To address the issue of declining prediction accuracy caused by the lack of data in newly constructed wind and solar power stations, this paper introduces a transfer learning-based forecasting approach for wind and photovoltaic power. The method incorporates sensitive meteorological feature selection and utilizes a Temporal Convolutional Network–Attention–Long Short-Term Memory (TCN-ATT-LSTM) model. Spearman’s rank correlation, mutual information entropy, and Pearson correlation are employed to investigate the relationship between meteorological features and power output. Through evidence theory, meteorological features with a cumulative contribution exceeding 85% are selected as inputs for the wind and solar power forecasting model. The TCN-ATT-LSTM network is pre-trained to extract common knowledge, and transfer learning is applied to fine-tune (FT) the model through network parameter adjustments. This enables the adaptive model to be quickly constructed for target wind and solar power stations with limited data, improving the prediction accuracy. Finally, the effectiveness of the proposed method is validated through its application to data from a projected wind and solar power station planned for a region in northwestern China. The proposed method not only enhances forecasting accuracy for emerging wind and solar power stations with limited data but also has significant implications for the renewable energy industry.
In response to the complexity and high volatility of original load data affecting the accuracy of load forecasting, a combined method for short-term load forecasting considering the characteristics of components of seasonal and trend decomposition using local regression (STL) is proposed. The original load data are decomposed into a trend component, seasonal component, and residual component using STL. Then, considering the characteristics of each component, a long short-term memory (LSTM) neural network, a convolutional neural network (CNN), and Gaussian process regression (GPR) are used to predict the trend component, seasonal component, and residual component, respectively. The final outcome of the load forecasting is obtained by summing the forecasted results of each individual component. A specific case study is conducted to compare the proposed combined method with LSTM, CNN, GPR, STL-LSTM, STL-CNN, and STL-GPR prediction methods. Through comparison, the proposed combined method exhibits lower errors and higher accuracy, demonstrating the effectiveness of this method.
The proposed approach involves a method of joint optimization configuration for wind–solar–thermal-storage (WSTS) power energy bases utilizing a dynamic inertia weight chaotic particle swarm optimization (DIWCPSO) algorithm. The power generated from the combination of wind and solar energy is analyzed quantitatively by using the average complementarity index (ACI) to determine the optimal ratio of wind and solar installations. We constructed a multi-objective optimization configuration model for the WSTS power generation systems, considering the equivalent annual income and the optimal energy consumption level as objective functions of the system. We solved the model using the chaotic particle swarm optimization algorithm with linearly decreasing dynamic inertia weight. To validate the effectiveness of the proposed approach, we conducted a simulation using the 2030 power energy base planning data of a particular region in Inner Mongolia. The results demonstrate that the proposed method significantly improves the annual income, enhances the consumption of wind–solar energy, and boosts the power transmission capacity of the system.
To address the issue of premature wear and tear in wind turbines due to uneven fatigue load distribution within wind farms, this study proposes an optimal active power allocation method that considers unit fatigue loads. First, the fatigue load expressions for wind turbine shafts and tower systems with two degrees of freedom are derived, and a quantitative relationship between turbine fatigue load and active power output variations is established. Subsequently, the optimization objective is set as minimizing the total fatigue load in the wind farm during frequency regulation. This model incorporates the fatigue load differences among different turbines and ensures that the sum of the power adjustments across all turbines meets the frequency regulation power demand, resulting in an active power allocation model. To solve this optimization model, an improved Firefly Algorithm (IFA), integrating Logistic mapping and an adaptive weight strategy, is employed. Aligned with the recommended goals of sustainable development, this approach not only reduces fatigue loads, enhancing the lifespan and efficiency of wind turbines, but also ensures that the wind farm retains strong frequency regulation performance. By optimizing turbine performance and promoting a more balanced load distribution, the proposed method significantly contributes to the overall reliability and economic sustainability of renewable energy systems. Finally, a case study system consisting of nine 5 MW turbines is established to validate the proposed method, demonstrating its ability to evenly distribute the fatigue load across turbines while effectively tracking higher-level dispatch commands and reducing the same fatigue loads.
During the peak load period, there is a high level of imbalance between power supply and demand, which has become a critical challenge, leading to higher operational costs for power grids. To improve the accuracy of peak load forecasting, this study introduces a novel approach based on Extreme Gradient Boosting Trees (XGBoost) and Multiple Linear Regression (MLR) for daily peak load prediction. The proposed methodology first employs an improved version of the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm to decompose the raw load data, subsequently reconstructing each Intrinsic Mode Function (IMF) into high-frequency and stationary components. For the high-frequency components, XGBoost serves as the base predictor within a Bagging-based ensemble structure, while the Sparrow Search Algorithm (SSA) is employed to optimize hyperparameters automatically, ensuring efficient learning and accurate representation of complex peak load fluctuations. Meanwhile, the stationary components are modeled using MLR to provide fast and reliable estimations. The proposed framework was evaluated using actual daily peak load data from Western Inner Mongolia, China. The results indicate that the proposed method successfully captures the peak characteristics of the power grid, delivering both robust and precise predictions. When compared to the baseline model, the RMSE and MAPE are reduced by 54.4% and 87.3%, respectively, underscoring its significant potential for practical applications in power system operation and planning.