Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G

Abstract

An edge intelligence-aided Internet-of-Things (IoT) network has been proposed to accelerate the response of IoT services by deploying edge intelligence near IoT devices. The transmission of data from IoT devices to the edge nodes leads to large network traffic in the wireless connections. Federated Learning (FL) is proposed to solve the high computational complexity by training the model locally on IoT devices and sharing the model parameters in the edge nodes. This paper focuses on developing an efficient integration of joint edge intelligence nodes depending on investigating an energy-efficient bandwidth allocation, computing Central Processing Unit (CPU) frequency, optimization transmission power, and the desired level of learning accuracy to minimize the energy consumption and satisfy the FL time requirement for all IoT devices. The proposal efficiently optimized the computation frequency allocation and reduced energy consumption in IoT devices by solving the bandwidth optimization problem in closed form. The remaining computational frequency allocation, transmission power allocation, and loss could be resolved with an Alternative Direction Algorithm (ADA) to reduce energy consumption and complexity at every iteration of FL time from IoT devices to edge intelligence nodes. The simulation results indicated that the proposed ADA can adapt the central processing unit frequency and power transmission control to reduce energy consumption at the cost of a small growth of FL time.INDEX TERMS Internet-of-things, federated learning, energy consumption, edge nodes, central processing unit.

Fedresource

“…3 also indicates that the suggested FEDRESOURCE approach performs better than the Scheduling policy [21], Asynchronous FL framework [20], and Heterogeneous computation [18] schemes. For high maximum transmit power, FE-DRESOURCE can increase up to 27%, 55%, and 68% energy efficiency when compared with the Scheduling policy [21], Asynchronous FL framework [20], and Heterogeneous computation [18] schemes respectively.…”

“…In [21] authors established an efficient integration of common edge intelligence nodes based on research on energy-efficient bandwidth allocation, CPU frequency calculation, optimized transmission performance, and required level of learning accuracy. Based on the simulation results, the proposed Alternative Direction Algorithm (ADA) can reduce energy consumption while slightly increasing FL time in the central processing unit.…”

“…The proposed method has been compared with existing techniques such as Heterogenous computation [18], Asynchronous FL framework [20], and scheduling policy [21] in terms of transmission power, convergence of algorithm, throughput, and cost.…”

Smart performance optimization of energy‐aware scheduling model for resource sharing in 5G green communication systems

“…This model incorporates techniques such as user grouping and resource allocation to efficiently manage the network's resources, reducing interference and enhancing the overall network capacity and quality of service. Salh et al [45] have discussed a framework that aims to reduce energy consumption in IoT devices by utilizing federated learning and resource allocation techniques. This approach enables efficient edge intelligence in the emerging 5G networks, leading to reduced energy consumption and improved network sustainability.…”

“…Salh et al. [45] have discussed a framework that aims to reduce energy consumption in IoT devices by utilizing federated learning and resource allocation techniques. This approach enables efficient edge intelligence in the emerging 5G networks, leading to reduced energy consumption and improved network sustainability.…”