Jianwu Zeng

Short-Term Wind Power Prediction Using a Wavelet Support Vector Machine

This paper proposes a wavelet support vector machine (WSVM)-based model for short-term wind power prediction (WPP). A new wavelet kernel is proposed to improve the generalization ability of the support vector machine (SVM). The proposed kernel has such a general characteristic that some commonly used kernels are its special cases. Simulation studies are carried to validate the proposed model with different prediction schemes by using the data obtained from the National Renewable Energy Laboratory (NREL). Results show that the proposed model with a fixed-step prediction scheme is preferable for short-term WPP in terms of prediction accuracy and computational cost. Moreover, the proposed model is compared with the persistence model and the SVM model with radial basis function (RBF) kernels. Results show that the proposed model not only significantly outperforms the persistence model but is also better than the RBF-SVM in terms of prediction accuracy.

An Isolated Multiport DC–DC Converter for Simultaneous Power Management of Multiple Different Renewable Energy Sources

This paper proposes a new isolated multiport dc-dc converter for simultaneous power management of multiple renewable energy sources, which can be of different types and capacities. The proposed dc-dc converter only uses one controllable switch in each port to which a source is connected. Therefore, it has the advantages of simple topology and minimum number of power switches. A general topology of the proposed converter is first introduced. Its principle and operation are then analyzed. The proposed converter is applied for simultaneous maximum power point tracking (MPPT) control of a wind/solar hybrid generation system consisting of one wind turbine generator (WTG) and two different photovoltaic (PV) panels. The experimental results are provided to validate the effectiveness of using the proposed converter to achieve MPPT simultaneously for the WTG and both PV panels.

Support vector machine-based short-term wind power forecasting

This paper proposes a support vector machine (SVM)-based statistical model for wind power forecasting (WPF). Instead of predicting wind power directly, the proposed model first predicts the wind speed, which is then used to predict the wind power by using the power-wind speed characteristics of the wind turbine generators. Simulation studies are carried out to validate the proposed model for very short-term and short-term WPF by using the data obtained from the National Renewable Energy Laboratory (NREL). Results show that the proposed model is accurate for very short-term and short-term WPF and outperforms the persistence model as well as the radial basis function neural network-based model.

Short-term solar power prediction using an RBF neural network

This paper proposes a radial basis function (RBF) neural network-based model for short-term solar power prediction (SPP). Instead of predicting solar power directly, the model predicts transmissivity, which is then used to obtain solar power according to the extraterrestrial radiation. The proposed model uses a novel two-dimensional (2D) representation for hourly solar radiation and uses historical transmissivity, sky cover, relative humidity and wind speed as the input. Simulation studies are carried out to validate the proposed model for short-term SPP by using the data obtained from the National Solar Radiation Database (NSRDB). The performance of the RBF neural network is compared with that of two linear regression models, i.e., an autoregressive (AR) model and a local linear regression (LLR) model. Results show that the RBF neural network significantly outperforms the AR model and is better than the LLR model. Furthermore, the use of transmissivity and other meteorological variables, especially the sky cover, can significantly improve the SPP performance.

An Isolated Three-Port Bidirectional DC–DC Converter for Photovoltaic Systems With Energy Storage

This paper proposes a new isolated three-port bidirectional dc–dc converter for simultaneous power management of multiple energy sources. The proposed converter has the advantage of using the least number of switches and soft switching for the main switch, which is realized by using an inductor–capacitor–inductor (

An Interconnection and Damping Assignment Passivity-Based Controller for a DC–DC Boost Converter With a Constant Power Load

LCL

A single-switch isolated DC-DC converter for photovoltaic systems

) -resonant circuit. The converter is capable of interfacing sources of different voltage–current characteristics with a load and/or a dc microgrid. The proposed converter is constructed for simultaneous power management of a photovoltaic (PV) panel, a rechargeable battery, and a load. Simulation and experimental results show that the proposed converter is capable of maximum power point tracking control for the PV panel, when there is solar radiation, and controlling the charge and discharge of the battery, when there is surplus energy and power deficiency with respect to the load, respectively.

Wind turbine fault detection and isolation using support vector machine and a residual-based method

This paper proposes an adaptive interconnection and damping assignment (IDA) passivity-based controller (PBC) with a complementary proportional integral (PI) controller for dc-dc boost converters with constant power loads (CPLs). The plant is modeled as a port-controlled Hamiltonian system (PCHS). A virtual circuit that interprets the parameters of the PCHS is then derived to determine the parameters of the IDA-PBC for the system to work in the underdamping, critical-damping, and overdamping modes. Moreover, a complementary PI controller is designed to eliminate the steady-state output voltage error of the IDA-PBC caused by the load variation. Simulation studies are carried out in MATLAB/Simulink to validate the proposed control algorithm for a dc-dc boost converter with a CPL; results show that the proposed control algorithm ensures the stability and fast response of the system in different modes when the load changes. Experimental results are provided to further validate the design and simulation of the proposed control algorithm.

A current-sensorless MPPT quasi-double-boost converter for PV systems

Isolated converters are desirable in the DC-DC power conversion applications where isolation or a large voltage step-up gain is needed. Traditional isolated DC-DC converters either utilize many switches to achieve high efficiency or use few switches which result in low efficiency. This paper proposes a new single-switch isolated DC-DC converter for maximum power point tracking (MPPT) control and voltage regulation of solar photovoltaic (PV) system. The proposed DC-DC converter has the advantage of using less number of switches than other existing isolated DC-DC converters. The operating principle and parameter design of the converter are described in the paper. Simulation studies are carried out in MATLAB to verify the theoretical analysis and show that the proposed converter is effective for MPPT for PV systems. Experimental results further validate the simulation studies. The proposed converter is capable of tracking the maximum power point of the PV panel in different time of the day.

An isolated three-port bidirectional DC-DC converter for photovoltaic systems with energy storage

This paper proposes a novel scheme combining support vector machines (SVM) and a residual-based method for wind turbine fault detection and isolation (FDI). SVMs with radius basis function kernels are used for detecting and identifying sensor stuck and offset faults, where binary codes of fault types are used as the outputs of the SVMs to minimize the number of SVMs being used. The same output of a SVM may correspond to different types of faults and the final decision is made by all SVMs instead of one SVM. Moreover, a residual-based fault detection method using a time-variant threshold is developed to identify the abrupt change and scaling faults. Monte Carlo simulations are carried out in MATLAB to test the effectiveness and robustness of the proposed FDI methods using a wind turbine FDI benchmark model. Results show that the proposed methods can always detect the faults successfully within the required time limits.