Efficient Miner Selection in Blockchain Based on Predicted Transaction Time

Abstract

Blockchain’s decentralized, transparent, and immutable nature has revolutionized digital transactions by removing the need for central authorities. Ethereum stands out among blockchain platforms for facilitating secure peer-to-peer transactions via smart contracts. Despite its transformative potential, blockchain faces challenges, particularly with the PoW consensus algorithm, which demands high energy consumption and raises centralization concerns. This affects the scalability of Blockchain by reducing the throughput. This paper explores machine learning (ML) integration to address these challenges, specifically focusing on optimizing miner selection in the Ethereum blockchain based on predicted transaction times. The study compares the performance of various machine learning models, including ElasticNet, Lasso Regression, Multilayer Perceptron (MLP) Regression in optimizing miner selection for reduced transaction times on the Ethereum blockchain. This study advances the ongoing research on integrating machine learning with blockchain to address the shortcomings of traditional Proof of Work (PoW) systems. It emphasizes the potential of machine learning to propel future innovations in blockchain technology.