Zhang Yaoxue

TL;DR: An onliNe multi-workflOw Scheduling Framework, named NOSF, to schedule deadline-constrained workflows with random arrivals and uncertain task execution time is proposed and significantly outperforms two state-of-the-art algorithms in terms of reducing VM rental costs and deadline violation probability.

TL;DR: In this article, an edge computation system distribution method is proposed, which comprises the following steps of: S1, receiving task information of to-be-distributed tasks sent by a scheduler by computation terminals; S2, calculating costs for executing the tasks and determining offers according to a preset offer model, and applying the tasks from the scheduler according to the offers; and S3,receiving the offer of each computation terminal by scheduler, and distributing the tasks to the computation terminals through a preset task distribution model so as to ensure that the sum of the

TL;DR: In this article, a resource allocation method for a cloud wireless access network is proposed, which comprises the steps: constructing a hybrid energy management calculation model, a data request control calculation model and a power and channel distribution calculation model; obtaining the state parameters of a current gap of the network; calculating and updating the network state through the hybrid EEM model, the data request controller model and the power-and channel distribution model, wherein the hybrid EE model is used for calculating an energy obtaining quantity and an energy purchasing quantity according to the energy state of the current gap, and the data

TL;DR: In this article, a monitoring image processing method and system, and a monitoring terminal is described, which comprises the following steps that: S1: obtaining an image, and extracting the image into an RoI (Region of Interest) and a non-RoI through a preset RoI extraction model; S2: comparing the RoI by a preset first compression rate, and compressing the non-ROI by an additional second compression rate.

TL;DR: In this article, a target detection method, an image recognition server and a system, wherein the method comprises the following steps: S1, receiving a monitoring image, where the monitoring image is divided into a RoI region and a non-RoI region, the RoI Region is compressed according to a first compression rate, the non-ROI region is compressed based on a second compression rate.