Enhancing photovoltaic power prediction using a CNN-LSTM-attention hybrid model with Bayesian hyperparameter optimization

Improving the accuracy of solar power forecasting is crucial to ensure grid stability,optimize solar power plant operations,and enhance grid dispatch efficiency.Although hybrid neural network models can effectively address the complexities of environmental data and power prediction uncertainties,challenges such as labor-intensive parameter adjustments and complex optimization processes persist.Thus,this study proposed a novel approach for solar power prediction using a hybrid model(CNN-LSTM-attention)that combines a convolutional neural network(CNN),long short-term memory(LSTM),and attention mechanisms.The model incorporates Bayesian optimization to refine the parameters and enhance the prediction accuracy.To prepare high-quality training data,the solar power data were first preprocessed,including feature selection,data cleaning,imputation,and smoothing.The processed data were then used to train a hybrid model based on the CNN-LSTM-attention architecture,followed by hyperparameter optimization employing Bayesian methods.The experimental results indicated that within acceptable model training times,the CNN-LSTM-attention model outperformed the LSTM,GRU,CNN-LSTM,CNN-LSTM with autoencoders,and parallel CNN-LSTM attention models.Furthermore,following Bayesian optimization,the optimized model demonstrated significantly reduced prediction errors during periods of data volatility compared to the original model,as evidenced by MRE evaluations.This highlights the clear advantage of the optimized model in forecasting fluctuating data.

Numerical Simulation Analysis of the Transformer Fire Extinguishing Process with a High-Pressure Water Mist System under Different Conditions

To thoroughly study the extinguishing effect of a high-pressure water mist fire extinguishing system when a transformer fire occurs,a 3D experimental model of a transformer is established in this work by employing Fire Dynamics Simulator(FDS)software.More specifically,by setting different parameters,the process of the highpressure water mist fire extinguishing system with the presence of both diverse ambient temperatures and water mist sprinkler laying conditions is simulated.In addition,the fire extinguishing effect of the employed high-pressure water mist system with the implementation of different strategies is systematically analyzed.The extracted results show that a fire source farther away fromthe centerline leads to a lower local temperature distribution.In addition,as the ambient temperature increases,the temperature above the fire source decreases,while the temperature and the concentrationof theupperflue gas layer bothdecrease.Interestingly,after thehigh-pressurewatermist sprinkler begins to operate,both the temperature distribution above the fire source and the concentration of the flue gas decrease,which indicates that the high-pressure water mist system plays the role of cooling and dust removal.By comparing various sprinkler laying methods,it is found that the lower sprinkler height has a better effect on the temperature above the fire source,the temperature of the upper flue gas layer,and the concentration of the flue gas.Moreover,when the sprinkler is spread over thewhole transformer,the cooling effect on both the temperature above the fire source and the temperature of the upper flue gas layer is good,whereas the change in the concentration of the flue gas above the fire source is not obvious compared to the case where the sprinkler is not fully spread.

Small-signal Stability Analysis and Improvement with Phase-shift Phase-locked Loop Based on Back Electromotive Force Observer for VSC-HVDC in Weak Grids

Voltage source converter based high-voltage direct current(VSC-HVDC)transmission technology has been extensively employed in power systems with a high penetration of renewable energy resources.However,connecting a voltage source converter(VSC)to an AC weak grid may cause the converter system to become unstable.In this paper,a phase-shift phaselocked loop(PS-PLL)is proposed wherein a back electromotive force(BEMF)observer is added to the conventional phaselocked loop(PLL).The BEMF observer is used to observe the voltage of the infinite grid in the stationaryαβframe,which avoids the problem of inaccurate observations of the grid voltage in the dq frame that are caused by the output phase angle errors of the PLL.The VSC using the PS-PLL can operate as if it is facing a strong grid,thus enhancing the stability of the VSC-HVDC system.The proposed PS-PLL only needs to be properly modified on the basis of a traditional PLL,which makes it easy to implement.In addition,because it is difficult to obtain the exact impedance of the grid,the influence of shortcircuit ratio(SCR)estimation errors on the performance of the PS-PLL is also studied.The effectiveness of the proposed PSPLL is verified by the small-signal stability analysis and timedomain simulation.

Characterization of focusing performance of spiral zone plates with fractal structure

We propose an efficient method of generating a vortex beam with multi-foci by using a fractal spiral zone plate(FSZP), which is designed by combining fractal structure with a spiral zone plate(SZP) in the squared radial coordinate.The theoretical analysis reveals that the number of foci that embed vortices is significantly increased as compared with that obtained by using a conventional SZP. Furthermore, the influence of topological charge on the intensity distribution in focal plane is also discussed in detail. For experimental investigation, an FSZP with topological charge p = 1 and 6.4 mm diameter is fabricated by using a photo-etching technique. The calibration indicates that the focusing performances of such a kind of zone plane(ZP) accord well with simulations, thereby providing its potential applications in multi-dimensional optical manipulation and optical imaging technology.