IP Library Granted Patent US 12,230,962
Granted Patent B2
US 12,230,962 · App. 17/663,210 · Granted Feb 18, 2025

Methods and systems for power-supply management in smart urban based on internet of things

Inventors: Zehua Shao (Chengdu, CN); Yong Li (Chengdu, CN); Bin Liu (Chengdu, CN); Yaqiang Quan (Chengdu, CN); Yongzeng Liang (Chengdu, CN)
Assignee: CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD.
H02J3/004H02J3/144
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,230,962
App. No.
17/663,210
Granted
Feb 18, 2025
Kind
B2
Abstract

The embodiments of the present disclosure provide methods and systems for power-supply management in a smart urban based on Internet of things (IoT), performed by an urban power-supply management platform. The method includes obtaining a first power-generation data by a sensor network platform; wherein the first power-generation data is determined by summarizing second power-generation data, and the second power-generation data is residential self-power-generation data; determining a power-supply prediction based on first power-generation data and environmental data; and sending the power-supply prediction to the power-supply company.

Claims (63)

1. A method of power-supply management in a smart urban based on Internet of things (IoT), performed by an urban power-supply management platform of a system for power-supply management in the smart urban based on IoT, wherein the system is a part of a processing device or implemented by the processing device; and the system further comprises a sensor network platform and an object platform, wherein

the urban power-supply management platform realize overall planning and coordination of connection and cooperation between various functional platforms; and the urban power-supply management platform gathers information of an operating system of the IoT, and provides perceptual management and control management functions for the operation system of the IoT;

the sensor network platform connects the urban power-supply management platform and the object platform, and plays functions of perceptual information sensing communication and control information sensing communication; and the sensor network platform is configured as a sensor network management server;

the object platform is a functional platform for performing perceptual information generation and control information; the sensor network platform communicates with the object platform, wherein the object platform is configured as a collection terminal and configured to obtain second power-generation data, and the collection terminal includes an intelligent meter or an energy router; wherein the smart meter is configured to collect self-power-generation data from each residential user, and the energy router is configured to collect self-power-generation data from multiple residential users in one or more communities;

the method comprising:

obtaining first power-generation data by the urban power-supply management platform communicating with the sensor network platform, wherein the first power-generation data is determined by summarizing the second power-generation data through network communication between the sensor network platform and the collection terminal, and the second power-generation data is residential self-power-generation data; wherein the second power-generation data is obtained from the collection terminal by the sensor network platform; wherein the first power-generation data is determined based on a process including:

sending, by the urban power-supply management platform, division of power generation modes and distribution information of power generation modes to the sensor network platform; determining, by the sensor network platform, the collection terminal according to the division of power generation modes; sub-dividing, by the urban power-supply management platform, area information according to dividing areas of the sensor network platform, sending a sub-division result to the sensor network platform, and determining, by the sensor network platform, the first power-generation data according to the sub-division result;

determining, by a first prediction model, a power-supply prediction based on the first power-generation data and environmental data; wherein

the first power-generation data includes at least one of first distribution information and second distribution information of the residential self-power-generation data, wherein the first distribution information includes distribution information according to power-generation mode, and the second distribution information includes distribution information according to time; and

the environmental data includes weather forecast data and traffic flow data; wherein the environmental data is obtained from the storage device or through invoking weather API by the urban power-supply management platform; and

transmitting, by the urban power-supply management platform, the power-supply prediction to a power-supply company through the sensor network platform; and

adjusting, by the power-supply company, power supply of different areas based on the power-supply prediction.

2. The method of claim 1 , wherein the obtaining the first power-generation data by the sensor network platform comprises:

obtaining, by the sensor network platform, the second power-generation data from the collection terminal in a staggered manner;

determining, by the sensor network platform, the first power-generation data based on the summary processing of the second power-generation data; and

obtaining, by the sensor network platform, the first power-generation data in the staggered manner; wherein the staggered manner refers to not carrying out different steps or operations at the same time; and the staggered manner include obtaining or uploading the power-generation data of different communities at different time periods.

3. The method of claim 1 , wherein the traffic flow data is used to predict a first power demand; wherein the predicting the first power demand comprises:

dividing an area where the power-supply terminal is located based on a main road of road traffic;

obtaining a traffic flow of each divided area as an environmental feature; and

determining, by a power consumption prediction model, the first power demand in the each divided area based on the environmental feature.

