This paper reports the use of machine learning to enhance the diagnosis of a dusty plasma. Dust in a plasma has a large impact on the properties of the plasma. According to a probe diagnostic experiment on a dust-free plasma combined with machine learning, an experiment on a dusty plasma is designed and carried out. Using a specific experimental device, dusty plasma with a stable and controllable dust particle density is generated. A Langmuir probe is used to measure the electron density and electron temperature under different pressures, discharge currents, and dust particle densities. The diagnostic result is processed through a machine learning algorithm, and the error of the predicted results under different pressures and discharge currents is analyzed, from which the law of the machine learning results changing with the pressure and discharge current is obtained. Finally, the results are compared with theoretical simulations to further analyze the properties of the electron density and temperature of the dusty plasma.
In the present study, the machine learning algorithm is utilized for the first time to improve the probe diagnosis. Machine learning methods are utilized to improve the Langmuir probe diagnostic accuracy and the diagnosable plasma parameter range without changing the probe structure based on the Langmuir probe. They provide a new way for experimentally obtaining electron density. A DC glow discharge simulation model and experimental equipment are established. Utilizing the discharge pressure and voltage as independent variables, the simulation and experimental electron densities are collected, the simulation and experimental data are utilized for training, and the plasma electron density outside of the pressure and voltage range of the training data is predicted, thereby achieving the prediction. Simultaneously, when the data amount is large enough, even without experimental measurement, the electron density can be obtained directly through the input parameters, without relying on the plasma physical model.
The power prediction error of uncertain renewable energy sources (URESs) affects the power balance of a power grid. In the power systems with high proportion renewable power sources (PSHPRPSs), automatic generation control (AGC) cannot accommodate the day-ahead power prediction error. The dispatching control system (DCS) of PSHPRPSs adds real-time dispatching links to modify the day-ahead dispatching plan so that the grid power error is within the range of AGC accommodation. This paper proposes a critical time scale (CTS) selection algorithm based on time aggregation characteristics for real-time dispatching of PSHPRPSs and calculates the annual CTS of real-time dispatching of power grids. The uncertainty function is used to describe the relationship between the prediction error of the URESs and the prediction lead time. The total uncertainty function is calculated based on the time aggregation characteristics and is used to select the annual CTS of real-time dispatching. The proposed algorithm quantitatively describes the relationship between the CTS and the operation proportion of URESs and also AGC accommodation capacity. The calculated annual CTS not only ensures the power balance of the power grid, but also avoids the daily change of the CTS. Using the data of URESs in the Irish power grid, the feasibility of the proposed method was verified. The research results of this paper are helpful to accommodate the day-ahead power prediction error of URESs and maintain the safe operation of power grid. INDEX TERMS Uncertain renewable energy sources, power prediction error, real-time dispatching, critical time scale, time aggregation characteristics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.