By incorporating Nokia Bell Labs' artificial intelligence (AI) innovations and Nokia's capabilities in developing antennas for mobile devices and base stations, ReefShark chipsets leverage silicon developed by Nokia in Oulu, Espoo and Tampere, Finland, as well as in Sunnyvale, California.
ReefShark chipsets for radio frequency (RF) units, such as those used in antennas, improve their performance. This results in antennas that are half the size of massive MIMO antennas. ReefShark chipsets also reduce power consumption in baseband units by 64%, compared to currently used units.
ReefShark chipsets for computing power are delivered as pluggable units for the commercially available Nokia AirScale baseband module. AirScale is software-upgradeable to full 5G functionality, and these pluggable units triple Nokia's current 28 Gbps throughput to 84 Gbps per module. Furthermore, daisy-chaining the AirScale baseband module supports base station throughputs of up to 6 terabits per second, enabling operators to meet the growing demands of increasing densification and support the massive enhanced mobile broadband needs of people and devices in megacities.
 
AI in 5G networks enables real-time radio monitoring and optimization, and the ability to apply techniques such as network slicing to meet the service level demands of new business use cases. Nokia is developing technology with common interfaces and tools that allow service providers to deploy machine learning applications in their networks.
 
Nokia is working with 30 operators using ReefShark and will increase field deployments during the third quarter of 2018.
 
ReefShark chipsets include:
• ReefShark Digital Front End for LTE and 5G radio systems that support massive MIMO
• ReefShark RFIC front-end module and transceiver: massive MIMO Adaptive Antenna solution
• ReefShark baseband processor: all-in-one computing design, capable of supporting the massive scale requirements of 5G.

More information or a quote