {10.1109/TSC.2019.2927339}, author = {Song Yang and Fan Li and Ramin Yahyapour and Xiaoming Fu} } @book {1757, title = {Resource Allocation in Network Function Virtualization: Problems, Models and Algorithms}, year = {2022}, publisher = {Springer}, organization = {Springer}, address = {Singapore}, isbn = {978-981-19-4814-5}, url = {https://www.amazon.co.uk/Resource-Allocation-Network-Function-Virtualization/dp/9811948143}, author = {Song Yang and Nan He and Fan Li and Xiaoming Fu} } @conference {1732, title = {A-DDPG: Attention Mechanism-based Deep Reinforcement Learning for NFV}, booktitle = {The 29th IEEE/ACM International Symposium on Quality of Service (IWQoS 2021)}, year = {2021}, month = {06/2021}, author = {Nan He and Song Yang and Fan Li and Stojan Trajanovski and Fernando A. Kuipers and Xiaoming Fu} } @article {1713, title = {Recent Advances of Resource Allocation in Network Function Virtualization}, journal = {IEEE Transactions on Parallel and Distributed Systems}, volume = {32}, year = {2021}, month = {02/2021}, pages = {295-314}, chapter = {295}, author = {Song Yang and Fan Li and Stojan Trajanovski and Xiaoming Fu} } @article {1708, title = {Survivable Task Allocation in Cloud Radio Access Networks with Mobile Edge Computing}, journal = {IEEE Internet of Things Journal}, volume = {8}, year = {2021}, month = {01/2021}, pages = {1095-1108}, author = {Song Yang and Nan He and Fan Li and Stojan Trajanovski and Xu Chen and Yu Wang and Xiaoming Fu} } @article {1714, title = {Traffic routing in stochastic network function virtualization networks}, journal = {Journal of Network and Computer Applications}, volume = {169}, year = {2020}, month = {11/2020}, author = {Song Yang and Fan Li and Stojan Trajanovski and Xiaoming Fu} } @article {1671, title = {Cloudlet Placement and Task Allocation in Mobile Edge Computing}, journal = {IEEE Internet of Things Journal}, volume = {6}, year = {2019}, month = {06/2019}, pages = {5853-5863}, abstract = {

Mobile edge computing (MEC) offers a way to shorten the cloud servicing delay by building the small-scale cloud infrastructures, such as cloudlets at the network edge, which are in close proximity to end users. On one hand, it is energy consuming and costly to place each cloudlet on each access point (AP) to process the requested tasks. On the other hand, the service provider should provide delay-guaranteed service to end users, otherwise they may get revenue loss. In this paper, we first model how to calculate the task completion delay in MEC and mathematically analyze the energy consumption of different equipments in MEC. Subsequently, we study how to place cloudlets on the network and allocate each requested task to cloudlets and public cloud with the minimum total energy consumption without violating each task{\textquoteright}s delay requirement. We prove that this problem is NP-hard and propose a Benders decomposition-based algorithm to solve it. We also present a software-defined network (SDN)-based framework to deploy the proposed algorithm. Extensive simulations reveal that the proposed algorithm can achieve an (close-to-)optimal performance in terms of energy consumption and acceptance ratio compared with two benchmark heuristics.

}, doi = {10.1109/JIOT.2019.2907605}, author = {Song Yang and Fan Li and Meng Shen and Xu Chen and Xiaoming Fu and Yu Wang} }