Net Load Forecasting

Net load forecasting aims to accurately predict the overall electricity demand on a power grid, considering both consumption and renewable energy generation, primarily to optimize grid reliability and energy trading. Current research emphasizes improving the accuracy and trustworthiness of these forecasts, particularly focusing on deep learning architectures like LSTMs, Temporal Convolutional Networks, and novel hybrid models incorporating autoencoders and kernel methods, to handle the increasing variability from sources like solar power. This work is crucial for efficient grid management, enabling better integration of renewable energy and more informed decision-making in energy markets. A key challenge is building trust in model predictions through improved visualization and analysis of model performance under diverse conditions, including extreme events.

Papers

July 31, 2024

Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models
Kaustav Bhattacharjee, Soumya Kundu, Indrasis Chakraborty, Aritra Dasgupta
Forecasting Model Visual Analytics Probabilistic Load Net Load Forecasting

November 10, 2023

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting
Kaustav Bhattacharjee, Soumya Kundu, Indrasis Chakraborty, Aritra Dasgupta
Forecasting Model Interventional Data Visual Analytics Tool Net Load Forecasting

February 25, 2023

In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance
Sotiris Pelekis, Evangelos Karakolis, Francisco Silva, Vasileios Schoinas, Spiros Mouzakitis, Georgios Kormpakis, Nuno Amaro, John Psarras
Long Short Term Memory Comparative Study Deep Learning Architecture Model Performance Load Forecasting Covid 19 Pandemic Short Term Load Forecasting Neural Forecasting Net Load Forecasting

March 5, 2022

KPF-AE-LSTM: A Deep Probabilistic Model for Net-Load Forecasting in High Solar Scenarios
Deepthi Sen, Indrasis Chakraborty, Soumya Kundu, Andrew P. Reiman, Ian Beil, Andy Eiden
Deep Learning Long Short Term Memory Deep Probabilistic Model Net Load Forecasting

Net Load Forecasting

Papers

Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance

KPF-AE-LSTM: A Deep Probabilistic Model for Net-Load Forecasting in High Solar Scenarios