Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction

• URL: http://arxiv.org/abs/2410.13303v1
• Date: Thu, 17 Oct 2024 08:00:36 GMT
• Title: Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction
• Authors: Chongyang Wan, Shunbo Lei, Yuan Luo,
• Abstract summary: We propose a novel approach called Hybrid Frequency Feature Enhancement Inverted Transformer (Hiformer) Hiformer integrates signal decomposition technology with weather feature extraction technique to enhance the modeling of correlations between meteorological conditions and wind power generation. Compared to the state-of-the-art methods, Hiformer: (i) can improve the prediction accuracy by up to 52.5%; and (ii) can reduce computational time by up to 68.5%.
• Score: 6.936415534357298
• License:
• Abstract: The increasing severity of climate change necessitates an urgent transition to renewable energy sources, making the large-scale adoption of wind energy crucial for mitigating environmental impact. However, the inherent uncertainty of wind power poses challenges for grid stability, underscoring the need for accurate wind energy prediction models to enable effective power system planning and operation. While many existing studies on wind power prediction focus on short-term forecasting, they often overlook the importance of long-term predictions. Long-term wind power forecasting is essential for effective power grid dispatch and market transactions, as it requires careful consideration of weather features such as wind speed and direction, which directly influence power output. Consequently, methods designed for short-term predictions may lead to inaccurate results and high computational costs in long-term settings. To adress these limitations, we propose a novel approach called Hybrid Frequency Feature Enhancement Inverted Transformer (Hiformer). Hiformer introduces a unique structure that integrates signal decomposition technology with weather feature extraction technique to enhance the modeling of correlations between meteorological conditions and wind power generation. Additionally, Hiformer employs an encoder-only architecture, which reduces the computational complexity associated with long-term wind power forecasting. Compared to the state-of-the-art methods, Hiformer: (i) can improve the prediction accuracy by up to 52.5\%; and (ii) can reduce computational time by up to 68.5\%.

Related papers

• Short-Term Photovoltaic Forecasting Model for Qualifying Uncertainty during Hazy Weather [9.367926898177815]
  We introduce a modified entropy to qualify uncertainty during hazy weather. clustering and attention mechanisms are employed to reduce computational costs and enhance forecasting accuracy. Experiments on two datasets related to hazy weather demonstrate that our model significantly improves forecasting accuracy.
  arXiv  Detail & Related papers  (2024-07-29T02:53:39Z)
• FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting [56.73502043159699]
  This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution. It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model. The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
  arXiv  Detail & Related papers  (2024-01-28T13:23:25Z)
• Global Transformer Architecture for Indoor Room Temperature Forecasting [49.32130498861987]
  This work presents a global Transformer architecture for indoor temperature forecasting in multi-room buildings. It aims at optimizing energy consumption and reducing greenhouse gas emissions associated with HVAC systems. Notably, this study is the first to apply a Transformer architecture for indoor temperature forecasting in multi-room buildings.
  arXiv  Detail & Related papers  (2023-10-31T14:09:32Z)
• Improving the forecast accuracy of wind power by leveraging multiple hierarchical structure [0.0]
  Recent advances in hierarchical forecasting through reconciliation have demonstrated a significant increase in the quality of wind energy forecasts for short-term periods. We leverage the cross-sectional and temporal hierarchical structure of turbines in wind farms and build cross-temporal hierarchies to investigate how integrated cross-sectional and temporal dimensions can add value to forecast accuracy in wind farms.
  arXiv  Detail & Related papers  (2023-08-07T11:02:44Z)
• Prediction of wind turbines power with physics-informed neural networks and evidential uncertainty quantification [2.126171264016785]
  We use physics-informed neural networks to reproduce historical data coming from 4 turbines in a wind farm. The developed models for regression of the power, torque, and power coefficient showed great accuracy for both real data and physical equations governing the system.
  arXiv  Detail & Related papers  (2023-07-27T07:58:38Z)
• 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)
• Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer [112.12271800369741]
  Wind power is attracting increasing attention around the world due to its renewable, pollution-free, and other advantages. Accurate wind power forecasting (WPF) can effectively reduce power fluctuations in power system operations. Existing methods are mainly designed for short-term predictions and lack effective spatial-temporal feature augmentation.
  arXiv  Detail & Related papers  (2023-05-30T04:03:15Z)
• Enhancing Short-Term Wind Speed Forecasting using Graph Attention and Frequency-Enhanced Mechanisms [17.901334082943077]
  GFST-WSF comprises a Transformer architecture for temporal feature extraction and a Graph Attention Network (GAT) for spatial feature extraction. GAT is specifically designed to capture the complex spatial dependencies among wind speed stations. Model time lag in wind speed correlation between adjacent wind farms caused by geographical factors.
  arXiv  Detail & Related papers  (2023-05-19T08:50:58Z)
• A novel automatic wind power prediction framework based on multi-time scale and temporal attention mechanisms [6.120692237856329]
  Wind power generation is characterized by volatility, intermittence, and randomness. Traditional wind power forecasting systems primarily focus on ultra-short-term or short-term forecasts. We propose an automatic framework capable of forecasting wind power across multi-time scale.
  arXiv  Detail & Related papers  (2023-02-02T17:03:08Z)
• Data-Driven Stochastic AC-OPF using Gaussian Processes [54.94701604030199]
  Integrating a significant amount of renewables into a power grid is probably the most a way to reduce carbon emissions from power grids slow down climate change. This paper presents an alternative data-driven approach based on the AC power flow equations that can incorporate uncertainty inputs. The GP approach learns a simple yet non-constrained data-driven approach to close this gap to the AC power flow equations.
  arXiv  Detail & Related papers  (2022-07-21T23:02:35Z)
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting [68.86835407617778]
  Autoformer is a novel decomposition architecture with an Auto-Correlation mechanism. In long-term forecasting, Autoformer yields state-of-the-art accuracy, with a relative improvement on six benchmarks.
  arXiv  Detail & Related papers  (2021-06-24T13:43:43Z)

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.