Telecommunications carriers have investigated automating network operations such as failure recovery over the years. When a failure occurs, a large number of alarms (ALMs) are generated from multiple sets of equipment. However, the issuing of ALMs and the number of ALMs change dynamically depending on the situation. Therefore, in order to identify a suspected failure, the scope of the investigation must be specified based on the network topology and the combination of ALMs as a preliminary step. The workflow of such network operations is difficult to define, and efficiently selecting the range to investigate the failure is necessary for rapid failure recovery. However, automating such processes is difficult because in existing search algorithms defining in advance the solution that will terminate a search or conditions under which the search will be completed is impossible. In this paper, we propose a network node search algorithm that uses a graph neural network (GNN) to determine repeatedly the necessity for investigating neighboring equipment to determine the scope of the failure investigation in the network.

Building resilient infrastructure is a Sustainable Development Goal (SDG) defined by the United Nations. Telecommunications infrastructure and electric power infrastructure are crucial to social and economic activities, and increased resilience is required by society. The telecommunications infrastructure requires support from the electric power infrastructure, and vice versa. This dependency limits the degree of optimal control that can be achieved using only the information from one infrastructure. Telecom carriers cannot monitor the status of the electric power infrastructure, which may affect telecommunications' reliability. This problem can be addressed through infrastructure crossover, thus integrating network infrastructure information and electric power infrastructure information. This paper proposes two methods to achieve crossover. The first estimates blackouts of telecommunications service buildings using logs of telecommunications network equipment, even when the power monitoring networks (NWs) have failed. The other prevents construction errors of telecommunications network equipment by detecting changes in the electric current of the equipment. The coordinated use of information from both infrastructures will create new value.

Network and maintenance operations (NWOPs) are being automated. In recent years, there have been attempts to develop artificial intelligence (AI) using machine learning models such as neural networks in order to automate more sophisticated decisions among NWOPs. Equipment alarms (ALMs) are commonly used in many NWOP decisions. To handle ALMs as AI input requires vectorization as other AI inputs, though vectorization employing general one-hot encoding cause generalization performance problem. Its general performance tends to be low despite the large amount of computation. This paper proposes new vectorization method(ALM2Vec) that reflects ALM data and their relational information onto the network topology. ALM2Vec method is able to reduce the amount of calculation, and learning with a high level of generalization performance can be achieved.

Deploying artificial intelligence (AI) to network operations have long been an issue. AI has been expected to help automating network operations, especially in those requiring human decisions, such as handling failures which involve complex decisions. Since current AIs do not have enough parameters for individual failures cases, their accuracy is not enough to fully rely on their decisions. Thus, handing unusual fault cases are still dominated by skilled operators. This paper proposes an extended Business Process Model and Notation (BPMN) which uses Bayesian networks to represent operator's decisions, to connect AIs and workflow engines (WFE) which automates handing atypical failures.

The movement of digital transformation (DX) has reached to telecom carriers. Telecom carriers have long been trying to automate their operation, including assurance works, such as responding to fault alarms. Automating failure response is challenging since the work flows comprises complex flow containing many conditional branches, requiring judgement of skilled operator. Currently, only specific portions are automated, such as verifying construction work and executing specific commands. Therefore, we clarify the evidence accumulation and response process based on system-wide evidence, and propose a fully automated failure response system employing an augmented orchestrator that implements functions equivalent to human judgment. This paper proposes an enhanced orchestrator to automate the entire flow of failure response, such as fault alarm response, which is capable of handling alarms of commercial environment. This paper also describes the problems to automate entire flow of failure response and evaluates implemented proposing orchestrator. Evaluation results show that the aggregation of process succeeded to reduce approximately 82% the amount of in work flow description, and also the orchestrator is capable to handle large amount of alarms in bursts, such as in case of disaster.

In recent years, there are many work efficiency efforts in particular automation of business processes in various industry. The same trend applies to the network operations of telecommunication carriers; however, although automation of service fulfillment, such as developing network services, is progressing, automation of service assurance such as responding to network failure has not progressed. Currently, network maintenance personnel have independently developed tools for automation of network maintenance (such as troubleshooting) process partially and they are manually performing maintenance tasks by coordinating multiple groups of tools. However, in view of the future decrease in the working population, work efficiency must be further improved. Following this situation, this article focuses on further automation of network maintenance process, by developing technologies to orchestrate existing automation tools. In this paper, handling network failures among network maintenance work is targeted, the challenges and the requirements for expansion in the range of automation is discussed, after discussing current automation of network maintenance at telecom carriers in the real world. After that an implementation method that satisfies these requirements using our orchestrator and OSS products is proposed and evaluated. By defining a workflow of network maintenance that makes each process reusable, it becomes easy to create new workflow and update the one, and furthermore it was found that by reviewing how to code the workflow, it was possible to significantly improve processing performance.