In order to improve software reliability, software defect prediction is applied to the process of software maintenance to identify potential bugs. Traditional methods of software defect prediction mainly focus on designing static code metrics, which are input into machine learning classifiers to predict defect probabilities of the code. However, the characteristics of these artificial metrics do not contain the syntactic structures and semantic information of programs. Such information is more significant than manual metrics and can provide a more accurate predictive model. In this paper, we propose a framework called defect prediction via attention-based recurrent neural network (DP-ARNN). More specifically, DP-ARNN first parses abstract syntax trees (ASTs) of programs and extracts them as vectors. Then it encodes vectors which are used as inputs of DP-ARNN by dictionary mapping and word embedding. After that, it can automatically learn syntactic and semantic features. Furthermore, it employs the attention mechanism to further generate significant features for accurate defect prediction. To validate our method, we choose seven open-source Java projects in Apache, using F1-measure and area under the curve (AUC) as evaluation criteria. The experimental results show that, in average, DP-ARNN improves the F1-measure by 14% and AUC by 7% compared with the state-of-the-art methods, respectively.

On‐demand resource management is a key characteristic of cloud computing. Cloud providers should support the computational resource sharing in a fair way to ensure that no user gets much better resources than others. Another goal is to improve the resource utilization by minimizing the resource fragmentation when mapping virtual machines to physical servers. The focus of this paper is the proposal of a game theoretic resources allocation algorithm that considers the fairness among users and the resources utilization for both. The experiments with an FUGA implementation on an 8‐node server cluster show the optimality of this algorithm in keeping fairness by comparing with the evaluation of the Hadoop scheduler. The simulations based on Google workload trace demonstrate that the algorithm is able to reduce resource wastage and achieve a better resource utilization rate than other allocation mechanisms.

Edge computing provides physical resources closer to end users, becoming a good complement to cloud computing. With the rapid development of container technology and microservice architecture, container orchestration has become a hot issue. However, the container-based microservice scheduling problem in edge computing is still urgent to be solved. In this paper, we first formulate the container-based microservice scheduling as a multi-objective optimization problem, aiming to optimize network latency among microservices, reliability of microservice applications and load balancing of the cluster. We further propose a latency, reliability and load balancing aware scheduling (LRLBAS) algorithm to determine the container-based microservice deployment in edge computing. Our proposed algorithm is based on particle swarm optimization (PSO). In addition, we give a handling strategy to separate the fitness function from constraints, so that each particle has two fitness values. In the proposed algorithm, a new particle comparison criterion is introduced and a certain proportion of infeasible particles are reserved adaptively. Extensive simulation experiments are conducted to demonstrate the effectiveness and efficiency of the proposed algorithm compared with other related algorithms.