Predicting Bitcoin Mining Energy Consumption Using Machine Learning: A Case for k-Nearest Neighbors Regression DOI Open Access
Nazmiye Eligüzel, Sena Aydoğan

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, Journal Year: 2025, Volume and Issue: 14(1), P. 561 - 582

Published: March 26, 2025

The energy consumption of Bitcoin mining has emerged as a critical topic in cryptocurrency research, influenced by the significant environmental and economic impacts blockchain activities. This study examines with dataset that includes essential variables such overall hash rate, network difficulty, daily confirmed transactions, mempool size, average block output. A new indicator is proposed to contribute research domain. better accurately reflects dynamics utilization. Various machine learning models, Random Forest, Gradient Boosting, Support Vector Regression, Multi-layer Perceptron, are evaluated, particular emphasis on k-Nearest Neighbors Regression (k-NNR). k-NNR model surpassed all other 𝑅2 value 0.80427 Mean Squared Error (MSE) 0.00441, indicating its high prediction accuracy. Analysis feature importance indicated production size determinants use. findings underscore efficacy modeling, offering insights into Bitcoin's establishing foundation for more energy-efficient systems.

Language: Английский

Predicting Bitcoin Mining Energy Consumption Using Machine Learning: A Case for k-Nearest Neighbors Regression DOI Open Access
Nazmiye Eligüzel, Sena Aydoğan

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, Journal Year: 2025, Volume and Issue: 14(1), P. 561 - 582

Published: March 26, 2025

The energy consumption of Bitcoin mining has emerged as a critical topic in cryptocurrency research, influenced by the significant environmental and economic impacts blockchain activities. This study examines with dataset that includes essential variables such overall hash rate, network difficulty, daily confirmed transactions, mempool size, average block output. A new indicator is proposed to contribute research domain. better accurately reflects dynamics utilization. Various machine learning models, Random Forest, Gradient Boosting, Support Vector Regression, Multi-layer Perceptron, are evaluated, particular emphasis on k-Nearest Neighbors Regression (k-NNR). k-NNR model surpassed all other 𝑅2 value 0.80427 Mean Squared Error (MSE) 0.00441, indicating its high prediction accuracy. Analysis feature importance indicated production size determinants use. findings underscore efficacy modeling, offering insights into Bitcoin's establishing foundation for more energy-efficient systems.

Language: Английский

Citations

0