Hyper-Heuristic Task Scheduling Algorithm Based on Reinforcement Learning in Cloud Computing

The solution strategy of the heuristic algorithm is pre-set and has good performance in the conventional cloud resource scheduling process.However,for complex and dynamic cloud service scheduling tasks,due to the difference in service attributes,the solution efficiency of a single strategy is low for such problems.In this paper,we presents a hyper-heuristic algorithm based on reinforcement learning(HHRL)to optimize the completion time of the task sequence.Firstly,In the reward table setting stage of HHRL,we introduce population diversity and integrate maximum time to comprehensively deter-mine the task scheduling and the selection of low-level heuristic strategies.Secondly,a task computational complexity estimation method integrated with linear regression is proposed to influence task scheduling priorities.Besides,we propose a high-quality candidate solution migration method to ensure the continuity and diversity of the solving process.Compared with HHSA,ACO,GA,F-PSO,etc,HHRL can quickly obtain task complexity,select appropriate heuristic strategies for task scheduling,search for the the best makspan and have stronger disturbance detection ability for population diversity.

An Iterative Learning Approach to Identify Fractional Order KiBaM Model

This paper discusses the parameter and differentiation order identification of continuous fractional order Ki Ba M models in ARX(autoregressive model with exogenous inputs)and OE(output error model) forms. The least squares method is applied to the identification of nonlinear and linear parameters,in which the Grunwald-Letnikov definition and short memory principle are applied to compute the fractional order derivatives.An adaptive P-type order learning law is proposed to estimate the differentiation order iteratively and accurately. Particularly,a unique estimation result and a fast convergence speed can be arrived by using the small gain strategy, which is unidirectional and has certain advantages than some state-of-art methods. The proposed strategy can be successfully applied to the nonlinear systems with quasi-linear characteristics. The numerical simulations are shown to validate the concepts.

Building an Intelligent Home Space for Service Robot Based on Multi-Pattern Information Model and Wireless Sensor Networks

This paper is concerned with constructing a prototype intelligent home environment for home service robot. In this environment, multi-pattern information can be represented by some intelligent artificial marks. Light-packs service robots can provide reliable and intelligent service by interacting with the environment through the wireless sensor networks. The intelligent space consists the following main components: smart devices with intelligent artificial mark;home server that connects the smart device and maintains the information through wireless sensor network;and the service robot that perform tasks in collaboration with the environment. In this paper, the multi-pattern information model is built, the construction of wireless sensor networks is presented, the smart and agilely home service is introduced. Fi- nally, the future direction of intelligent space system is discussed.

CdS nanoparticles decorated hexagonal Fe_(2)O_(3) nanosheets with a Z-scheme photogenerated electron transfer path for improved visible-light photocatalytic hydrogen production

Photocatalytic water splitting for hydrogen production(H_(2))is one of the main potential applications of photocatalytic technology,which can use solar energy as the energy required for chemical reactions to alleviate the energy crisis.In this work,zero-dimensional/two-dimensional(0D/2D)contact surface CdS/α-Fe_(2)O_(3)(CF)heterojunction photocatalyst was synthesized via a simple solvothermal method.Photocatalytic hydrogen production experiments revealed that the CF-15 sample shows the optimal photocatalytic H_(2)rate(1806μmol·h^(-1)·g^(-1))and apparent quantum efficiency(AQE=13.7%atλ=420 nm).The enhancement of photocatalytic performance is mainly attributed to the contact of 0D/2D interface and the synergistic effect of Z-scheme electron transfer mechanism.This work provides an effective way for modified composite semiconductor photocatalyst by constructing special interface heterojunction to achieve highly efficiently catalysis.

Extending the Frequency Range of Surface Plasmon Polariton Mode with Meta-Material

The frequency range that surface plasmon polariton(SPP) mode exists is mainly limited by the metal material.With high permittivity dielectrics above metal surface, the SPP mode at high frequency has extremely large loss or can be cutoff, which limits the potential applications of SPP in the field of optical interconnection, active SPP devices and so on.To extend the frequency range of SPP mode, the surface mode guided by metal/dielectric multilayers meta-material has been studied based on the theory of electromagnetic field. It is demonstrated that surface mode not only could be supported by the meta-material but also extends the frequency to where conventional metal SPP cannot exist. Meanwhile, the characteristics of this surface mode, such as dispersion relation, frequency range, propagation loss and skin depth in metamaterial and dielectrics, are also studied. It is indicated that, by varying the structure parameters, the meta-material guided SPP mode presents its advantages and flexibility over traditional metal one.