With the rapid development of intelligent sensing and data storage technologies, power systems have accumulated vast amounts of time-series data characterized by strong nonlinearity and high noise levels. To address the limitations of traditional prediction models in handling complex noise interference, which results in insufficient modeling capability and reduced accuracy, this paper proposes a variational autoencoder predictor integrated with normalizing flows. First, a gated recurrent unit (GRU)-based recurrent autoencoder framework is constructed to dynamically extract temporal features and filter noise through its time-dependent modeling capability. Then, a planar flow layer is introduced at the encoder output, transforming latent variables into complex distribution spaces via invertible map-pings to enhance the model’s adaptability to non-Gaussian noise. Experimental results demonstrate that the proposed method outperforms conventional models in noise suppression and dynamic adaptation, achieving a 27.7% reduction in mean squared error (MSE). The study confirms that the synergistic optimization of normalizing flows and variational autoencoders effectively resolves the nonlinear modeling challenges of power time-series data. This approach provides a new technical pathway for mid-to-long-term load forecasting, contributing to grid stability and optimized energy scheduling.