Training Recurrent Neural Networks With the Levenberg–Marquardt Algorithm for Optimal Control of a Grid-Connected Converter
نویسندگان
چکیده
منابع مشابه
Stability Analysis, Control and Modeling of Micro-grid Connected to Wind Turbine: Effect of Optimal Amplified Converter
Wind turbines as a renewable energy are installed and operated as wind farms in various locations with windy climates. Connecting micro grids to wind turbines can lead to improved power generation and transmission to distribution networks. Therefore, formulating and configuring the micro-grid connected to the wind turbine requires accurate examination of the configuration of the micro-grid wit...
متن کاملA Cellular Genetic Algorithm for training Recurrent Neural Networks
Recurrent neural networks (RNNs), with the capability of dealing with spatio-temporal relationship, are more complex than feed-forward neural networks. Training of RNNs by gradient descent methods becomes more dii-cult. Therefore, another training method, which uses cellular genetic algorithms, is proposed. In this paper, the performance of training by a gradient descent method is compared with...
متن کاملDecentralized Control Strategy for Optimal Energy Management in Grid-Connected and Islanded DC Microgrids
This paper proposes a decentralized control technique to minimize the total operation cost of a DC microgrid in both grid-connected and islanded modes. In this study, a cost-based droop control scheme based on the hourly bids of all participant distributed generators (DGs) and the hourly energy price of the utility is presented. An economic power sharing technique among various types of DG unit...
متن کاملModel Predictive Control of a BCDFIG With Active and Reactive Power Control Capability for Grid-Connected Applications
Recently, Brushless Cascaded Doubly Fed Induction Generator (BCDFIG) has been considered as an attractive choice for grid-connected applications due to its high controllability and reliability. In this paper, a Finite Control Set Model Predictive Control (FCS-MPC) method with active and reactive power control capability in grid-connected mode is proposed for controlling the BCDFIG in a way that...
متن کاملon descent spectral cg algorithm for training recurrent neural networks
In this paper, we evaluate the performance of a new class of conjugate gradient methods for training recurrent neural networks which ensure the sufficient descent property. The presented methods preserve the advantages of classical conjugate gradient methods and simultaneously avoid the usually inefficient restarts. Simulation results are also presented using three different recurrent neural ne...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Neural Networks and Learning Systems
سال: 2015
ISSN: 2162-237X,2162-2388
DOI: 10.1109/tnnls.2014.2361267