To achieve digital transformation, it is becoming more important to flexibly and quickly provide information and communication technology (ICT) services according to various business requirements. Closed-loop control and its automation with artificial intelligence/machine learning (AI/ML) is a promising approach. However, most of such efforts focus on monitoring and analysis of resources. The challenges remain in automating operation of an entire service that consists of many resources in accordance with the results of the monitoring and analysis. We propose a scheme for automatically designing the topology and configuration of an entire service with various functional/non-functional requirements. To increase both the flexibility of the requirements and quickness to design, our scheme combines a model-based approach with AI/ML. It generates a huge number of design candidates through the model-based approach, and selects promising candidates efficiently by using AI/ML. We present the architecture of the proposed scheme and experiments we conducted involving a case study. Through the experiment, we confirmed that (1) the design speed was improved by 6 times autonomously, and (2) the increasing speed of design time with respect to the increase of intent size is significantly suppressed.

Intent-based design (IBD) methods are used for automatically designing system configurations from service requirements. IBD methods based on graph rewriting can receive flexible requirement definitions as input, which are not confined to a specific format, and flexibly respond to the environment and user demands.However, current graph-rewriting-based methods require a large amount of time to discover a concrete system configuration. Therefore, we propose a graph-rewriting-based IBD method that can discover system configurations more efficiently while maintaining the advantages of current graph-rewriting-based methods by introducing a pruning method that focuses on a single unit in the requirements to be resolved.This paper includes a description of a specific procedure of the proposed method, proof that pruning does not reduce the number of variations of generated system configurations, and experimental results of comparing the proposed method with a graph-rewriting-based method without pruning. The results indicate that the proposed method can reduce computation time by 4-10 times compared with the method without pruning.

In this paper, we propose a novel architecture for a (quasi) optimization problem solver for system designing automation that combines a problem generator and general problem solver. It efficiently generates the number of constraints from a simple description about system requirements, and solves the optimization problem at high speed by utilizing a powerful problem solver. Our challenge is to apply quantum annealing for this purpose. However, we faced the following technical problems caused by the fundamental properties of a quantum annealer: P1) a quantum annealer does not accept a constraint with inequality, which is necessary to describe system design problems, and P2) digit overflow of the coefficient value in the constraints. In this paper, we illustrate the overall architecture of our problem solver and clarify the aforementioned issues. Then, we present solutions to each problem: S1) a conversion method from inequality to equation by the augmented Lagrange method, and S2) a problem conversion method that reduces the number of digits of the coefficient without changing the meaning of the problem. Through experiments with a number of example problems, we evaluated the performance and accuracy of our scheme in comparison with a traditional rigorous problem solver. We show that our scheme outperforms the solver at least in a number of situations, and discuss its future utility.

A configuration of an information technology/network (IT/NW) service is composed of components (e.g., applications, servers, and switches), relationships among them, and their attributes. To run a service appropriately, its configuration should be carefully organized to satisfy customer requirements, as well as dependencies and constraints derived from the components. Designing such a service configuration is daunting when the service is deployed in a heterogeneous environment including multiple clouds, edge devices, and different types of existing servers and network nodes. Thus, the time and cost for the designing task are serious problems in providing new services. In this paper, we present Weaver, an automated service configuration designer that generates a concrete service configuration on the basis of abstract customer requirements and the environment in which the service is deployed. Weaver accepts information about such requirements and environment as input and converts it into a fully concretized service configuration that can be deployed in the designated environment. In this paper, we take an example of a video surveillance Internet of Things (IoT) service, where multiple components including cameras, video analyzers and terminals, are distributed over multiple locations. In the evaluation, we show that Weaver produces configurations for designated heterogeneous environments. We also show that design time is dramatically shorter than in traditional system integration procedures. For example, the design time is shorter than a minute when the number of components is less than 150.