SumComp coding for digital OTA computation of nomographic functions achieves ~10 dB better normalized MSE than analog and ChannelComp baselines for arithmetic and geometric means in low-noise regimes.
Over-the-air Function Computation in Sensor Networks
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Many sensor applications are interested in computing a function over measurements (e.g., sum, average, max) as opposed to collecting all sensor data. Today, such data aggregation is done in a cluster-head. Sensor nodes transmit their values sequentially to a cluster-head node, which calculates the aggregation function and forwards it to the base station. In contrast, this paper explores the possibility of computing a desired function over the air. We devise a solution that enables sensors to transmit coherently over the wireless medium so that the cluster-head directly receives the value of the desired function. We present analysis and preliminary results that demonstrate that such a design yield a large improvement in network throughput.
fields
cs.IT 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SumComp: Coding for Digital Over-the-Air Computation via the Ring of Integers
SumComp coding for digital OTA computation of nomographic functions achieves ~10 dB better normalized MSE than analog and ChannelComp baselines for arithmetic and geometric means in low-noise regimes.