A Case for Adaptive Resource Management in Alibaba Datacenter Using Neural Networks

Both resource efficiency and application QoS have been big concerns of datacenter operators for a long time,but remain to be irreconcilable.High resource utilization increases the risk of resource contention between co-located workload,which makes latency-critical(LC)applications suffer unpredictable,and even unacceptable performance.Plenty of prior work devotes the effort on exploiting effective mechanisms to protect the QoS of LC applications while improving resource efficiency.In this paper,we propose MAGI,a resource management runtime that leverages neural networks to monitor and further pinpoint the root cause of performance interference,and adjusts resource shares of corresponding applications to ensure the QoS of LC applications.MAGI is a practice in Alibaba datacenter to provide on-demand resource adjustment for applications using neural networks.The experimental results show that MAGI could reduce up to 87.3%performance degradation of LC application when co-located with other antagonist applications.     

High Accuracy and Real-Time Gated Viewing Laser Radar

A gated viewing laser radar has an excellent performance in underwater low light level imaging,and it also provides a viable solution to inhibit backscattering.In this paper,a gated viewing imaging system according to the demand for real-time imaging is presented,and then the simulation is used to analyze the performance of the real-time gated viewing system.The range accuracy performance is limited by the slice number,the width of gate,the delay time step,the initial delay time,as well as the system noise and atmospheric turbulence.The simulation results indicate that the highest range accuracy can be achieved when the system works with the optimal parameters.Finally,how to choose the optimal parameters has been researched.