Cloud and edge computing have been widely adopted in many application scenarios. With the increasing demand of fast iteration and complexity of business logic, it is challenging to achieve rapid development and continuous delivery in such highly distributed cloud and edge computing environment. At present, microservice-based architecture has been the dominant deployment style, and a microservice system has to evolve agilely to offer stable Quality of Service (QoS) in the situation where user requirement changes frequently. Many research have been conducted to optimally re-deploy microservices to adapt to changing requirements. Nevertheless, complex dependencies between microservices and the existence of multiple instances of one single microservice in a microservice system have not been fully considered in existing works. This paper defines SPPMS, the Service Placement Problem in Microservice Systems that feature complex dependencies and multiple instances, as a Fractional Polynomial Problem (FPP) . Considering the high computation complexity of FPP, it is then transformed into a Quadratic Sum-of-Ratios Fractional Problem (QSRFP) which is further solved by the proposed greedy-based algorithms. Experiments demonstrate that our models and algorithms outperform existing approaches in both quality and computation speed.

The foremost challenge in continual learning is to mitigate catastrophic forgetting, allowing a model to retain knowledge of previous tasks while learning new tasks. Knowledge distillation (KD), a form of regularization, has gained significant attention for its ability to maintain a model’s performance on previous tasks by mimicking the outputs of earlier models during the learning of new tasks, thus reducing forgetting. This article offers a comprehensive survey of continual learning methods employing KD within the realm of image classification. We provide a detailed analysis of how KD is utilized in continual learning methods, categorizing its application into three distinct paradigms. Besides, we classify these methods based on the type of knowledge source used and thoroughly examine how KD consolidates memory in continual learning from the perspective of loss functions. In addition, we have conducted extensive experiments on CIFAR-100, TinyImageNet, and ImageNet-100 across ten KD-integrated continual learning methods to analyze the role of KD in continual learning, and we have further discussed its effectiveness in other continual learning tasks. Our extensive experimental evidence demonstrates that KD plays a crucial role in mitigating forgetting in continual learning and substantiates that, when used with data replay, classification bias adversely affects the effectiveness of KD, whereas employing a separated softmax loss can significantly enhance its efficacy.

An increasing number and diversity of services are available, which results in significant challenges to effectively reuse service during mashup creation. Many works have modeled the mashup creation problem as a service recommendation task and have achieved remarkable results. However, the performance of these methods can be further improved. The main problems affecting these methods include the constraints among recommended services, the evolution of services, and the semantic gap existing in services and mashups. In this paper, we model the mashup creation problem as a service bundle recommendation task that is formally defined to address the constraints among recommended services. And then, a dynamic graph neural network based model called DySR is proposed to tackle the evolution of service and the semantic gap between services and mashups. In order to quantitatively measure how significant the semantic gap between mashups and services is, a measurement method of a semantic gap is given. With it, experiments show that to what extent DySR can reduce the semantic gap in the context of mashup creation. In addition, new evaluation metrics are introduced to overcome the preference for popular services in traditional service recommendations. Extensive experiments conducted on a real-world dataset from ProgrammableWeb, and the experiment results show that DySR outperforms existing state-of-the-art methods.

Microservices along with cloud-edge computing technologies are widely adopted to take advantage of the abundant computing resources of the cloud and the low latency, high bandwidth capabilities of the edge. However, factors such as frequent user requirement changes have made the current deployment scheme not fully adaptable to new requirements, resulting in an increase in average response time. Therefore, the microservice system needs to adjust the microservice deployment scheme online in response to continuously changing user requirements to reduce the average response time, which is known as the cloud-edge collaborative microservice deployment problem. However, existing methods are not able to meet the efficiency requirements and do not fully consider the complex dependencies of microservices and budget constraints in the cloud. To address this problem, this paper proposes a solution to the cloud-edge collaborative microservice deployment problem by modeling it as an NP-hard integer nonlinear programming problem in a cloud-edge environment consisting of private edge clouds and public cloud. An efficient Two-stage Iterated Greedy Optimization (TIGO) algorithm is also proposed and its convergence is proven. Extensive experimental results show that this approach achieves better average response times in less time compared to existing methods.

QoS (Quality of Service) prediction is a fundamental task for downstream service computing tasks. Yet, how to predict QoS still remains a non-trivial issue. Existing works try to address this problem by either better modeling the impact between users and services or learning better user/service feature embeddings. Despite the challenges, modeling the two aspects jointly can improve the performance of QoS prediction. However, existing works have rarely attempted this approach. In this regard, Graph Neural Networks (GNNs), with their ability to model these two aspects simultaneously, present an exciting opportunity to advance QoS prediction. Unfortunately, GNNs have not yet been systematically studied in this context, and their potential for improving QoS prediction warrants further investigation. In this paper, we apply GNN to the QoS prediction task by proposing a framework called QoSGNN. In this framework, we systematically explore all steps required when applying GNN to QoS prediction and discuss each step's design principles and advantages. Based on these design principles, we provide an implementation of QoSGNN and conduct extensive experiments on a real-world QoS dataset. The experimental results show that our proposed QoSGNN not only significantly outperforms the baselines in terms of QoS prediction performance but also substantially improves other aspects such as cold start, scalability, robustness, and fairness.