With the rapid increase of user access, load balancing in cloud data center has become an important factor affecting cluster stability. From the point of view of green scheduling, this paper proposed a virtual machine intelligent scheduling strategy based on machine learning algorithm to achieve load balancing of cloud data center. Firstly, a load forecasting algorithm based on genetic algorithm (SVR_GA), k-means clustering algorithm based on optimized min-max, and adaptive differential evolution algorithm (ESA_DE) to enhance local search ability are proposed to solve the load imbalance problem in cloud data center. The experimental results showed that compared with other classical algorithms, the proposed virtual machine scheduling strategy reduces the number of virtual machine migration by 94.5% and the energy consumption of cloud data center by 49.13%.

Flying safely in complex urban environments is a challenge for unmanned aerial vehicles because path planning in urban environments with many narrow passages and few dynamic flight obstacles is difficult. The path planning problem is decomposed into global path planning and local path adjustment in this paper. First, a branch-selected rapidly-exploring random tree (BS-RRT) algorithm is proposed to solve the global path planning problem in environments with narrow passages. A cyclic pruning algorithm is proposed to shorten the length of the planned path. Second, the GM(1,1) model is improved with optimized background value named RMGM(1,1) to predict the flight path of dynamic obstacles. Herein, the local path adjustment is made by analyzing the prediction results. BS-RRT demonstrated a faster convergence speed and higher stability in narrow passage environments when compared with RRT, RRT-Connect, P-RRT, 1-0 Bg-RRT, and RRT*. In addition, the path planned by BS-RRT through the use of the cyclic pruning algorithm was the shortest. The prediction error of RMGM(1,1) was compared with those of ECGM(1,1), PCGM(1,1), GM(1,1), MGM(1,1), and GDF. The trajectory predicted by RMGM(1,1) was closer to the actual trajectory. Finally, we use the two methods to realize path planning in urban environments.

We successfully improved the interfacial adhesion strength between ultra‐high molecular weight polyethylene (UHMWPE) fiber and resin by the surface modification of UHMWPE fiber with two kinds of SiO2 nanoparticles through gel spinning process. Modified effect of treated SiO2 nanoparticles by coupling agent was superior to original SiO2 nanoparticles. Compared with unmodified fibers, pull‐out tests of modified UHMWPE/treated SiO2 fibers revealed that interfacial adhesion strength increased by the maximum of 10.95%, but corresponding breaking strength decreased by 8.51%. In addition, the interfacial adhesion strength and breaking strength could continue to enhance with increasing the additive amount of treated SiO2 nanoparticles. The results of Differential Scanning Calorimetry (DSC), X‐ray diffraction (XRD), Fourier Transform Infrared Spectroscopy (FTIR), and Scanning Electron Microscopy (SEM) indicated that the crystallinity of all modified fibers decreased while crystallite dimension increased, and the surface of modified fibers by treated SiO2 nanoparticles exhibited polar functional group (C=O). The superiority of this modified technology was that it realized the bulk industrial production and maneuverability, low cost, and no pollution. POLYM. COMPOS., 38:1928–1936, 2017. © 2015 Society of Plastics Engineers

Selection of the optimal users to maximize the quality of the collected sensing data within a certain budget range is a crucial issue that affects the effectiveness of mobile crowdsensing (MCS). The coverage of mobile users (MUs) in a target area is relevant to the accuracy of sensing data. Furthermore, the historical reputation of MUs can reflect their previous behavior. Therefore, this study proposes a coverage and reputation joint constraint incentive mechanism algorithm (CRJC-IMA) based on Stackelberg game theory for MCS. First, the location information and the historical reputation of mobile users are used to select the optimal users, and the information quality requirement will be satisfied consequently. Second, a two-stage Stackelberg game is applied to analyze the sensing level of the mobile users and obtain the optimal incentive mechanism of the server center (SC). The existence of the Nash equilibrium is analyzed and verified on the basis of the optimal response strategy of mobile users. In addition, mobile users will adjust the priority of the tasks in time series to enable the total utility of all their tasks to reach a maximum. Finally, the EM algorithm is used to evaluate the data quality of the task, and the historical reputation of each user will be updated accordingly. Simulation experiments show that the coverage of the CRJC-IMA is higher than that of the CTSIA. The utility of mobile users and SC is higher than that in STD algorithms. Furthermore, the utility of mobile users with the adjusted task priority is greater than that without a priority order.

No abstract