Cisco develops a technology to predict network failures

Cisco has developed a technology that will allow those who use it predict problems and possible failures in company networks before they occur. With it they will have more elements to avoid problems, and also to increase the reliability of the networks.

The software has a predictive engine equipped with Artificial Intelligence and machine learning, which will be in charge of collecting data and telemetry from various sources located within a company’s network, such as routers, switches and servers. Also to learn the patterns of said network, through different models. The engine relies on connectivity and quality of service when making predictions and planning alternative routes, and customers can decide the extent of the engine’s connection to the company network, through a variety of flexible expansion options.

With all this information, the system will help engineers discover hardware problems, bandwidth spikes, and application configuration changes before they can cause problems. It will also offer concrete options for troubleshooting.

Cisco has already tested this technology with some 15 of its most representative clients. Among them are Philips 66, the Adecco Group and Schneider Electric. And according to the Cisco CEO Chuck Robbins, a team of about 30 people has been working on the development of this technology for two years. The company plans to apply it to a fairly diverse range of products and services over the next few years.

Their first plans for it and their initial offerings and integrations will be announced at the annual Cisco Live networking event in June. What is clear is that will be offered in software as a service (SaaS) mode.

Robbins has highlighted that «the future of connectivity will rest on self-healing networks that can learn, predict and plan. Our predictive networking research has been tested and developed with customers, and early adopters are seeing remarkable benefits that are saving them time and money.«.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *