Deep generative modeling for probabilistic forecasting in power systems
- URL: http://arxiv.org/abs/2106.09370v1
- Date: Thu, 17 Jun 2021 10:41:57 GMT
- Title: Deep generative modeling for probabilistic forecasting in power systems
- Authors: Jonathan Dumas and Antoine Wehenkel Damien Lanaspeze and Bertrand
Corn\'elusse and Antonio Sutera
- Abstract summary: This study uses a recent deep learning technique, the normalizing flows, to produce accurate probabilistic forecasts.
We show that our methodology is competitive with other state-of-the-art deep learning generative models.
- Score: 34.70329820717658
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Greater direct electrification of end-use sectors with a higher share of
renewables is one of the pillars to power a carbon-neutral society by 2050.
This study uses a recent deep learning technique, the normalizing flows, to
produce accurate probabilistic forecasts that are crucial for decision-makers
to face the new challenges in power systems applications. Through comprehensive
empirical evaluations using the open data of the Global Energy Forecasting
Competition 2014, we demonstrate that our methodology is competitive with other
state-of-the-art deep learning generative models: generative adversarial
networks and variational autoencoders. The models producing weather-based wind,
solar power, and load scenarios are properly compared both in terms of forecast
value, by considering the case study of an energy retailer, and quality using
several complementary metrics.
Related papers
- Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting.
Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server.
We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
arXiv Detail & Related papers (2024-11-24T04:56:45Z) - A Survey of AI-Powered Mini-Grid Solutions for a Sustainable Future in Rural Communities [0.18783379094746652]
This paper reviews various forecasting models, including statistical methods, machine learning algorithms, and hybrid approaches.
It explores public datasets and tools such as Prophet, NeuralProphet, and N-BEATS for model implementation and validation.
The survey concludes with recommendations for future research, addressing challenges in model adaptation and optimisation for real-world applications.
arXiv Detail & Related papers (2024-07-17T20:23:38Z) - Deep Generative Methods for Producing Forecast Trajectories in Power
Systems [0.0]
Transport System Operators (TSOs) must conduct analyses to simulate the future functioning of power systems.
These simulations are used as inputs in decision-making processes.
arXiv Detail & Related papers (2023-09-26T14:43:01Z) - Benchmarks and Custom Package for Energy Forecasting [55.460452605056894]
Energy forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch.
In this paper, we collected large-scale load datasets and released a new renewable energy dataset.
We conducted extensive experiments with 21 forecasting methods in these energy datasets at different levels under 11 evaluation metrics.
arXiv Detail & Related papers (2023-07-14T06:50:02Z) - MATNet: Multi-Level Fusion Transformer-Based Model for Day-Ahead PV
Generation Forecasting [0.47518865271427785]
MATNet is a novel self-attention transformer-based architecture for PV power generation forecasting.
It consists of a hybrid approach that combines the AI paradigm with the prior physical knowledge of PV power generation.
Results show that our proposed architecture significantly outperforms the current state-of-the-art methods.
arXiv Detail & Related papers (2023-06-17T14:03:09Z) - Denoising diffusion probabilistic models for probabilistic energy
forecasting [0.0]
This paper presents a promising deep learning generative approach called denoising diffusion probabilistic models.
It is a class of latent variable models which have recently demonstrated impressive results in the computer vision community.
We propose the first implementation of this model for energy forecasting using the open data of the Global Energy Forecasting Competition 2014.
arXiv Detail & Related papers (2022-12-06T13:50:17Z) - Machine learning applications for electricity market agent-based models:
A systematic literature review [68.8204255655161]
Agent-based simulations are used to better understand the dynamics of the electricity market.
Agent-based models provide the opportunity to integrate machine learning and artificial intelligence.
We review 55 papers published between 2016 and 2021 which focus on machine learning applied to agent-based electricity market models.
arXiv Detail & Related papers (2022-06-05T14:52:26Z) - Validation Methods for Energy Time Series Scenarios from Deep Generative
Models [55.41644538483948]
A popular scenario generation approach uses deep generative models (DGM) that allow scenario generation without prior assumptions about the data distribution.
We provide a critical assessment of the currently used validation methods in the energy scenario generation literature.
We apply the four validation methods to both the historical and the generated data and discuss the interpretation of validation results as well as common mistakes, pitfalls, and limitations of the validation methods.
arXiv Detail & Related papers (2021-10-27T14:14:25Z) - Probabilistic Solar Power Forecasting: Long Short-Term Memory Network vs
Simpler Approaches [0.2867517731896504]
Article presents a comparison between a long short-term memory neural network and other more simple approaches.
The paper makes use of an open-source dataset provided during the Global Energy Forecasting Competition of 2014.
arXiv Detail & Related papers (2021-01-20T18:13:07Z) - Towards a Peer-to-Peer Energy Market: an Overview [68.8204255655161]
This work focuses on the electric power market, comparing the status quo with the recent trend towards the increase in distributed self-generation capabilities by prosumers.
We introduce a potential multi-layered architecture for a Peer-to-Peer (P2P) energy market, discussing the fundamental aspects of local production and local consumption as part of a microgrid.
To give a full picture to the reader, we also scrutinise relevant elements of energy trading, such as Smart Contract and grid stability.
arXiv Detail & Related papers (2020-03-02T20:32:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.