Artificial Intelligence and machine learning have long been associated with science fiction movies, with no better example than 2001: A Space Odyssey and Hal the computer (“I’m sorry Dave, I am afraid I can’t do that”).
But what exactly is Artificial Intelligence (AI)?
In its simplest form it is the automation of tasks or functions which otherwise require human intelligence to execute.
Many people may be surprised to learn that AI is already widely used in their day-to-day activities through digital voice assistants such as Amazon’s Alexa or Google Home. AI enables users to interact with their services and devices without using their hands by simply asking them to do certain routine, well-defined tasks such as playing music or turning lights on or off, etc.
But what If we could leverage AI’s ability to engage in active learning while analyzing very large amounts of data? In a telecommunications environment, this could open up a wide range of use cases across both management and operations as well as support a variety of revenue-impacting applications.
To date, the role of AI within the telecommunications environment has been limited to chat bots that are automating customer service inquiries, routing customers to the proper agent and routing prospects with buying intent directly to salespeople.
However, AI is finding its way into many other areas of the telecom networks beyond customer service as a means to help operators improve network efficiency, lower operating costs and improve both the quality of service and customer experience.
As operators transition their network architectures with software-defined networking and virtualization technologies that enable automation, AI will leverage these capabilities to self-diagnose, self-heal and self-orchestrate the network.
Through the use of algorithms that look for patterns, AI will be able to both detect and predict network anomalies, enabling operators to proactively fix problems before customers are impacted. This pattern-recognition capability is particularly useful with respect to network security as AI will be able to help identify suspicious activity related to potential security threats, allowing the network to “take-action” in real time before it impacts network performance.
From a subscriber intelligencer perspective, AI will allow operators to collect, store and analyze data from across an operator’s entire customer base to achieve real-time behavioral insights. This information can be used for a variety of scenarios, such as personalized offers, advertisements and services to the subscriber at the right time. Through partnerships with cities, this information could be used for public safety, traffic management and local event management. Regardless, this information will be essential for operators to achieve better utilization of network resources, allowing the network to adjust services based on user needs, environmental conditions and business goals resulting in better network optimization.
One of the greatest capabilities of AI is its ability to gather and process the large volume of data associated with both the network and its devices to better understand, optimize and improve network capabilities through faster decision making.
ATIS recently released a new report Evolution to an Artificial Intelligence Enabled Network (ATIS-I-0000067), to help the industry further understand how the power of increasingly sophisticated artificial intelligence and machine learning can be leveraged to address some of the ICT industry’s leading challenges.
This new report documents a wide variety of network-related AI use cases including: network anomaly detection, network security, radio access network optimization, dynamic traffic and capacity management, AI and orchestrated management, AI-based subscriber insights, AI-assisted customer support and sales as well as AI-based content processing and management. It also addresses AI architectures and technologies as well as network requirements in support of AI.
Tom Anderson is a Principal Technologist at ATIS specializing in standards, architecture and evolution of service provider networks. In the past, he has worked for major industry vendors including Bell Labs, Lucent, Alcatel-Lucent, Juniper and Cisco where he managed network technology evolution, strategy, standards and architecture. As a 30+ year veteran of the telecommunications industry, Tom has been active in telecommunications standards activities and has held numerous positions in the areas of architecture, product development, systems engineering, and product management. His more recent work has focused on Network Function Virtualization (NFV), SDN (Software Defined Networking), end-to-end network optimization, and standards strategy and has chaired a variety of ATIS working groups as well the CSRIC WG8 on Priority Services.