Search

Accurate prediction of renewable energy generation acts as a critical role which not only provides short-term power generation in the future, but also facilitates scheduling and pre-configuration of energy storage systems. More importantly, the power generation prediction is of great significance to the demand response management (DRM) of renewable energy to participate in the electricity spot market. Therefore, DRM helps improve the stability and reliability of renewable energy systems. This paper presents a novel prediction-smoothing based methodology to reduce and eliminate the influence caused by the uncertainty of renewable energy output. Firstly, the Whale Optimization Algorithm (WOA) is combined with Long Short-Term Memory (LSTM) to predict short-term wind power output. Then, the Hampel-Butterworth-SG filtering strategy with outlier regression and specific risk band elimination is introduced. After that, according to the short-term output forecast results, the scheduling and pre-configuration scheme of peak-filling type energy storage is developed. Finally, based on the predicted renewable energy output and electricity price, the dynamic changes of demand response (DR) are calculated based on Logistics function, optimistic response and pessimistic response factors. Through extensive case studies, it is demonstrated that the assessment deviations in different scenarios is less than 5%, which are 0.64% for Scenario 1 and 3.64% for Scenario 2, and no additional penalty is required at this time. In addition, the proposed Demand Response Load Adjustment Rate (DRLAR) help compare the differences between predicted and actual DR, which are DRLAR = 0.03% in Scenario 1 and DRLAR = 0.01% in Scenario 2. Users are able to adjust the DR dynamically according to the electricity price to realize the optimal scheduling of their renewable resources. The proposed methodology creates a special connection between DRM and renewable energy prediction, which provides a reliable reference for future work. [ABSTRACT FROM AUTHOR]

This paper investigates the multi‐dimensional non‐linear exponential smoothing prediction method under different weight coefficients, so as to realize the short‐term prediction of the original wind power output. Based on the current research on wind power fluctuation prediction, this paper firstly proposes a new multi‐dimensional nonlinear exponential smoothing prediction method. Based on different weight coefficients, the corresponding short‐term forecast volatility is obtained. Then, the wavelet packet decomposition method is used to further realize the secondary smoothing of the prediction wind power fluctuations. Hybrid energy storage system (HESS) plays an important role in wind power fluctuation suppression from different frequency bands. However, the traditional fixed frequency power allocation method significantly degrades the performance of the accuracy of the algorithm. Therefore, this paper proposes a frequency conversion entropy strategy, which combines energy value with wavelet packet decomposition. By calculating the energy components of different frequency bands, the fluctuation can be divided effectively. Finally, simulation and experiment discussions show that the proposed algorithm in this paper can realize the power allocation effectively compared to the traditional one. And it further verifies the feasibility and reliability of the strategy proposed in this work. [ABSTRACT FROM AUTHOR]

The proper integration of wind power-driven grids relies heavily on a reliable balance between electricity production and demand. Therefore, accurate prediction is essential for planning and efficient operation of wind power systems to ensure their continuous supply. However, increasingly severe power quality disturbance (PQD) constantly disturbs this equilibrium, which affects the accuracy of wind power prediction to a large extent. For this purpose, this paper developed a novel optimization methodology to improve wind power prediction accuracy considering micro PQD dimension reduction and elimination for wind-storage integrated systems. A novel idea has been presented in this optimization methodology to eliminate the barrier of PQD and wind power prediction. In the micro aspect, a PQD dimension reduction and elimination strategy based on dynamic mode decomposition (DMD) and Wiener Filter (WF) is proposed to eliminate the autonomy of PQD. This elimination of autonomy allows the WF to get a higher signal-to-noise ratio (SNR). In the macro aspect, this paper takes PQD of different complexity into full consideration, and compares their effects on improving wind power prediction accuracy based on deep learning-based approaches. Through the experimental verification, it is confirmed that the proposed DMD-WF optimization method has demonstrated an effective dimension reduction and elimination of PQD. Moreover, it is found that the proposed PQD optimization method contributes to improve the deep learning-based prediction accuracy when PQD is more complex. The proposed methodology creates a novel perspective to improve the short-term wind power prediction accuracy, which provides a theoretical and methodological guidance for future development of large-scale integrated wind-storage systems. • Development of a novel methodology of PQD optimization and wind power prediction. • A Wiener Filter and dimension reduction-based PQD optimization method is proposed. • WOA-Attention-LSTM is used to analyze forecast accuracy based on PQD optimization. [ABSTRACT FROM AUTHOR]

• A hierarchical approach is proposed considering quartile method for optimization. • Proposed CEEMDAN-DMD can regress the energy based on pre-set energy proportion. • Proposed hierarchical allocation strategy can be used for severe power volatility. The development of renewable energy dominated power system and the integration of large-scale wind-storage energy system are inevitable trends of the future society. This paper developed a new methodology of hierarchical power allocation strategy considering wind power fluctuation. A novel idea is presented that fully considers the fluctuation and energy proportion. Based on the Quartile Method (QM) and Hampel-Savitzky Golay (HSG) strategy, a layered-based method that considers the volatility interval to effectively overcome the limitations of a single strategy caused by severe volatility interval is proposed. Then, an improved power division method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Dynamic Mode Decomposition (DMD) is proposed where CEEMDAN is used to decompose the Intrinsic Mode Function (IMF) of the remaining fluctuations. Furthermore, according to the required setting of energy proportion, DMD strategy is used for power fitting of the hybrid energy storage system (HESS). Through experimental verification, the hierarchical strategy proposed in this paper can effectively reduce the probability of severe volatility interval or distortion interval and ensure the sequence in the ideal interval. Moreover, the proposed CEEMDAN-DMD strategy can realize the power division according to the energy proportion demand. In model verification, the volatility improvement ζλ 1 min = 85.4766%. Set the energy demand ≥ 80%, the fitting energy proportion accounts for 87.7533%, which outperforms the traditional power division method. In addition, it is demonstrated that the theoretical method proposed in this paper is reliable and promising. [ABSTRACT FROM AUTHOR]

• An application fusion method of improved smoothing and noise reduction strategy and start-stop energy storage element is proposed in this paper. • The WF-FSBL algorithm proposed in this paper can effectively reduce the influence of PQD in three-phase voltage. • The hybrid energy storage system with start-stop standby energy storage element adopted in this paper can be widely used in many fields. In order to realize effective noise reduction of wind power under the influence of complex power quality disturbance(PQD), an application fusion method of improved smoothing and noise reduction strategy and start-stop energy storage element is proposed in this paper. Firstly, the complex power quality disturbance is filtered and de-noised based on Wiener filtering(WF) algorithm to obtain stable disturbance output. Then, a filtering self-built library(FSBL) is established to perform parallel operations of multiple filtering algorithms and obtain the optimal output power according to the constraints of time scale. After that, a hybrid energy storage system(HESS) with start-stop standby energy storage element is proposed. According to the maximum entropy difference drop point and permutation entropy test, the start-stop instructions of standby energy storage elements can be achieved. Finally, the state of charge(SOC) is optimized according to fuzzy control constraints. In order to verify the effectiveness of the proposed method, this paper constructs the wind power output based on the hardware experimental platform. The power quality disturbance database is further constructed to verify and analyze power quality disturbance types from simple to complex. The results show that the proposed method is reliable. And the hybrid energy storage system with start-stop standby energy storage elements can be widely used in many fields and scenarios. [ABSTRACT FROM AUTHOR]