Federated Deep Reinforcement Learning for Joint AeBSs Deployment and Computation Offloading in Aerial Edge Computing Network

Abstract

In the 6G aerial network, all aerial communication nodes have computing and storage functions and can perform real-time wireless signal processing and resource management. In order to make full use of the computing resources of aerial nodes, this paper studies the mobile edge computing (MEC) system based on aerial base stations (AeBSs), proposes the joint optimization problem of computation the offloading and deployment control of AeBSs for the goals of the lowest task processing delay and energy consumption, and designs a deployment and computation offloading scheme based on federated deep reinforcement learning. Specifically, each low-altitude AeBS agent simultaneously trains two neural networks to handle the generation of the deployment and offloading strategies, respectively, and a high-altitude global node aggregates the local model parameters uploaded by each low-altitude platform. The agents can be trained offline and updated quickly online according to changes in the environment and can quickly generate the optimal deployment and offloading strategies. The simulation results show that our method can achieve good performance in a very short time.

Deep Reinforcement Learning-Assisted Optimization for Resource Allocation in Downlink OFDMA Cooperative Systems

“…DRL can also be applied to different function blocks in communication networks, such as end-to-end design, slice management [ 38 ], mobile edge computing [ 39 ], etc. In [ 40 ], the authors construct a DNN-based end-to-end system optimization model to reduce the data at the transmitter end while improving the decoding accuracy.…”

Clustering Technique for Mobile Edge Computing To Detect Clumps in Transportation-Related Problems

“…Liu, L., Zhao et.al [4] additionally, some academics talked about the use of transfer culture in MEC. Reference used distributed knowledge to simultaneously decide which MEC networks should be offloaded.…”

“…The vehicles travelling in a fixed direction (e1) while inside the range of a certain 2. GAM is a member of the set Yd1 Due to the complicated nature of a road network and the frequent entry and exit of vehicles, the connection link is unstable due to the difficulties of mobile nodes that exist with vehicular traffic, and there is a substantial danger that the link will fail [4].…”

Aprendizado Federado e Deep Q-Network habilitando VANTs como Infraestrutura em Redes 6G

“…De acordo com os autores, o cenário inclui vários VANTs aprendendo a trajetória em diferentes configurac ¸ões de ambiente, resultando na convergência mais rápida do modelo. No trabalho de [Liu et al 2022], os autores propuseram uma abordagem para resolver o problema de otimizac ¸ão conjunta da implantac ¸ão de estac ¸ões base aéreas (Aerial Base Station -AeBS) em uma rede de computac ¸ão de borda aérea. A abordagem utiliza um mecanismo de treinamento baseado em FDL, onde AeBSs de baixa altitude treinam suas redes neurais locais individualmente e um HAP desempenha o papel de um nó global para a agregac ¸ão dos modelos.…”