The U.S. Department of Defense has long aimed to develop a network architecture that’s highly secure, flexible and intelligent. The objective is to enable safe and timely communications to support warfighters and dominate the battlespace.
Military leaders have made important progress toward this goal, though a network that seamlessly and dynamically connects military domains and assets has remained elusive. The technology pieces of the puzzle are now available, and it’s just a matter of fitting them together in real-world use cases.
In particular, layering 5G communications with various forms of artificial intelligence holds the promise of a network topology that’s situationally aware and continuously optimizes to local conditions and objectives. The result will be improved operational success and asset survivability through faster situational awareness driven by efficient data sharing, and more effective collaborative decision-making.
Bringing Together Advanced Technologies
5G is the latest standard for broadband cellular networks. It has significantly improved the speed and responsiveness of communications at the tactical edge.
AI supports more and more military operations. Today’s military aircraft, for example, rely extensively on AI for flight control and systems management. While most aircraft are still operated by humans, operational safety would be compromised without AI providing situational awareness of weather conditions, the presence of other aircraft, and much more.
It’s time to bring together these advanced technologies. Layering AI on top of 5G can give the military’s cellular network the intelligence to seamlessly connect various domain architectures and dynamically modify the network topology at the edge to be more secure and resilient to attack.
Many DoD organizations struggle with a plethora of nodes – compute platforms, user devices, sensors and so on – that need to be integrated over 5G. Many of these are mobile and may be transient in operation; coming and going from the network over time.
5G provides a means to connect these edge resources seamlessly, and AI then processes the data generated to make it coherent, contextual and actionable. The result would be a holistic AI-backed 5G nervous system that continually senses changing local conditions, intelligently forwards information to where it’s needed, and enables people and autonomous systems to make fast, accurate decisions.
Expanding the Tactical Edge
AI can support even more dynamic network configurations at the edge. One use case would be to deploy drones as autonomous, adaptive 5G cellular relays, continually adjusting their locations to optimize communications for mobile warfighters and military assets.
Forms of AI such as machine learning (ML) and heuristics – which are essentially AI shortcuts based on past learnings – can track and predict the locations of troops and resources, weather systems, detect obstructions such as mountains or smoke, rapidly heal damaged portions of the infrastructure, and expand or contract the network as needed. Currently that’s a manual process. AI could automate many portions of it.
None of this was achievable even a few years ago. But the technology is now available. As compute power doubles every 18 months, edge nodes will process more data as sensors increase in number and resolution. As the use of 5G expands, military networks will consolidate and increase compatibility and interoperability with national and international forces. And with the application of AI, mission situational awareness dynamically modifies the behavior and software running on the nodes and the networks that integrate them.
Of course, AI needs time to learn, and that process is continual. But learning began in the datacenter, moved to the cloud, and is now extending to the edge. As the AI-backed system encounters new conditions and classes of objects, new techniques in transfer and federated learning will expand the neural network to understand any new requirements and situations.
AI can give the military’s 5G networks tremendous flexibility, so missions can deploy a flexible technology architecture and use it to solve current problems and adapt to emerging ones. The network at the tactical edge will apply AI techniques to increase node and data security and be more resilient to attack. By combining 5G and AI, the military can better support warfighters, improve asset survivability and contribute to mission operational success.
Leland Brown is a principal engineer and technical director of advanced communications for military, aerospace and government at Intel Corp. Stan Mo is a systems architect in the Internet of Things Group for public sector programs at Intel Corp.
Have an Opinion?
This article is an Op-Ed and the opinions expressed are those of the author. If you would like to respond, or have an editorial of your own you would like to submit, please email C4ISRNET Senior Managing Editor Cary O’Reilly.