Corpus ID: 218870021

Short-term Load Forecasting Based on Hybrid Strategy Using Warm-start Gradient Tree Boosting

  title={Short-term Load Forecasting Based on Hybrid Strategy Using Warm-start Gradient Tree Boosting},
  author={Yuexin Zhang and J. Wang and S. S. Ge and L. Wang},
  • Yuexin Zhang, J. Wang, +1 author L. Wang
  • Published 2020
  • Mathematics, Computer Science, Engineering
  • ArXiv
  • A deep-learning based hybrid strategy for short-term load forecasting is presented. The strategy proposes a novel tree-based ensemble method Warm-start Gradient Tree Boosting (WGTB). Current strategies either ensemble submodels of a single type, which fail to take advantage of statistical strengths of different inference models. Or they simply sum the outputs from completely different inference models, which doesn't maximize the potential of ensemble. WGTB is thus proposed and tailored to the… CONTINUE READING


    Publications referenced by this paper.
    Long Short-Term Memory
    • 31,867
    • PDF
    Greedy function approximation: A gradient boosting machine.
    • 6,168
    • PDF
    Extreme Learning Machine for Regression and Multiclass Classification
    • 3,594
    • PDF
    Stochastic gradient boosting
    • 3,093
    • PDF
    Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
    • 3,239
    • PDF
    Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network
    • 341
    Electric load forecasting using an artificial neural network
    • 1,230
    • Highly Influential
    • PDF
    Short-term hourly load forecasting using time-series modeling with peak load estimation capability
    • 450