For 17 years, I’ve been writing about the possibilities of “cognitive radio”, in which radios sense which spectrum is available from moment to moment and collaborate to frequency-hop (and perform other tricks) to maximize the efficiency of wireless communications.
It’s hard to overstate how revolutionary this would be; today, most radio communication takes place through dedicated spectrum allocations (for example, a radio station will have exclusive rights to a given band in a given territory) that prohibit others from using the spectrum, even if it’s not in use at a given moment.
With cognitive radio, spectrum becomes a commons that everyone shares, with computation, software-defined radios, and phased-array antennas subbing in for the blunt instrument of exclusive spectrum allocation.
Writing in IEEE Spectrum, DARPA’s Paul Tilghman reports on the Agency’s Spectrum Collaboration Challenge, in which teams competed to design algorithms that found efficient models for collaboration with one another. The Challenge has a $4m prize for the winning team, and the championship will be held in LA in October.
The Challenge runs in Colosseum, a simulated environment hosted on a supercomputing cluster at the Johns Hopkins University Applied Physics Laboratory.
As Tilghman writes, the approaches taken by the teams in previous rounds are a kind of recapitulation of the history of AI, starting with first-wave-style expert systems, then evolving into second-wave-style Big Data/machine learning approaches.
I’m not thrilled about this stuff being associated with the DoD, but it’s very exciting to see progress towards delivering on the long-anticipated promise of cognitive radio.
Rather than rely on a few hard-and-fast rules, it seems that a better approach is for each radio to adapt its strategy based on the other radios with which it is sharing spectrum. In effect, the radio should develop an ever-growing series of rules by mining them from a large volume of data—the kind of data that Colosseum is good at generating. That’s why now, during this trial on 9 December 2018, we’re seeing teams shift to a second-wave AI approach. Several teams have built fledgling second-wave AI networks that can quickly characterize how the other networks are playing a match, and use this information to change their own radios’ rules on the fly.When SC2 started, we suspected that many teams would take the simple approach of employing a “sense and avoid” strategy. This is what a Bluetooth device does when it discovers that the spectrum it wants is being used by a Wi-Fi router: It jumps to a new frequency. But Bluetooth’s frequency hopping works, in part, because Wi-Fi acts in a predictable way (that is, it broadcasts on a specific frequency and won’t change that behavior). However, in our competition, each team’s radios behave very differently and not at all predictably, making a sense-and-avoid strategy, well, senseless.
Instead, we’re seeing that a better approach is to predict what the spectrum will look like in the future. Then, a radio could use those predictions to decide which frequencies might open up—even if only for a moment or two, just enough to push through even a small amount of data. More precise predictions will allow collaborating radios to capitalize on every opportunity to transmit more data, without interfering by grabbing for the same frequency at the same time. Now our hope is that second-wave AIs can learn to predict the spectrum environment with enough precision to not let a single hertz go to waste.
If DARPA Has Its Way, AI Will Rule the Wireless Spectrum [Paul Tilghman/IEEE Spectrum]
(via Four Short Links)