Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network

Journal paper

Plain

Danila Valko and Daniel Kudenko (2024). Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network. Neural Computing and Applications, https://doi.org/10.1007/s00521-024-10588-2

BibTeX

@article{ValkoKudenko2024,
author = {Danila Valko and Daniel Kudenko},
title = {Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network},
journal = {Neural Computing and Applications},
year = {2024},
month = {12},
volume = {},
pages = {},
doi = {10.1007/s00521-024-10588-2},
}

Sources and References

• Native pathfinding algorithms are based on (Kumble & Roos, 2021); (Kumble, Epema & Roos, 2021); see also, GitHub.
• Carbon emissions were measured with CodeCarbon package.
• Experiments were run on a snapshot of the Lightning Network obtained from (Decker, 2020).
• The ForestFire sampling method was introduced in (Leskovec & Faloutsos, 2006); see also, GitHub.
• Note that one-shot path planning for 2D and 3D environments using fully convolutional neural network was introduced in (Kulvicius et al., 2020).