There are 4 repositories under load-forecasting topic.
使用bp神经网络预测电力负荷,使用小型数据集,通过一个简单的例子。Using BPNN to predict power load, using small data set, a simple example.
Project to explore & optimize dispatch of a commercial-scale battery storage system
The work develops a multi-step time series load forecasting model that predicts daily power consumption for the upcoming week based on historic daily data of consumption at a university campus.
Load Forecasting with MATLAB (ANN)
A Moroccan Buildings’ Electricity Consumption Dataset. MORED is made available by TICLab of the International University of Rabat (UIR), and the data collection was carried out as part of PVBuild research project, coordinated by Prof. Mounir Ghogho and funded by the United States Agency for International Development (USAID).
Source code for our ICCEP paper "Secure short-term load forecasting for smart grids with transformer-based federated learning".
load point forecast
使用灰色系统理论做负荷预测。Using Grey System Theory to Make Load Forecasting
Enhanced spatio-temporal electric load forecasts with less data using active deep learning
Contains the code for the paper "Multi-Horizon Short-Term Load Forecasting Using Hybrid of LSTM and Modified Split Convolution"
This repo contains data and code for Task-Aware Machine Unlearning with Application to Load Forecasting.
Source code for our preprint paper "Advancing Accuracy in Load Forecasting using Mixture-ofExperts and Federated Learning".
T-DPnet-Transformer-based-deep-Probabilistic-network-for-load-forecasting
Research done by me and @mennanawar on load forecasting using the ASHRAE building dataset provided by kaggle.
A black box data driven model that considers the characterization and prediction of heat load in buildings connected to District Heating by using smart heat meters
Project uses machine learning to predict energy load in Spanish cities based on weather data, aiming to optimize grid management and renewable energy integration. It tackles challenges in data cleaning, model selection, and feature engineering, demonstrating ML's superiority in handling complex relationships and improving forecasting accuracy
Grid-Aware STGNN for Multi-horizon Power Load Forecasting
This is the official repo for the paper E2E-AT: A Unified Framework for Tackling Uncertainty in Task-aware End-to-end Learning, to be appeared in AAAI-24.
In this project, we've tried applying various DNNs to the problem of non-intrusive load monitoring (NILM) and compared their results for various appliances using the REDD dataset. We took a sliding window approach in hopes that we'll be able to achieve real time disaggregation with further tuning and testing. We compare the disaggregated energy consumption results based on MSE, MAE, Relative Error and F1 Score.
This repository is for load forecasting using machine learning.
Studied the impact of adversarial attacks on RNN Based load forecasting model.
Implementation of two different models (TF2/Keras) from literature and a custom model for day-ahead load forecasting (short term load forecasting) on two different datasets.
This is part of the research work based on Smart Grid Cyber Threat Intelligence (SG-CTI). The research paper of this work is under review in the journal. Detailed information about this work will be provided after it is published in the journal. Research Grant: GUP-2023-010 (supported by the Ministry of Higher Education, Malaysia)
Power Systems Foundation Models
Exploring Different Personalization Mechanisms for Federated Time Series Forecasting. Paper DOI: 10.1109/JIOT.2025.3580378
Probabilistic building load forecasting (Q10/Q50/Q90) + risk-aware supervisory control using Patch Transformer (QR-PatchTST)
Prediction of kW 48 hours ahead. Smart meter reading, real world untouched data of client.
A Load Forecasting Prediction System with Frontend
This repository is part of my thesis on short-term load forecasting using LSTM neural networks.
Electricity Demand Forecasting for the Luzon Power System
BDRC, 台灣工業用電預測
Data driven load forecasting using energy generation and weather conditions
The project focuses on predicting electricity load demand using the ARIMA model, a widely used time series forecasting technique.