Short- Term Power Prediction Method for Photovoltaic Power Generation Based on Elman Neural Network for Aspen Swarm Optimization

Cai, Xinlei; Zhu, Jinzhou; Liu, Jiale; Meng, Zijie; Huo, Yujia; Yu, Yang

doi:10.1109/ceepe58418.2023.10166666

Cited by 5 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [24] used the IOIF-Elman neural network to predict air quality, addressing the shortcomings both slow convergence and falling into local minimums. Simliarly, these Elman neural networks implemented in [25][26][27][28] unveil excellent forecast performance. To optimize Elman neural networks, usually, other methods or other network structures are fused into them.…”

Section: Plos Onementioning

confidence: 99%

Regional economic forecast using Elman neural networks with wavelet function

Liang,

Zeng,

Dong

2024

PLoS ONE

View full text Add to dashboard Cite

Recently, the economy in Guangdong province has ranked first in the country, maintaining a good growth momentum. The prediction of Gross Domestic Product (GDP) for Guangdong province is an important issue. Through predicting the GDP, it is possible to analyze whether the economy in Guangdong province can maintain high-quality growth. Hence, to accurately forecast the economy in Guangdong, this paper proposed an Elman neural network combining with wavelet function. The wavelet function not only stimulates the forecast ability of Elman neural network, but also improves the convergence speed of Elman neural network. Experimental results indicate that our model has good forecast ability of regional economy, and the forecast accuracy reach 0.971. In terms of forecast precision and errors, our model defeats the competitors. Moreover, our model gains advanced forecast results to both individual economic indicator and multiple economic indicators. This means that our model is independently of specific scenarios in regional economic forecast. We also find that the investment in education has a major positive impact on regional economic development in Guangdong province, and the both surges positive correlation. Experimental results also show that our model does not exhibit exponential training time with the augmenting of data volume. Consequently, we propose that our model is suitable for the prediction of large-scale datasets. Additionally, we demonstrate that using wavelet function gains more profits than using complex network architectures in forecast accuracy and training cost. Moreover, using wavelet function can simplify the designs of complexity network architectures, reducing the training parameter of neural networks.

show abstract

Section: Plos Onementioning

confidence: 99%

Regional economic forecast using Elman neural networks with wavelet function

Liang,

Zeng,

Dong

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In order to solve the problem of the difficult location of shortcircuit faults in the 10 kV distribution network, Gao Yiwen et al ( 2022) [20] used the data of the short-circuit fault diagnosis feature database of the distribution network as the data input of the Elman neural network, and achieved fuzzy matching between multi-source data and the type and location of short-circuit faults in the distribution network through data training, and subsequently, verified the feasibility of this model with examples. Cui Xinyuan et al (2022) [21] took the "weather-power" sample data as the input data of the Elman neural network and conducted the training. Then, CGABC was used to optimize the connection weight of the Elman neural network.…”

Section: Introductionmentioning

confidence: 99%

A Model for Determining the Optimal Decommissioning Interval of Energy Equipment Based on the Whole Life Cycle Cost

Wang²,

Sun

et al. 2023

Sustainability

View full text Add to dashboard Cite

An appropriate technical overhaul strategy is very important for the development of enterprises. Most enterprises pay attention to the design life of the equipment, that is, the point when the equipment can no longer be used as stipulated by the manufacturer. However, in the later stage of the equipment, the operation and maintenance costs may be higher than the benefit of the equipment. Therefore, only the design life of the equipment may cause a waste of funds, so as to avoid the waste of funds, the enterprise’s strategy of technical reform and overhaul are optimized. This paper studies the optimal decommissioning life of the equipment (taking into account both the safety and economic life of the equipment), and selects the data of a 35 kV voltage transformer in a powerful enterprise. The enterprise may have problems with the data due to recording errors or loose classification. In order to analyze the decommissioning life of the equipment more accurately, it is necessary to first use t-distributed stochastic neighbor embedding (t-SNE) to reduce the data dimension and judge the data distribution. Then, density-based spatial clustering of applications with noise (DBSCAND) is used to screen the outliers of the data and mark the filtered abnormal data as a vacancy value. Then, random forest is used to fill the vacancy values of the data. Then, an Elman neural network is used for random simulation, and finally, the Fisher orderly segmentation is used to obtain the optimal retirement life interval of the equipment. The overall results show that the optimal decommissioning life range of the 35 kV voltage transformer of the enterprise is 31 to 41 years. In this paper, the decommissioning life range of equipment is scientifically calculated for enterprises, which makes up for the shortage of economic life. Moreover, considering the “economy” and “safety” of equipment comprehensively will be conducive to the formulation of technical reform and overhaul strategy.

show abstract

Research on UPQC harmonic control strategy based on optimized QPIR controller of beetle antennae search algorithm in microgrid

Fuyin,

Jian

2023

Electr Eng

View full text Add to dashboard Cite

It is di cult to achieve low-order harmonic tracking control without static difference when PI control is used in uni ed p-ower quality conditioner (UPQC). What's more, the traditional PI parameter trial method has the problems such as low accuracy and anti-interference to meet the needs of real time control.Aiming at this issue, this paper proposes a UPQC harmonic control method based on the beetle antennae search (BAS) algorithm to optimize the parameters of quasi-proportional integral resonance (QPIR) controller. The harmonic current is detected by the i p -i q method based on the instantaneous power theory, and the detected signal is input to the QPIR controller. The controller parameters are optimized by the BAS algorithm to improve the dynamic response performance and control accuracy of the UPQC. Then use the MATLAB/Simulink software platform to build UPQC simulation models for PV and wind microgrids.Finally, the simulation comparison is veri ed between the optimized QPIR controller strategy based on by BAS method and PI control strategy based on neural network algorithm (NNA)respectively. The results show that use QPIR controller optimized through the beetle antennae search (BAS) method is more accurate and resistant to interference. So, the proposed UPQC control strategy has innovation and feasibility, and it can be applied in the practical engineering.

show abstract

Short- Term Power Prediction Method for Photovoltaic Power Generation Based on Elman Neural Network for Aspen Swarm Optimization

Cited by 5 publications

References 1 publication

Regional economic forecast using Elman neural networks with wavelet function

Regional economic forecast using Elman neural networks with wavelet function

A Model for Determining the Optimal Decommissioning Interval of Energy Equipment Based on the Whole Life Cycle Cost

Research on UPQC harmonic control strategy based on optimized QPIR controller of beetle antennae search algorithm in microgrid

Contact Info

Product

Resources

About