Communication efficiency optimization of federated learning for computing and network convergence of 6G networks

Federated learning effectively addresses issues such as data privacy by collaborating across participating devices to train global models.However,factors such as network topology and computing power of devices can affect its training or communication process in complex network environments.Computing and network convergence(CNC)of sixth-generation(6G)networks,a new network architecture and paradigm with computing-measurable,perceptible,distributable,dispatchable,and manageable capabilities,can effectively support federated learning training and improve its communication efficiency.By guiding the participating devices'training in federated learning based on business requirements,resource load,network conditions,and computing power of devices,CNC can reach this goal.In this paper,to improve the communication eficiency of federated learning in complex networks,we study the communication eficiency optimization methods of federated learning for CNC of 6G networks that give decisions on the training process for different network conditions and computing power of participating devices.The simulations address two architectures that exist for devices in federated learning and arrange devices to participate in training based on arithmetic power while achieving optimization of communication efficiency in the process of transferring model parameters.The results show that the methods we proposed can cope well with complex network situations,effectively balance the delay distribution of participating devices for local training,improve the communication eficiency during the transfer of model parameters,and improve the resource utilization in the network.

LONG VALID TIME ENERGY PERFECT CONSERVATIVE FIDELITY SPECTRAL SCHEMES OF BAROTROPIC PRIMITIVE EQUATIONS

In accordance with a new compensation principle of discrete computations,the traditional meteo- rological global (pseudo-) spectral schemes of barotropic primitive equation (s) are transformed into perfect energy conservative fidelity schemes,thus resolving the problems of both nonlinear computa- tional instability and incomplete energy conservation,and raising the computational efficiency of the traditional schemes. As the numerical tests of the new schemes demonstrate,in solving the problem of energy conser- vation in operational computations,the new schemes can eliminate the (nonlinear) computational in- stability and,to some extent even the (nonlinear) computational diverging as found in the traditional schemes,Further contrasts between new and traditional schemes also indicate that,in discrete opera- tional computations,the new scheme in the case of nondivergence is capable of prolonging the valid in- tegral time of the corresponding traditional scheme,and eliminating certain kind of systematical com- putational“climate drift”,meanwhile increasing its computational accuracy and reducing its amount of computation.The working principle of this paper is also applicable to the problem concerning baroclin- ic primitive equations.