A new formula designed to improve how 5G and wireless networks select and share frequencies has been developed by the National Institute of Standards and Technology (NIST).
According to NIST’s research, the machine-learning formula could make frequency sharing about 5,000 times more efficient. “The study found that an exhaustive effort [using trial and error] to identify the best solution would require about 45,600 trials, whereas the formula could select a similar solution by trying only 10 channels, just 0.02 percent of the effort,” the article stated.
Using the theory that radio equipment can “learn” its network environment through experience, a computer-modeled algorithm formulates prior experience in environmental RF conditions to determine which channel provides the best outcome. In this model, the transmitter remembers which channel provides the best outcome and competing transmitters “each learn to maximize the total network data rate without communicating with each other.”
NIST’s model is a promising solution to the chaotic environment that occurs with shared spectrum. For example, when combining WiFi with License Assisted Access – LTE-U at 5GHz – transmissions can bump into each other because the radios don’t communicate with one another. Whereas NIST’s scenario teaches the competing transmitters to “learn to maximize the total network data rate without communicating with each other.”
As 5G and IoT progress, more sharing will be needed to increase communications in limited spectrum. NIST engineer Jason Coder said, “This could potentially make communications in the unlicensed bands much more efficient.”
NIST’s team says the formula could be programmed into software on transmitters in many [different] types of real-world networks.
The post NIST Designs Algorithm to Streamline Frequency Sharing For 5G appeared first on Inside Towers.