Wind speed interval prediction plays an increasingly important role in wind power production. The intermittent and fluctuant characteristics of wind power make high-quality prediction interval (PI) challenging. In this paper, a novel hybrid model based on gated recurrent unit (GRU) neural network and variational mode decomposition (VMD) is proposed for the wind speed interval prediction. At first, VMD is employed to decompose the complex wind speed time series into simplified modes, interval prediction model (IPM) and point prediction model (PPM) based on GRU are designed to conduct interval prediction on primary mode and point prediction on the rest modes before a composition and construction of the prediction interval. Then, error prediction model based on GRU is proposed to enhance the model performance by error correction. Eight cases from two wind fields are used to test and verify the proposed method. The results indicate that the proposed method is a high qualified method which is in possession of much higher PI coverage probability and narrower PI width.

Wind power interval prediction (WPIP) plays an increasingly important role in evaluations of the uncertainty of wind power and becomes necessary for managing and planning power systems. However, the intermittent and fluctuating characteristics of wind power mean that high-quality prediction intervals (PIs) production is a challenging problem. In this article, we propose a novel hybrid model for the WPIP based on the gated recurrent unit (GRU) neural networks and variational mode decomposition (VMD). In the hybrid model, VMD is employed to decompose complex wind power data into simplified modes. Basic GRU prediction models, comprising a GRU input layer, multiple fully connected layers, and a rank-ordered terminal layer, are then trained for each mode to produce PIs, which are combined to obtain final PIs. In addition, an adaptive optimization method based on constructed intervals (CIs) is proposed to build high-quality training labels for supervised learning with the hybrid model. Several numerical experiments were implemented to validate the effectiveness of the proposed method. The results indicate that the proposed method performs better than the traditional interval prediction models with much higher quality PIs, and it requires less training time.

In this paper, a novel energy storage method based on pumped hydropower energy storage (PHES) for a renewable energy integrated micro-grid (REMG) is proposed, and the load frequency control (LFC) for the system is studied. In a typical REMG, micro pumped storage units (MPSUs) are built that rely on a tall building to convert energy by pumping water up to store energy and releasing the stored water to generate energy. Because of the fluctuation of RE and the perturbation of the load demand, frequency deviation and tie-line power interchange are inevitable. In this study, the LFC controller optimization problem for the REMG is investigated, and the optimal controllers for multi-areas in the REMG are designed. To solve the optimization problem of LFC, a novel meta-heuristic called Artificial Sheep Algorithm (ASA) is applied in the task of LFC optimization. In the experiments, RE scenarios of different seasons, the impact of PHES and the control robustness are studied. The results not only prove the feasibility of the proposed REMG but also show the effectiveness of the optimized controllers in maintaining frequency stability under various conditions.