Pconvlstm: an effective parallel convlstm-based model for short-term electricity load forecasting

HIGHLIGHTS

• What: This work examines different encoding techniques such as Gramian angular field, Markov transition field, and Recurrent plot. Ablation experiments are carried out to determine the implications for the proposed multi-input P-ConvLSTM model. The aim is to determine the significance of using features other than the load feature, and the second objective is to determine whether splitting features into individual inputs profoundly impacts the proposed model`s performance. The authors assess the variant of the proposed model that utilized the load feature as the only input.
• Who: Forecasting et al. from the Manipur . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.