Carbon-Neutral ESG Method Based on PV Energy Generation Prediction Model in Buildings for EV Charging Platform

Energy prediction models and platforms are being developed to achieve carbon-neutral ESG, transition buildings to renewable energy, and supply sustainable energy to EV charging infrastructure. Despite numerous studies on machine learning (ML)-based prediction models for photovoltaic (PV) energy, integrating models with carbon emission analysis and an electric vehicle (EV) charging platform remains challenging. To overcome this, we propose a building-specific long short_term memory (LSTM) prediction model for PV energy supply. This model simulates the integration of EV charging platforms and offer solutions for carbon reduction. Integrating a PV energy prediction model within buildings and EV charging platforms using ICT is crucial to achieve renewable energy transition and carbon neutrality. The ML model uses data from various perspectives to derive operational strategies for energy supply to the grid. Additionally, simulations explore the integration of PV-EV charging infrastructure, EV charging control based on energy, and mechanisms for sharing energy, promoting eco-friendly charging. By comparing carbon emissions from fossil-fuel-based sources with PV energy sources, we analyze the reduction in carbon emission effects, providing a comprehensive understanding of carbon reduction and energy transition through energy prediction. In the future, we aim to secure economic viability in the building energy infrastructure market and establish a carbon-neutral city by providing a stable energy supply to buildings and EV charging infrastructure. Through ongoing research on specialized models tailored to the unique characteristics of energy domains within buildings, we aim to contribute to the resolution of inter-regional energy supply challenges and the achievement of carbon reduction.

Cette oeuvre a été publiée sous la license Creative Commons Attribution 4.0 (CC-BY 4.0). Il est autorisé de partager et adapter l'oeuvre tant que l'auteur est crédité et la license est indiquée (avec le lien ci-dessus). Vous devez aussi indiquer si des changements on été fait vis-à-vis de l'original.