Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study

Source

arXiv

arxiv.org/abs/2607.14024v1

Read the source

Source

Plain-Language Brief

Researchers propose a new method for feature selection in renewable energy prediction pipelines, called Cluster-based Sequential Feature Selection (CSFS). This method aims to address the gap in limited or unsystematic methods for feature selection in wind turbine power curve modeling and photovoltaic power prediction. The CSFS is model-agnostic, clustering-based, wrapper method that reduces computational cost by an average of 21% compared to existing feature selection techniques such as SFS.

What the Document Says

  • Rising global energy demand and climate change awareness are leading to a growing share of renewable energies.
  • Output of renewable energy sources is not consistent due to environmental conditions, requiring reliable prediction.
  • The authors conducted a literature review on wind turbine power curve modeling and synthesized findings for photovoltaic power prediction.
  • Limited or unsystematic methods exist for feature selection in both domains.
  • The researchers propose CSFS, a novel, model-agnostic, clustering-based wrapper method for efficient feature selection in renewable energy prediction pipelines.
  • CSFS is open-source on GitHub.
  • Empirical evaluation shows that wrapper-based methods provide better feature selections than filter-based methods and Random Forest's embedded feature importance.
  • CSFS achieves a predictive performance comparable to SFS while reducing computational cost by an average of 21%.

Key Concepts Mentioned

  • renewable energy
  • wind turbine power curve modeling
  • photovoltaic power prediction
  • feature selection
  • Cluster-based Sequential Feature Selection (CSFS)
  • wrapper method
  • computational cost

Claims Made by the Document

  • Rising global energy demand and climate change awareness are leading to a growing share of renewable energies.
  • Limited or unsystematic methods exist for feature selection in both wind turbine power curve modeling and photovoltaic power prediction.
  • The proposed CSFS method is more efficient than existing feature selection techniques such as SFS.
  • CSFS achieves a predictive performance comparable to SFS.

Evidence Used

  • Global energy demand and awareness of climate change are increasing.
  • Limited or unsystematic methods for feature selection are identified in the literature review.
  • The researchers provide an open-source implementation of CSFS on GitHub.
  • Empirical evaluation results show that wrapper-based methods perform better and CSFS reduces computational cost.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

With rising global energy demand and growing awareness of climate change and its impacts, the share of renewable energies in the global energy mix continues to grow. Unlike conventional power generation, the output of renewable energy sources cannot be controlled as consistently due to their dependence on environmental conditions. Therefore, reliable prediction of current and future energy production is essential. In this paper, we report findings from two structured literature reviews on real-world renewable energy prediction tasks: wind turbine power curve modeling and photovoltaic power prediction. For the former, we conducted a comprehensive literature review ourselves, while for the latter, we synthesize the key findings regarding frequently selected input features based on an existing survey. Across both domains, our analysis reveals that despite the large number of available monitoring and environmental variables, only limited or unsystematic methods for feature selection exist. To address this gap, we propose Cluster-based Sequential Feature Selection (CSFS), a novel, model-agnostic, clustering-based wrapper method for automatic, efficient, and reliable feature selection in renewable energy prediction pipelines. To support reproducibility and reuse, we provide an open-source implementation of CSFS on GitHub. We empirically evaluate the proposed approach on both use cases and compare it with established feature selection techniques such as wrapper-based sequential feature selection (SFS), filter-based methods, and Random Forest's embedded feature importance. The results show that the wrapper-based methods overall provide better-performing selections of features. CSFS achieves a predictive performance comparable to SFS while reducing computational cost by an average of 21%.