Policy Network-Based Dual-Agent Deep Reinforcement Learning for Multi-Resource Task Offloading in Multi-Access Edge Cloud Networks

The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC networks can support a wide range of applications. MEC networks can also leverage various types of resources, including computation resources, network resources, radio resources,and location-based resources, to provide multidimensional resources for intelligent applications in 5/6G.However, tasks generated by users often consist of multiple subtasks that require different types of resources. It is a challenging problem to offload multiresource task requests to the edge cloud aiming at maximizing benefits due to the heterogeneity of resources provided by devices. To address this issue,we mathematically model the task requests with multiple subtasks. Then, the problem of task offloading of multi-resource task requests is proved to be NP-hard. Furthermore, we propose a novel Dual-Agent Deep Reinforcement Learning algorithm with Node First and Link features(NF_L_DA_DRL) based on the policy network, to optimize the benefits generated by offloading multi-resource task requests in MEC networks. Finally, simulation results show that the proposed algorithm can effectively improve the benefit of task offloading with higher resource utilization compared with baseline algorithms.

What is the purpose of launching World Journal of Cardiology?

The first issue of World Journal of Cardiology (WJC), whose preparatory work was initiated on December 13, 2009, will be published on December 31, 2009. The WJC Editorial Board has now been established and consists of 298 distinguished experts from 40 countries. Our purpose of launching WJC is to publish peer-reviewed, high-quality articles via an open-access online publishing model, thereby acting as a platform for communication between peers and the wider public, and maximizing the benefits to editorial board members, authors and readers

Baishideng's century goal:Editing and publishing high-quality articles

Baishideng's goal over the next few years is to edit and publish high-quality articles through the open-access model, to maximize the benefits to members of the editorial board, authors and readers, as well as achieving social and economic benefits.

What is the purpose of launching the World Journal of Pharmacology?

The first issue of the World Journal of Pharmacology(WJP), whose preparatory work was initiated on January 10, 2011, will be published on February 9, 2012. The WJP editorial board has now been established and consists of 100 distinguished experts from 23 countries. Our purpose of launching the WJP is to publish peerreviewed, high-quality articles via an open-access online publishing model, thereby acting as a platform for communication between peers and the wider public, and maximizing the benefits to editorial board members, authors and readers.

Research and Practice of Meta-synthesis Management for the Government-led Urban Complex Construction Project

This paper researches the overall construction target of government-led urban complex construction projects based on the perspective of sustainable urban development. In order to achieve benefit maximization, the meta-synthesis management for the government-led urban complex construction project is studied. In order to combine theory and practice, several typical government-led urban complex construction project cases, such as Guangzhou Higher Education Mega Center and Guangzhou International Financial City etc. are examined. These examples point to the feasibility of government-led meta-synthesis management and demonstrate the benefits that can be achieved through this model.