Maximizing solar panel power generation with shadow energy generation

Patent metadata

Field	Value
Publication number	US-12411476-B2
Application number	US-202218064570-A
Country	US
Kind code	B2
Filing date	Dec 12, 2022
Priority date	Dec 12, 2022
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

An approach for adjusting an inclination angle of a mirror to maximize power output of an adjacent solar panel and shadow-effect energy generator (SEG). The approach retrieves data associated with a solar irradiance profile and a SEG shadow profile. The approach predicts an irradiance profile based on the data. The approach predicts a shadow contrast ratio based on the data. The approach predicts a SEG shadow profile based on the data. The approach calculates optimized control parameters associated with a mirror based on the irradiance profile, the shadow contrast ratio and the SEG shadow profile. The approach adjusts the mirror inclination angle based on the optimized control parameters.

First claim

What is claimed is:

1. A computer-implemented method comprising:
retrieving, by one or more processors, data associated with a solar irradiance profile and a shadow-effect energy generator (SEG) shadow profile;
predicting, by the one or more processors, an irradiance profile based on the data;
predicting, by the one or more processors, a shadow contrast ratio based on the data;
predicting, by the one or more processors, a SEG shadow profile based on the data;
calculating, by the one or more processors, optimized control parameters associated with a mirror based on the irradiance profile, the shadow contrast ratio and the SEG shadow profile; and
adjusting, by the one or more processors, an inclination angle of the mirror based on the control parameters.

2. The computer-implemented method of claim 1 , wherein the predicting the irradiance profile, the predicting the shadow contrast ratio, and the predicting the SEG shadow profile employ a spatial temporal learning model.

3. The computer-implemented method of claim 1 , wherein the data comprises a selection from the group consisting of: geolocation data, terrain topography data, irradiance satellite observation data, time of day data, and solar panel area data.

4. The computer-implemented method of claim 1 , wherein the calculating is based on an equation:

J
=

∑

i
=
1

N

⁢

w

L
i

(

L
i
r

-

L
i
m

(
α
)

)

2

+

∑

i
=
1

N

⁢

w

C
⁢

R
i

(

C
⁢

R
i
r

-

C
⁢

R
i
m

(
α
)

)

2

+

∑

i
=
1

N

⁢

w

C
⁢

R
i

(

R
i
r

-

R
i
m

(
α
)

)

2

+

∑

i
=
1

N

⁢

w

u
⁡
(
a
)

i

(

Δ
⁢
u

)

2

,

wherein J is a cost function over a receding horizon; L i r is an optimal irradiance for an instant “i;” L i m , is a measured irradiance for the instant “i;” CR i r is an optimal shadow contrast ratio for the instant “i” from a knowledge base; CR i m is a chosen shadow contrast for the instant “i;” R i r is an optimal relative shadow position for the instant “i” from the knowledge base; R i m is a captured relative shadow position for the instant “i,” which is a function of a horizontal and lateral position of the SEG; u is a respective mirror controller variable; w CR i is a weighting coefficient for the instant shadow contrast ratio; w L i is a weighting coefficient for the instant irradiance; w u(α) i is a penalizing coefficient for large changes in a

Assignees

• IBM

Inventors

• Rakshit Sarbajit K
• Padmanaban Manikandan
• Hazra Jagabondhu

Classifications

• G05B2219/37283

  Photoelectric sensor · CPC title

• G05B19/4155 Primary

  characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program · CPC title