Data Forecasting with Application to Blockchain-based Local Energy Markets

Abstract

The creation of distributed energy generation that eliminates conventional differences between energy producers and consumers creates a new role called prosumer. This study aims at deploying a general ABM simulation framework to facilitate electricity exchange and demonstrate the functionality of blockchain. The simulation involved a Transactive Energy Distributed Energy Resource in a block chain dependent robust multi-agent structure. The LEM proposal based on blockchain uses auction system to balance supply and demand. Prediction error impacts on market outcomes were reduced by the LTSM model. The prediction procedure works on blockchain based LEM with adjusted prediction procedure. In ten real-world household power consumption datasets, the proposed hybrid deep learning neural network outperforms the state-of-the-art methods. To complement the proposed framework for actual application use, we additionally offer a k-step power consumption forecasting technique. This research offers a scalable environment for analyzing an energy blockchain from the perspective of Qatari society, finance, and technology.