To improve the stability of high-proportion power electronic systems for power line communications and reducethenoise effect of power electronic equipment operation, this paper analyzes the principle and architecture of the deepconvolutional neural network (DCNN) algorithm. The noise modeling method based on the prediction parameters ofDCNN is proposed to reduce the reconstruction error and improve the noise immunity. Simulation results verifiedthat the proposed algorithm achieves superior performance in peak signal-to-noise ratio (PSNR) and reconstruction error.
With the expanding scale of photovoltaic (PV) power generation installed in the grid, the scattered communication terminals and the large-scale data communication led to the problem that the master station cannot aggregate information from multiple terminals and analyze data efficiently in real time. In this paper, a power line communication (PLC)-based efficient information aggregation and data compression architecture is constructed. On the basis, we propose genetic algorithm-based information aggregation algorithm to optimize PLC channel selection and reduce information aggregation delay. Moreover, we propose a multi-intersection approximation data estimation algorithm to support the master station for regulation and decision-making by improving data compression accuracy. Simulation results show that the proposed algorithm has superior performance in terms of information aggregation delay and data compression accuracy.
In order to meet the communication requirements of the new power system where a large number of power electronic objects are concurrently connected to the network, this paper first proposes a multi-layer hierarchical networking architecture for low-voltage power line carrier communication adapted to the new power system. Then, a greedy algorithmbased low-voltage power line carrier packet aggregation method is proposed to improve the overall transmission rate of the system by aggregating the filtered carriers. The simulation results show the effectiveness of the proposed algorithm.
The large-scale access of electrical equipment will generate serious noise interference, which affects the reliability of lowvoltage power line system. Establishing accurate noise model is the foundation for improving the anti-noise performance of the system. Therefore, this paper propose a noise extraction and measurement method for colored background noise generated by electrical equipment. The modeling scheme of wavelet neural network is proposed to model the colored background noise. Simulation results show that compared with the model of wavelet Markov chain, the output noise of the proposed model has a relatively consistent variation trend of the actual noise in the time domain waveform and power spectral density, making it more suitable for noise modeling in low-voltage power line communication system.
With the encouragement of new energy policies and the continuous promotion of solar energy development. Distributed photovoltaic (PV) grid connection operation has become a trend. However, due to the large impact of the weather, the power output of distributed PV is unstable. It is difficult for the grid scheduling department to timely adjust the power generation and load of the grid based on PV power changes, resulting in difficulty in balancing supply and demand, affecting the stable operation of the grid and PV consumption. In response to the above issues, this paper proposes a wavelet neural network-based distributed PV grid-connected power prediction method, which provides data reference for the scheduling department through the prediction of distributed PV power. First, distributed PV power prediction architecture is studied, including the sensing layer, prediction layer, and service layer. Then the specific functions of the prediction layer are designed based on a wavelet neural network. Finally, the simulation results show that the proposed method can effectively achieve the power prediction of distributed PV.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.