Control Strategy Based on Wavelet Transform and Neural Network for Hybrid Power System

Abstract

This paper deals with an energy management of a hybrid power generation system. The proposed control strategy for the energy management is based on the combination of wavelet transform and neural network arithmetic. The hybrid system in this paper consists of an emulated wind turbine generator, PV panels, DC and AC loads, lithium ion battery, and super capacitor, which are all connected on a DC bus with unified DC voltage. The control strategy is responsible for compensating the difference between the generated power from the wind and solar generators and the demanded power by the loads. Wavelet transform decomposes the power difference into smoothed component and fast fluctuated component. In consideration of battery protection, the neural network is introduced to calculate the reference power of battery. Super capacitor (SC) is controlled to regulate the DC bus voltage. The model of the hybrid system is developed in detail under Matlab/Simulink software environment.

A Review on the Selected Applications of Battery-Supercapacitor Hybrid Energy Storage Systems for Microgrids

“…Here, to satisfy the demand-generation mismatch a power allocation is coordinated between the HESS components using HPF, coordinating the depth of discharge (DoD) of BESS within specified limits. In [123], wavelet decomposition and neural network based energy management strategy is presented to compensate for the power variation caused by the RES and loads. Under the description of a unified voltage standalone RES configuration, a three-level Haar wavelet is implemented that decomposes the power difference between the RES generation and the load into approximation component and detailed component.…”

Load Forecasting and Operation Strategy Design for CCHP Systems Using Forecasted Loads

“…Load forecasting can also be accomplished by adopting artificial neural network [24], [25] and Kalman filter [23], [26], [27]. Other control approaches related to load forecasting and system identification can be found in [28]- [32], to name a few. Here, in this paper, since the temperature information is available, ARMAX model will be selected as the forecasting model; and the structure of two-stage least squares (TSLS) will be chosen to identify the model parameters.…”

“…represent the system input vector and the system output (forecasted load) vector during the time interval [t, t + 1], respectively; and (32), shown at the bottom of the page, represents the overall system conversion matrix. In (30), F m (t) and E grid (t) are the total fuel and electricity purchased during [t, t + 1].…”

“…In (30), F m (t) and E grid (t) are the total fuel and electricity purchased during [t, t + 1]. In (32), η pgu , η b , η hrs , and η h denote the efficiencies of PGU, auxiliary boiler, heating recovery system, and heating unit, respectively; COP ec and COP ac represent coefficients of performance of electric chiller and absorption chiller, respectively. In addition, α pgu and α b are the dispatch factors denoting the fuel fraction flows into the PGU and boiler, and α pgu + α b = 1; α user and α ec are the dispatch factors denoting the electricity fraction flows to the terminal users and electric chiller, and α user + α ec = 1; α ac and α h are the dispatch factors denoting the heat fraction flows to the absorption chiller and heating unit, and α ac + α h = 1.…”

Detection of heart murmurs based on radial wavelet neural network with Kalman learning

“…Wavelet transform has been used as signal pre-processor and in neural network classifiers as input space feeders with 90% classification accuracy [5][6][7]. Wavelet neural networks have been used as classifiers in real applications [8][9][10] due to their advantages of fitting functions and dealing with information [11]; higher prediction accuracy and better fault tolerance to meet the uncertainty, nonlinearity, and complexity in real-world systems [12].…”