“…An increasing number of researches on distributed offloading techniques has been conducted to address these difficulties. In [20][21][22][23][24], hybrid computation offloading architectures that adopt centralized training and distributed execution are proposed. A distributed DNN offloading algorithm (DDOA) is proposed in [20], multiple distributed DNNs working in parallel are used to create offloading decisions, these DNNs are enhanced further by using the newly generated decisions as a public training set and the back-propagation method with cross-entropy as the loss function.…”
Section: Related Workmentioning
confidence: 99%
“…In [20][21][22][23][24], hybrid computation offloading architectures that adopt centralized training and distributed execution are proposed. A distributed DNN offloading algorithm (DDOA) is proposed in [20], multiple distributed DNNs working in parallel are used to create offloading decisions, these DNNs are enhanced further by using the newly generated decisions as a public training set and the back-propagation method with cross-entropy as the loss function. A Multi-Agent DRL algorithm is proposed in [21] to maximize energy consumption while simultaneously optimizing power control, resource allocation, and user equipment association, considering the cost of offloading and MEC server pricing.…”
Section: Related Workmentioning
confidence: 99%
“…• DDOA [20]: A distributed DNN offloading algorithm, uses two OGs, each one simultaneously making an offloading decision for 3 MDs. .…”
The Internet of Things (IoT), real-time media streaming, and other related technologies have increased due to the rapid development of wireless communication technologies and the enormous growth of computation, storage, and data transmission tasks. Edge-Cloud Computing (ECC) is a technology that can be used to better meet the diverse needs of IoT users, it combines the benefits of Mobile Cloud Computing (MCC) and Mobile Edge Computing (MEC) to meet energy consumption and delay requirements, and achieve more stable and affordable task execution. The most significant challenge in ECC is making realtime task offloading decisions. In order to generate offloading decisions in ECC environments in an efficient and near optimal manner, a Deep Reinforcement Learning (DRL)-based Distributed task Offloading (DRL-DO) framework is proposed. Simulation results demonstrate the accuracy of the DRL-DO framework, it achieves high Gain Ratio (GR) and greatly reduces the energy consumption, response time, while attaining moderate time cost compared with other offloading algorithms.
“…An increasing number of researches on distributed offloading techniques has been conducted to address these difficulties. In [20][21][22][23][24], hybrid computation offloading architectures that adopt centralized training and distributed execution are proposed. A distributed DNN offloading algorithm (DDOA) is proposed in [20], multiple distributed DNNs working in parallel are used to create offloading decisions, these DNNs are enhanced further by using the newly generated decisions as a public training set and the back-propagation method with cross-entropy as the loss function.…”
Section: Related Workmentioning
confidence: 99%
“…In [20][21][22][23][24], hybrid computation offloading architectures that adopt centralized training and distributed execution are proposed. A distributed DNN offloading algorithm (DDOA) is proposed in [20], multiple distributed DNNs working in parallel are used to create offloading decisions, these DNNs are enhanced further by using the newly generated decisions as a public training set and the back-propagation method with cross-entropy as the loss function. A Multi-Agent DRL algorithm is proposed in [21] to maximize energy consumption while simultaneously optimizing power control, resource allocation, and user equipment association, considering the cost of offloading and MEC server pricing.…”
Section: Related Workmentioning
confidence: 99%
“…• DDOA [20]: A distributed DNN offloading algorithm, uses two OGs, each one simultaneously making an offloading decision for 3 MDs. .…”
The Internet of Things (IoT), real-time media streaming, and other related technologies have increased due to the rapid development of wireless communication technologies and the enormous growth of computation, storage, and data transmission tasks. Edge-Cloud Computing (ECC) is a technology that can be used to better meet the diverse needs of IoT users, it combines the benefits of Mobile Cloud Computing (MCC) and Mobile Edge Computing (MEC) to meet energy consumption and delay requirements, and achieve more stable and affordable task execution. The most significant challenge in ECC is making realtime task offloading decisions. In order to generate offloading decisions in ECC environments in an efficient and near optimal manner, a Deep Reinforcement Learning (DRL)-based Distributed task Offloading (DRL-DO) framework is proposed. Simulation results demonstrate the accuracy of the DRL-DO framework, it achieves high Gain Ratio (GR) and greatly reduces the energy consumption, response time, while attaining moderate time cost compared with other offloading algorithms.
“…In order to solve the problem of limited resource in the servers in the edge computing system, Tang et al [30] jointly optimize the problem of DNN partition and resource allocation, and obtain ideal efficiency through iterator alternating optimization algorithm. In order to solve the problem of offloading decisions and bandwidth allocation in the edge computing system, Yang et al [31] propose a distributed DNN offloading algorithm (DDOA) algorithm to generate offloading decisions through multiple parallel DNNs and jointly optimize the weighted sum of delay and energy consumption. To solve the bandwidth allocation problem, the DDOA algorithm uses the orthogonal frequency division multiple access (OFDMA) technique to divide the bandwidth, and the simulation results show the superiority of the performance.…”
Section: Related Workmentioning
confidence: 99%
“…By setting parameter ϕ, we can more intuitively express the relationship between delay and energy consumption. The optimization objective of DDOA algorithm [31] is Delay-Energy Weighted Sum (DEWS) metric:…”
Huge low earth orbit (LEO) satellite networks can achieve global coverage with low latency. In addition, mobile edge computing (MEC) servers can be mounted on LEO satellites to provide computing offloading services for users in remote areas. A multi−user multi−task system model is modeled and the problem of user’s offloading decisions and bandwidth allocation is formulated as a mixed integer programming problem to minimize the system utility function expressed as the weighted sum of the system energy consumption and delay. However, it cannot be effectively solved by general optimizations. Thus, a deep learning−based offloading algorithm for LEO satellite edge computing networks is proposed to generate offloading decisions through multiple parallel deep neural networks (DNNs) and store the newly generated optimal offloading decisions in memory to improve all DNNs to obtain near−optimal offloading decisions. Moreover, the optimal bandwidth allocation scheme of the system is theoretically derived for the user’s bandwidth allocation problem. The simulation results show that the proposed algorithm can achieve a good convergence effect within a small number of training steps, and obtain the optimal system utility function values compared with the comparative algorithms under different system parameters, and the time cost of the system and DNNs is very satisfactory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.