Logistic Modeling of Worldwide Energy Consumption and U.S. Oil Production Trends
The logistic function can be used to make reliable long-term forecasts for worldwide energy consumption and U.S. oil production, revealing insights into the evolving energy mix and the impact of new extraction methods like hydraulic fracturing.
Lightweight Federated Learning for Distributed Short-Term Load Forecasting
A lightweight federated learning framework can achieve comparable short-term load forecasting accuracy to state-of-the-art methods while preserving privacy and reducing computational overhead on smart meter devices.
MATNet: Multi-Level Fusion Transformer-Based Model for Day-Ahead PV Generation Forecasting
MATNet combines AI with physical knowledge for accurate day-ahead PV generation forecasting.
A Transformer Approach for Electricity Price Forecasting: Novel Insights and Results
The Transformer model outperforms traditional methods in electricity price forecasting, offering a reliable solution for sustainable power system operation.
Multivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows
Probabilistic forecasting of day-ahead electricity prices using normalizing flows yields accurate and high-quality scenarios.
MATNet: Multi-Level Fusion Transformer-Based Model for Day-Ahead PV Generation Forecasting
MATNet is a novel self-attention transformer-based architecture that significantly outperforms current state-of-the-art methods in day-ahead PV generation forecasting, demonstrating the potential to improve accuracy and facilitate the integration of PV energy into the power grid.
Addressing Missing Values in Probabilistic Wind Power Forecasting: A Generative Approach
The author argues that addressing missing values in wind power forecasting through a generative approach can lead to more accurate predictions and better performance compared to traditional methods.
A Novel Approach to Natural Gas Consumption Forecasting with Change Point Detection
The author introduces a novel approach to natural gas consumption forecasting using change point detection and continual learning capabilities.
