The growing integration of renewable energy sources into the power grid has introduced unprecedented uncertainty. Ensuring an appropriately scheduled reserve is essential to accommodate renewable energy's intermittent and volatile nature. This study introduces an innovative approach to ultra‐short‐term wind power forecasting, which relies on feature engineering and a hybrid model. The effectiveness of this proposed method is showcased through a case study involving a utility‐scale wind farm in Inner Mongolia, China. The findings indicate that the hybrid model, which combines the XGBoost (Extreme Gradient Boosting) algorithm and LSTM (Long Short‐Term Memory) network with KDJ (Stochastic Oscillator), and MACD (Moving Average Convergence and Divergence), achieves the highest forecasting accuracy. Specifically, the proposed model yields a normalized mean absolute error of 0.0396 for wind power forecasting. The modelling and forecasting process takes approximately 550 s. Furthermore, the suggested method is employed to predict wind power and wind speed for a wind farm in the USA. The experimental results consistently indicate that the proposed model maintains a dependable performance across various raw datasets; it is suitable for use in power system operations.
23 December 2024 in IEEE Transactions on Power Systems
The integration of electricity, heat, and gas networks introduces additional dimensions of flexibility, but the complex network topology makes power dispatch challenging. This paper presents a method for constructing a convex polyhedron to define the dynamic 3D flexible region (FR), which represents all possible power/heat/gas flow injection solutions that simultaneously satisfy operational constraints. First, a modified energy hub framework is proposed, and Monte Carlo simulations are used to sample feasible unit commitment and power dispatch scenarios. The Quick-Hull algorithm is applied to form a polyhedron that encloses all feasible solutions. Second, a point coordinate projection technique is employed to approximate the non-convex optimization problem to a convex one by shaping a projected 2D dispatchable plane. A case study using the modified IEEE33-NGS15-DHS15 and IEEE33-NGS25-DHS28 test systems demonstrates the efficiency and effectiveness of the proposed 3D geometry-based approach in solving joint scheduling problems across electricity, heat, and gas clusters.
This study introduces an ultra-short-term wind power prediction model with financial factors based on the LightGBM algorithm, which innovatively introduces the KDJ and MACD from financial time series data into the wind power time series data to address the challenges of existing prediction models due to the uncertainty factors such as wind speed and wind direction. The experiments show that the model has satisfactory prediction results and a short prediction time, which can contribute to developing grid dispatching plans and adjusting national strategies.