A team of UConn engineers is developing an energy-efficient “smart sensor network” to track targets of interest, such as the proximity of enemy submarines or ships to Navy vessels.
The U.S. Navy currently uses underwater Intelligence, Surveillance, & Reconnaissance (ISR) sensor networks that run on full power, which can be a problem for long-term operations. The more accurate the sensor, the more power they consume.
The sensor networks currently being used could consist of several multi-modal sensor nodes, called sensor buoys, where each node acts independently and contains a diverse sensor suite, a data-processing unit, a transmitter and receiver, and a GPS device. The sensor suite can be composed of different types of sensors to detect and track targets, such as underwater microphones and active sonars.
Traditionally, these sensor nodes operate on full power, running all devices simultaneously, but the batteries that power them typically burn out within a few days of operation, just as cell phones suck up more power when running multiple operations. This causes sensing failures which, in turn, leads to holes in coverage and affects tracking performance.
This poses a challenge to the Navy, since it deploys thousands of acoustic sensor networks throughout the ocean, where battery replacement can be time-consuming or impossible.
To address the challenge, Shalabh Gupta, a UConn engineer and researcher at the National Institute for Undersea Vehicle Technology, devised the concept of a “smart sensor network” that is energy-efficient as well as resilient to failures.
In a smart sensor network, sensor nodes adapt their sensing modalities based on the information about the targets’ whereabouts. Thus, the nodes around the target, such as a ship or submarine, activate their high-power sensing devices to track the target accurately, pinpointing its location, velocity, and trajectory.
On the other hand, the nodes that are located farther away from the target cycle between low-power sensing and sleep states to minimize energy consumption while still remaining aware.
Thus, if a low-power sensor detects a target, the node switches to high-power sensing to track it. Similarly, the high-power sensing devices that are tracking the target predict the target’s trajectory and alert other sensors within range of the target’s path, so that they switch to high power. Once the target has passed outside of a sensor’s range, it reverts to low-power mode.
The smart sensor networks also provide resilience. If a few nodes in the network fail, then the nodes surrounding the hole in coverage formed by the failed nodes jointly optimize to expand their sensing ranges to cover the gap.
“These networks have to contain built-in, distributed intelligence,” says Gupta, an assistant professor of electrical and computer engineering.
His first research paper on the algorithm, coauthored by graduate student James Hare, was published online in IEEE Transactions on Cybernetics in August 2017.
With this advance, crews on ships and submarines will be able to track enemy watercraft with batteries that last about 60 to 90 percent longer, Gupta says.
Source: University of Connecticut