AI predicts 5G performance across cities with nearly 100% accuracy
SmartCIC Technologies, a global leader in enterprise-grade wireless testing and Artificial Intelligence (AI), tested and predicted 5G cellular performance across Washington D.C., USA, with 97% accuracy. During International Telecoms Week in May, the company drive tested local networks then compared them to its AI algorithm’s predictions. The results were highly accurate predictive analytics that enable enterprise wireless use cases to rapidly scale across metro areas.
SmartCIC Technologies ‘Drive’ and ‘Walk’ initiatives tested cellular networks across Washington DC and Maryland for a week using its purpose-built technology. Data was captured in the field then uploaded to its database in real-time. More than 30 Machine Learning (ML) models and methodologies were then used to accurately predict cellular performance, boosted by proprietary AI. Testing found maximum download speeds in Washington D.C were 879.20 Mbps with millions of tests conducted.
“97% accuracy was far better than we expected, and we were excited to see this level of precision delivered across a major US city. The results reflect the level of skill in our data and analytics teams and the progress they are making every day. They are optimizing our approach to AI modelling and refining our algorithm and it is delivering amazing results,” said Toby Forman, CEO and Co-Founder at SmartCIC Group. “This level of accuracy enables MNOs and enterprises to confidently rollout new services and benefit from wireless technologies, knowing that local connectivity has the capabilities they need.”
SmartCIC Technologies is capturing independent and enterprise-grade cellular intelligence across 30 National Football League (NFL) cities across the US this year. Its mapping tools provide a visual display of performance and present granular data at each test location. Its AI engine provides visual clusters of the areas that are detected to behave in a consistent way. Clusters show a combination of observed and predicted performance of the networks, down to a street address or enterprise location.
“We’re visualizing data to make it immediately consumable by engineers, network planners, and senior decision makers. Carriers gain insights into where they can deploy enterprise-grade solutions, which accelerates network monetization. They can sell more enterprise services if they know immediately the quality of connectivity that is available at a site. We’re excited to be collaborating with Tier 1 carriers, briefing analysts on our findings and presenting out our data at events around the world,” said Forman.
The accuracy of SmartCIC Technologies’ AI algorithm supports sustainability and ESG principles. It means that testing is not required on every single street or at all enterprise locations to achieve the data density required for predictive analytics. By optimizing test routes, AI helps to minimize carbon footprint while maximizing efficiency.
