Method for hybrid solar tracking, and apparatus for hybrid solar tracking and photovoltaic blind system using same

Patent metadata

Field	Value
Publication number	US-9660571-B2
Application number	US-201514979658-A
Country	US
Kind code	B2
Filing date	Dec 28, 2015
Priority date	Dec 31, 2014
Publication date	May 23, 2017
Grant date	May 23, 2017

Abstract

A method for hybrid solar tracking, and an apparatus for hybrid solar tracking and a photovoltaic blind system using the same are disclosed. The method includes generating first predicted power output data by analyzing first measured power output data of the past; generating a lagged error; constructing a regression analysis (RA) model, and deriving second predicted power output data; constructing an artificial neural network (ANN) model, and deriving third predicted power output data; selecting either a method for solar tracking based on photovoltaic power output or a method for solar tracking based on location and time depending on whether the second measured power output data of the present time falls within a filtering range based on a first error range and a second error range; and determining the directions of photovoltaic panels according to the selected method for solar tracking.

First claim

What is claimed is:

1. A photovoltaic blind system, comprising:
a plurality of blind slats configured such that photovoltaic panels are attached thereto, respectively;
a power amount measurement unit configured to measure power amounts generated by the photovoltaic panels;
an apparatus for hybrid solar tracking; and
a drive unit configured to control directions of the blind slats according to directions of the photovoltaic panels determined by the apparatus for hybrid solar tracking;
wherein the apparatus for hybrid solar tracking comprises:
a first power output prediction unit configured to generate first predicted power output data by analyzing first measured power output data of the past through time series analysis;
a second power output prediction unit configured to obtain a lagged error between the first measured power output data and the first predicted power output data, to construct an RA model for predicting second predicted power output data based on the first measured power output data, the first predicted power output data and the lagged error, and to derive the second predicted power output data;
a third power output prediction unit configured to construct an ANN model for predicting third predicted power output data according to the following equation to derive the third predicted power output data:
{circumflex over( Z )} t =f ANN ( Z t−1 ,{circumflex over( L )} t−m ,e t−n s ),

where {circumflex over (Z)} t is the third predicted power output data predicted at time t, f ANN is the artificial neural network model, Z t−1 is the first measured power output data measured at time t−l (l is an integer), {circumflex over (L)} t−m is the first predicted power output data predicted at time t−m (m is an integer), and e t−n s is the lagged error calculated at time t−n (n is an integer);
a solar tracking control unit configured to select either a method for solar tracking based on photovoltaic power output or a method for solar tracking based on location and time, depending on whether the second measured power output data of the present time falls within a filtering range based on a first error range of the second predicted power output data and a second error range of the third predicted power output data, and to determine the directions of photovoltaic panels according to the selected method for solar tracking,
wherein the drive unit is operable to:
control vertical directions of the photovoltaic panels on the blind slats by controlling angles of the blind slats in such a way as to wind or unwind ropes for the control of angles using wire pullers and motors according to the determined directions of the photovoltaic panels; and
control horizontal directions of the photovoltaic panels on the blind slats hung from a housing including the drive unit and the apparatus for hybrid solar tracking by rotating the housing connected to a window frame in such a way as to drive gears, fastened to the housing and the window frame, respectively, using a motor.

2. The photovoltaic blind system of claim 1 , wherein the time series analysis of the first measured power output data is based on auto-regressive integrated moving average (ARIMA) analysis or seasonal ARIMA (SARIMA) analysis.

3. The photovoltaic blind system of claim 1 , wherein the first error range or second error range is a range that is determined by setting up upper and lower limits using one of a mean absolute percentage error (MAPE) and a standard error of regression (SER).

4. The photovoltaic blind system of claim 1 , wherein the filtering range is a cross range in which the first error range and the second error range overlap each other.

5. The photovoltaic blind system of claim 4 , wherein the filtering range is a range in which upper and lower limits of the cross range, in which the first error range and the second error range overlap each other, have been extended by a predetermined tolerance range.

Assignees

• Industry-Academic Cooperation Foundation Yonsei Univ

Inventors

• Hong Tae Hoon
• Koo Choong Wan
• Jeong Kwang Bok
• Kim Ji Min
• Ban Cheol Woo
• Lee Min Hyun
• Ji Chang Yoon

Classifications

• G06N3/02

  Neural networks · CPC title

• H02S20/32 Primary

  specially adapted for solar tracking · CPC title

• G05B13/048

  using a predictor · CPC title

• Y02B80/50

  Cross-Sectional Technologies · mapped topic

• H02S50/00

  Monitoring or testing of PV systems, e.g. load balancing or fault identification · CPC title