Abstract The recent advances in renewable energy sources impose a greater need for smart grid. However, the process of power generation, distribution and consumption across smart grids are highly complex. Conventional systems are more prone to various security attacks and become a single point of failure during many instances. This paper proposes a blockchain-based decentralised multiparty learning system to ensure the stability of the smart grid while enhancing security and efficiency measures through blockchain. Simulations were conducted using a power grid dataset from Kaggle, and observations were made considering various factors. From the experiment, it was noted that the proposed approach takes an average of 25 ms to read the data across the blocks and approximately 4 s to generate a new block. Moreover, concerning the addition of a higher number of intelligent terminals, the proposed approach consumes only 70% of the energy required by conventional methods to perform the task. The prediction and classification accuracy of the proposed system is also analysed, showing a measure of 98% accuracy.
Tamizharasi et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: