Answers are grounded in this paper and cite their sources.
This paper proposes a novel methodology for optimizing Long Short-Term Memory (LSTM) models on realworld power load data. The proposed methodology comprises two algorithms. The first determines the optimal look-back parameter for an LSTM model and the second algorithm optimizes the number of appliance groups included in LSTM models for predicting the power consumption. The proposed algorithms are evaluated on a real-world dataset and compared against existing methods. Results show that the proposed algorithms outperform existing methods in terms of prediction accuracy. The proposed framework can be useful for optimizing LSTM models in various real-world applications.
No takes yet. Share an insight, caveat, or question.
Pentsos et al. (2023) studied this question.