In order to maximize the profit of service user virtual resource leasing in cloud computing,a new virtual resource leasing algorithm of cloud computing is proposed.By the cloud computing environment composed of three functional modules which are Virtual Resource Provider(VRP),Cloud Service Provider(CSP) and end user,it gives the virtual resource rental profit target.Considering the distribution of price and the urgency of tasks,for the weakly stationary price sequence,it uses the outlier detection method to filter the extreme price,designs the weak balance operator which uses the exponential function to control the integral shape of objective function’s curve,and uses the non-uniform mutation operator to adjust local operators and effectively predict the future price.Then it gets the optimal leasing rental price of Virtual Machine(VM) processing tasks.Experimental results show that the proposed algorithm can improve the efficiency and rental cost of virual resource and reduce its usage cost.
Cloudlets are small self-maintained clouds.They improve the overall performance of mobile services through balancing user access requests.In practice,the dispersed user demand changes with time,and the service resources of cloudlets need to be deployed in advance according to the prediction of the required resources.Therefore,in order to optimize the overall performance of the system resource utilization,queuing theory is used to construct resource limited service model of cloudlets which fits in with the birth and death processes.Then,the comparison between single and multiple queues show that the single queue model with multiple virtual cores is better than the multi-queue model with single virtual core under the same service intensity.Experimental result showes that the service model of cloudlets can further optimize the overall system performance with the increase of the virtual cores.
The schedulability can be determined based on deadline analysis and response time analysis for the global Fixed Priority(FP) real-time scheduling algorithm.The traditional method takes into account the real-time tasks with a carry-in job.The processor cannot meet the computing requirement of real-time tasks.So this paper proposes a schedulability method.The interference caused by the real time task is analyzed,which takes into account the number of jobs and the number of processors in real-time system.Experimental results show that the method can reduce the amount of interference,obtain a more compact schedulability criterion,and increases the number of tasks that can be passed by schedulability in multiprocessor real-time system.
The existing link estimation methods cannot guarantee the reliability of prediction and limitations large.To solve this problem,according to the similar current link information between the similar nodes of the source node and the similar nodes of the target nodes,the homophily connection principle is introduced,and a relatedness measure between different types of objects is designed to compute the existence probability of a link.It also extends conventional proximity measures to heterogeneous links.Furthermore,the labeled and unlabeled data in heterogeneous information networks are combined,and a heterogeneous collective link prediction algorithm is proposed to predict multiple types of links collectively by capturing the diverse and complex relationships among different types of links and leveraging the complementary prediction information.Empirical studies on real-world tasks demonstrate that the proposed collective link prediction approach can effectively boost link prediction performances in heterogeneous information networks.
In order to improve the computational efficiency and performance of the community discovery algorithm,a semi supervised community discovery gradient descent algorithm based on latent space mapping is proposed.Firstly,a semi supervised community discovery framework based on latent space mapping is constructed based on the latent space representation,then the similarity of the latent space is evaluated by use of the square distance or KL divergence;Secondly,the semi supervised gradient descent optimization rules community discovery algorithm based on the norm of matrices and Frobenius is constructed to achieve the objective function of the local minimum quick access points,which improves the algorithm in large scale community found in practical value.Finally,the theoretical analysis of the computational complexity of the proposed algorithm is presented.Experimental results show that compared with the finding local community structure in networks method,Girvan-Newman networks,Label propagation and other 6 algorithms,the performance of the proposed algorithm is found to have a better performance of community discovery,and the effectiveness of the algorithm is verified.