To address the low accuracy and poor reliability of short-term photovoltaic (PV) power forecasting under complex weather conditions, this study proposes a multi-strategy synergistic optimization framework for point-interval prediction. The methodology integrates similar day classification (SDC) via RDP-DTW-DBA-K-means, a hybrid BiTCN-MAOBiGRU-AM model with a mutation-aware mechanism, and Dream Optimization Algorithm (DOA) for global hyperparameter tuning of six key parameters. For interval prediction, an adaptive bandwidth kernel density estimation (ABKDE) dynamically adjusts bandwidth based on local error density and weather scenarios. Experiments using data from a Guangxi PV station demonstrate that the synergistic model reduces RMSE by 29.58% (cloudy) and 32.37% (overcast/rainy) versus the baseline, and cuts RMSE by 16.2–19.0% under abrupt weather events and 22.4–40.2% under non-ideal input data. At the 95% confidence level, ABKDE improves prediction interval coverage probability by 3.9–5.4 percentage points and reduces normalized average width by 20.8–23.6% compared to conventional KDE. The proposed framework significantly enhances prediction accuracy, robustness, and generalization, offering a reliable solution for PV power forecasting in highly variable meteorological scenarios.
Jian-Xin Zhang, Huan-Huan Yang, He Huang et al.· Energies· 0 citations
Next-generation green power direct-connection data centers face the dual challenges of the random nature of renewable energy output and short-term load fluctuations, which can cause significant power fluctuations at the grid connection point. This not only places enormous strain on grid operations but also poses security risks to the data centers themselves. Traditional scheduling paradigms often treat data centers as rigid loads, overlooking the inherent flexibility of computing tasks. In light of this, this paper proposes a coordinated optimization strategy for data center microgrids. First, a thermodynamic model incorporating temperature coupling is established to quantify the interactive energy consumption between IT systems and cooling systems, then a mixed-integer linear programming (MILP) model is constructed with the objective of minimizing operational costs, comprehensively considering grid power purchases, energy storage degradation, and penalty terms for workload shifting under time-of-use pricing. Simulation results indicate that, compared to traditional rigid operation modes, the proposed strategy can effectively shift peak loads, significantly reduce the curtailment rate of photovoltaic power, and demonstrate good economic performance.
Yucheng Zheng, G. I. Rashed, Xin-Fa Jiang et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
