With the rapid development of new energy generation technology and communication technology, the market demand and input-output ratio of smart microgrid are getting higher and higher. Smart microgrid combines the advantages of smart grid and microgrid into one, with high automation, flexible and reliable power supply, which is a good carrier to study smart grid and its operation control methods. Compared with traditional power grids, smart microgrids have a complex structure and there are many potential faults that are difficult to detect by traditional methods, leading to changes in configuration structure, which in turn have a more obvious impact on the safe and stable operation of smart microgrids, and the system operation efficiency decreases or even generates systemic instability. In this paper, a deep learning algorithm is used to construct an AI fault identification and localization system for smart microgrid. The convolutional neural network structure is used to extract the simulation data of smart microgrid in different states and build a training set.
Traditional AC system protection and conventional DC transmission system protection principles and methods are difficult to apply to current DC transmission lines. First, analyze the transient characteristics of DC transmission line faults, and then extract high-frequency transient voltage components at the moment of fault through wavelet changes. Based on the wavelet energy values of the faults inside and outside the zone, propose a fault identification method. A DC fault protection scheme based on the reclosing criterion. A fault protection algorithm based on the combination of DC circuit breaker and transient traveling wave is given. Finally, a four-terminal voltage source converter-type DC grid model was built on the Matlab / Simulink simulation platform, and the feasibility of the protection principle was verified through simulation experiments. The advantages are of great significance for the rapid determination of DC transmission faults.
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.