Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach

Georgios Tsoumplekas, Christos L. Athanasiadis, Dimitrios I. Doukas, Antonios Chrysopoulos, Pericles A. Mitkas

TL;DR

This paper proposes adapting an established Model-Agnostic Meta-Learning algorithm for short-term load forecasting in the context of few-shot learning that can rapidly adapt and generalize within any unknown load time series of arbitrary length using only minimal training samples.

Abstract

Despite the rapid expansion of smart grids and large volumes of data at the individual consumer level, there are still various cases where adequate data collection to train accurate load forecasting models is challenging or even impossible. This paper proposes adapting an established model-agnostic meta-learning algorithm for short-term load forecasting in the context of few-shot learning. Specifically, the proposed method can rapidly adapt and generalize within any unknown load time series of arbitrary length using only minimal training samples. In this context, the meta-learning model learns an optimal set of initial parameters for a base-level learner recurrent neural network. The proposed model is evaluated using a dataset of historical load consumption data from real-world consumers. Despite the examined load series' short length, it produces accurate forecasts outperforming transfer learning and task-specific machine learning methods by $12.5\%$. To enhance robustness and fairness during model evaluation, a novel metric, mean average log percentage error, is proposed that alleviates the bias introduced by the commonly used MAPE metric. Finally, a series of studies to evaluate the model's robustness under different hyperparameters and time series lengths is also conducted, demonstrating that the proposed approach consistently outperforms all other models.

Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach

TL;DR

This paper proposes adapting an established Model-Agnostic Meta-Learning algorithm for short-term load forecasting in the context of few-shot learning that can rapidly adapt and generalize within any unknown load time series of arbitrary length using only minimal training samples.

Abstract

Despite the rapid expansion of smart grids and large volumes of data at the individual consumer level, there are still various cases where adequate data collection to train accurate load forecasting models is challenging or even impossible. This paper proposes adapting an established model-agnostic meta-learning algorithm for short-term load forecasting in the context of few-shot learning. Specifically, the proposed method can rapidly adapt and generalize within any unknown load time series of arbitrary length using only minimal training samples. In this context, the meta-learning model learns an optimal set of initial parameters for a base-level learner recurrent neural network. The proposed model is evaluated using a dataset of historical load consumption data from real-world consumers. Despite the examined load series' short length, it produces accurate forecasts outperforming transfer learning and task-specific machine learning methods by . To enhance robustness and fairness during model evaluation, a novel metric, mean average log percentage error, is proposed that alleviates the bias introduced by the commonly used MAPE metric. Finally, a series of studies to evaluate the model's robustness under different hyperparameters and time series lengths is also conducted, demonstrating that the proposed approach consistently outperforms all other models.
Paper Structure (14 sections, 12 equations, 5 figures, 4 tables, 1 algorithm)

This paper contains 14 sections, 12 equations, 5 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Load Forecasting
  4. Meta-Learning
  5. Few-Shot Load Forecasting
  6. Methodology
  7. Problem Formulation
  8. Proposed Method
  9. Experiments
  10. Experimental Setup
  11. Main Results
  12. Effect of support set size
  13. Ablation Study
  14. Conclusion

Figures (5)

  • Figure 1: Each task's support set has a variable size and non-overlapping samples, while the query set has a fixed size and overlapping samples with a 1-day shift.
  • Figure 2: Boxplots of the reported model performance metrics for the main experiment setting. The proposed model produces more accurate and robust results than the baseline methods.
  • Figure 3: Model forecasts on the first three days of a meta-test set task's query set.
  • Figure 4: MSE values for different numbers of support set gradient steps.
  • Figure 5: MSE values for different numbers of neurons per layer.