Short-term Wind Speed Forecasting for Power Integration in Smart Grids based on Hybrid LSSVM-SVMD Method

TL;DR

The paper tackles short-term wind speed forecasting for grid integration by proposing a hybrid SVMD-EBQPSO-LSSVM-LSTM framework. It decomposes wind speed series with successive variational mode decomposition (SVMD), optimizes LSSVM hyperparameters and mode windows via elitist-breeding quantum-behaved PSO (EBQPSO), and models the residual error with an LSTM, then aggregates mode predictions with the error sequence. The approach yields consistent improvements over benchmarks across two Ashegoda Wind Farm datasets, notably reducing $\text{RMSE}$ and $\text{MAE}$ by substantial margins, and demonstrates strong generalization and reduced error dispersion. The findings suggest practical benefits for wind-plant forecasting and grid operation, with open data/code available to facilitate replication and extension.

Abstract

Owing to its minimal pollution and efficient energy use, wind energy has become one of the most widely exploited renewable energy resources. The successful integration of wind power into the grid system is contingent upon accurate wind speed forecasting models. However, the task of wind speed forecasting is challenging due to the inherent intermittent characteristics of wind speed. In this paper, a hybrid machine learning approach is developed for predicting short-term wind speed. First, the wind data was decomposed into modal components using Successive Variational Mode Decomposition (SVMD). Then, each sub-signal was fitted into a Least Squares Support Vector Machines (LSSVM) model, with its hyperparameter optimized by a novel variant of Quantum-behaved Particle Swarm Optimization (QPSO), QPSO with elitist breeding (EBQPSO). Second, the residuals making up for the differences between the original wind series and the aggregate of the SVMD modes were modeled using long short-term model (LSTM). Then, the overall predicted values were computed using the aggregate of the LSSVM and the LSTM models. Finally, the performance of the proposed model was compared against state-of-the-art benchmark models for forecasting wind speed using two separate data sets collected from a local wind farm. Empirical results show significant improvement in performance by the proposed method, achieving a 1.21% to 32.76% reduction in root mean square error (RMSE) and a 2.05% to 40.75% reduction in mean average error (MAE) compared to the benchmark methods. The entire code implementation of this work is freely available in Github.

Figures (14)

• Figure 1: The flowchart for the SVMD method.
• Figure 2: Original wind speed series and the decomposed modes of SVMD (April Dataset).
• Figure 3: Original wind speed series and the decomposed modes of SVMD (May Dataset).
• Figure 4: LSTM architecture used for error sequence modeling.
• Figure 5: Applying the cut-and-paste transposon operator to LSSVM parameters and window size: (a) Same particle; (b) Different particles