Through bypassing the long-distance transmission of cloud services, Mobile Edge Computing (MEC) reduces response delay and ensures Quality-of-Service (QoS). In resource-constrained MEC, due to the strong coupling between service provisioning and task execution, reasonable service caching and resource allocation face many challenges on 1) coordinating the limited storage resources to improve cache hit rate, 2) allocating limited computing resources under delay constraints, and 3) sample collection and model training in dynamic environments. To address these important challenges, we propose CAMART, a novel service Caching and resource Allocation framework via Multi-Agent Reinforcement learning (MARL) with hierarchical knowledge Transfer in Digital Twin (DT) empowered Cloud-Edge Networks (DTCEN). Specifically, we first construct a new DTCEN to realize the mapping from physical to virtual networks. Next, we decouple the joint optimization of service caching and resource allocation into two sub-problems. For the service caching sub-problem, we design an improved MARL-based method to capture global information via a shared-feature extraction network and optimize caching and offloading decisions via a dual-head feature processing network. For the resource allocation sub-problem, we convert it into 0-1 integer programming and design an improved branch-and-bound-based method to reduce computational complexity while guaranteeing a high-quality solution set. Finally, we develop an original DT-driven hierarchical knowledge transfer mechanism to realize cross-scenario knowledge reuse and convergence acceleration. Using real-world datasets, extensive experiments are conducted to validate the superiority of the proposed CAMART. Compared to the state-of-the-art methods, CAMART achieves higher rewards, task completion rate, and cache hit rate in different scenarios.
Zheyi Chen, Jia-Yun Zheng, Hong-Ju Cheng et al.· IEEE Transactions on Mobile...· 1 citation
As public concern about data privacy continues to grow, federated learning (FL), as a machine learning technique that does not require the disclosure of user raw data, has attracted widespread attention. However, it still has many common problems. The first problem stems from the absence of incentive mechanisms utilized to incentivize more participation to improve the performance of learning models. The second problem arises from the limited resources of mobile devices that can be utilized for model training, which will seriously decrease the performance of learning models. To address the aforementioned issues, in this paper, we propose a novel incentive-aware collaborative construction of heterogeneous <underline>Fed</underline>erated lear<underline>N</underline>ing und<underline>e</underline>r <underline>re</underline>so<underline>u</underline>rce con<underline>s</underline>traint, namely FedNereus. In fact, FedNereus incentivizes more workers to participate in model training by applying an auction-based incentive mechanism. It is proved that FedNereus allows participating workers to report their actual cost as their bidding price, which is referred to as <italic>truthfulness</italic>. Furthermore, it also allows workers to obtain non-negative reward, which is also referred to as the <italic>individual rationality</italic>. In order to break the resource limitation, FedNereus meticulously designs the rules of model selection so that workers can only train a portion of the learning model based on their limited hardware capabilities, while maintaining the performance guarantee of learning models. The excess empirical risk of FedNereus is shown to be upper bounded by <inline-formula><tex-math notation="LaTeX">$\mathcal{O}(\frac{1}{T})$</tex-math><alternatives><mml:math><mml:mrow><mml:mi mathvariant="script">O</mml:mi></mml:mrow><mml:mo stretchy="false">(</mml:mo><mml:mfrac><mml:mn>1</mml:mn><mml:mi>T</mml:mi></mml:mfrac><mml:mo stretchy="false">)</mml:mo></mml:math><inline-graphic xlink:href="ying-ieq1-3713425.gif"/></alternatives></inline-formula>, where <inline-formula><tex-math notation="LaTeX">$T$</tex-math><alternatives><mml:math><mml:mi>T</mml:mi></mml:math><inline-graphic xlink:href="ying-ieq2-3713425.gif"/></alternatives></inline-formula> is the number of training rounds. Finally, extensive experiments are conducted, whose results show that FedNereus outperforms state-of-the-art approaches in different learning tasks.
Fu-Yuan Xia, Chen-Hao Ying, Xikun Jiang et al.· IEEE transactions on compute...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
