A meteorological big data-driven method for generating chaotic time-series curves of power supply loads for wind-solar-storage hybrid systems

The wind-solar-storage hybrid system represents an efficient and clean energy supply mode. However, its power supply load is influenced by multiple factors and exhibits complex chaotic time-series characteristics, which pose significant challenges to system operation scheduling and load forecasting. To address this issue, this paper proposes a method for generating chaotic time-series curves of the power supply load in such hybrid systems based on meteorological big data. Specifically, the empirical mode decomposition (EMD) technique is employed to decompose the load sequence into intrinsic mode functions (IMFs) with distinct scale characteristics, while the collected meteorological big data are subjected to dimensionality reduction. Subsequently, the chaotic time-series phase-space reconstruction method is applied to reconstruct in real time the various IMF components and the reduced meteorological data, thereby revealing the correlations between each meteorological factor and each IMF component. On the basis of these correlations, the chaotic time-series curve of the power supply load is generated using a method grounded in the maximum Lyapunov exponent. Experimental results show that the proposed approach exhibits strong capability in decomposing the load sequence and reducing meteorological data dimensionality. Moreover, it can effectively generate chaotic time-series curves of the power supply load for the hybrid system under cloudy weather conditions, driven by big data, achieving favorable application outcomes.