基于负载特征的边缘智能系统性能优化

Workload Characteristics Based Performance Optimization for Edge Intelligence

边缘智能指利用人工智能算法为网络边缘设备提供数据分析能力的一种服务形式。然而,边缘计算环境比云计算更加复杂和多变。在构建边缘智能的过程中存在很多问题,例如缺乏量化的评价标准、异构计算平台、复杂的网络拓扑、不断变化的用户需求等,其中比较突出的是算法模型的高资源需求与边缘设备资源储备低之间的矛盾。机器学习是边缘智能的主要工作负载,它需要大量的计算资源,然而边缘设备的计算资源有限,两者的供求关系并不匹配,边缘智能负载的部署和优化成为了一个难题。因此,针对边缘智能负载性能优化问题,文中提出了基于负载特征的边缘智能性能优化CECI(Cloud-Edge Collaborative Inference)策略,从模型选择、批量自适应调整和云边协同方面对不同机器学习负载进行了优化。在模型选择方面,使用基于目标权重的模型自适应选择策略,实现在多个条件约束下,综合权衡多个性能优化目标的效果。在批量自适应调整方面,提出了基于开销反馈的批量自适应调整算法,使得模型在运行时能够达到更好的性能。在云边协同方面,通过结合网络状态和用户时延要求设计出了云边协同策略,进而达到了动态利用云端计算资源的效果。实验结果表明,与云智能相比,所提出的基于负载特征的边缘智能能够缩短50.79%的程序运行时间,降低了42.46%的系统能耗,并提升了4.52%的模型准确率。

Edge intelligence refers to a form of service that uses artificial intelligence algorithms to provide data analysis capabilities for network edge devices.However,the edge computing environment is more complex and changeable than cloud computing.There are many problems in the process of building edge intelligence,such as the lack of quantitative evaluation standards,heterogeneous computing platforms,complex network topologies,and changing user needs.Among them,the more prominent is the contradiction between the high resource demand of the algorithm model and the low resource reserve of edge devices.Machine lear-ning is the main workload of edge intelligence.It requires a lot of computing resources.However,the computing resources of edge devices are limited,and the supply and demand between the two do not match.The deployment and optimization of edge intelligent load has become a problem.Therefore,in response to the problem of edge intelligent load performance optimization,this paper proposes cloud-edge collaborative inference(CECI)based on load characteristics,which is optimized for different machine learning loads in terms of model selection,batch adaptive adjustment and cloud-side collaboration.In terms of model selection,a model adaptive selection strategy based on target weights is used to comprehensively weigh the effects of multiple performance optimization targets under multiple constraints.In the aspect of batch adaptive adjustment,a batch adaptive adjustment algorithm based on overhead feedback is proposed,so that the model can achieve better performance at runtime.In terms of cloud-side collaboration,a cloud-side collaboration strategy is designed by combining network status and user delay requirements to achieve the effect of dynamic utilization of cloud computing resources.Experimental results show that compared with cloud intelligence,the edge intelligence based on load characteristics proposed in this paper can reduce program running time by 50.79%,reduce system energy consumption by 42.46%,and improve model accuracy by 4.52%.