Marko Melnyk, Rihards Novickis. Real-time accelerator design for lossless compression of 1D data. 2025 International Conference on Networking, Sensing and Control (ICNSC), 8 pp. IEEE, 2025.
Bibtex citation:
Bibtex citation:
@inproceedings{20624_2025,
author = {Marko Melnyk and Rihards Novickis},
title = {Real-time accelerator design for lossless compression of 1D data},
journal = {2025 International Conference on Networking, Sensing and Control (ICNSC)},
pages = {8},
publisher = {IEEE},
year = {2025}
}
author = {Marko Melnyk and Rihards Novickis},
title = {Real-time accelerator design for lossless compression of 1D data},
journal = {2025 International Conference on Networking, Sensing and Control (ICNSC)},
pages = {8},
publisher = {IEEE},
year = {2025}
}
Abstract: The increasing number of Internet of Things devices puts a strain on the available wireless communication bandwidth and consequent power consumption. However, the modular System-on-Chip architecture is well-suited for on-the-fly data processing. Subsequently, this technical work proposes an accelerator-based solution for real-time compression and decompression of one-dimensional data, which consists of an encoder, decoder, predictor, variable-to-fixed and fixed-to-variable converter digital circuits. The solution is tested, validated and characterised with multiple real and synthetic datasets. The experiments demonstrate that using even the simplest predictor type can improve communication bandwidth by up to 49% in a serialised communication scenario.