4. A system for power-supply management in a smart urban based on Internet of things (IoT), wherein the system comprises an urban power-supply management platform, a sensor network platform, and an object platform, wherein the system is a part of a processing device or implemented by the processing device; wherein

the urban power-supply management platform realize overall planning and coordination of connection and cooperation between various functional platforms; and the urban power-supply management platform gathers information of an operating system of the IoT, and provides perceptual management and control management functions for the operation system of the IoT;

the sensor network platform connects the urban power-supply management platform and the object platform, and plays functions of perceptual information sensing communication and control information sensing communication; and the sensor network platform is configured as a sensor network management server;

the object platform is a functional platform for performing perceptual information generation and control information; the sensor network platform communicates with the object platform, wherein the object platform is configured as a collection terminal and configured to obtain second power-generation data, and the collection terminal includes an intelligent meter or an energy router; wherein the smart meter is configured to collect self-power-generation data from each residential user, and the energy router is configured to collect self-power-generation data from multiple residential users in one or more communities;

wherein the urban power-supply management platform is configured to perform the following operations including:

obtaining first power-generation data by the urban power-supply management platform communicating with the sensor network platform, wherein the first power-generation data is determined by summarizing the second power-generation data through network communication between the sensor network platform and the collection terminal, and the second power-generation data is residential self-power-generation data; wherein the second power-generation data is obtained from the collection terminal by the sensor network platform; wherein the first power-generation data is determined based on a process including:

sending, by the urban power-supply management platform, division of power generation modes and distribution information of power generation modes to the sensor network platform; determining, by the sensor network platform, the collection terminal according to the division of power generation modes; sub-dividing, by the urban power-supply management platform, area information according to dividing areas of the sensor network platform, sending a sub-division result to the sensor network platform, and determining, by the sensor network platform, the first power-generation data according to the sub-division result;

determining, by a first prediction model, a power-supply prediction based on the first power-generation data and environmental data; wherein

the first power-generation data includes at least one of first distribution information and second distribution information of the residential self-power-generation data, wherein the first distribution information includes distribution information according to power-generation mode, and the second distribution information includes distribution information according to time; and

the environmental data includes weather forecast data and traffic flow data; wherein the environmental data is obtained from the storage device or through invoking weather API by the urban power-supply management platform; and

transmitting, by the urban power-supply management platform, the power-supply prediction to a power-supply company through the sensor network platform; and

adjusting, by the power-supply company, power supply of different areas based on the power-supply prediction.

5. The system of claim 4 , wherein the urban power-supply management platform is further configured to perform the following operations including:

obtaining, by the sensor network platform, the second power-generation data from the collection terminal in a staggered manner;

determining, by the sensor network platform, the first power-generation data based on the summary processing of the second power-generation data; and

obtaining, by the sensor network platform, the first power-generation data in the staggered manner; wherein the staggered manner refers to not carrying out different steps or operations at the same time; and the staggered manner include obtaining or uploading the power-generation data of different communities at different time periods.

6. The system of claim 4 , wherein the urban power-supply management platform is further configured to perform the following operations including:

dividing an area where the power-supply terminal is located based on a main road of road traffic;

obtaining a traffic flow of each divided area as an environmental feature; and

determining, by a power consumption prediction model, the first power demand in the each divided area based on the environmental feature.

7. A computer-readable storage medium storing computer instructions, wherein when reading the computer instructions in the storage medium, a computer executes the method of power-supply management in a smart urban based on the Internet of things (IoT) according to claim 1 .

8. The method of claim 1 , wherein the first prediction model is a machine learning model; wherein the first prediction model is obtained by a training process including:

training an initial first prediction model using a plurality of training samples with labels; wherein the training samples include historical first power-generation data, historical environmental data in a month, a quarter, and a year, the labels of the training samples are historical power supply data, and the labels of the training samples are obtained by manual marking;

updating parameters of the initial first prediction model;

ending training when the initial first prediction model satisfies a preset condition; and

obtaining the first prediction model.

9. The method of claim 3 , wherein the power consumption prediction model is obtained based on training, the training of the power consumption prediction model is performed by the urban power-supply management platform; wherein the training of the power consumption prediction model includes:

obtaining at least one training sample with a label and an initial power consumption prediction model; wherein the at least one training sample includes historical first power-generation data of different divided areas and historical environmental features corresponding to the different divided areas, and the label is historical first power demand for the different divided areas;

the initial power consumption prediction model is a power consumption prediction model without adjusting model parameters or not meeting a training requirement; and a count of the at least one training sample is determined according to accuracy requirements of the power consumption prediction model, actual application scenarios, and other factors;

inputting the at least one training sample into the initial power consumption prediction model;

iteratively updating parameters of the initial power consumption prediction model until meeting a preset condition; wherein the preset condition is a loss function less than a threshold, convergence of the loss function, or a training cycle reaching a threshold; and

obtaining the power consumption prediction model.

10. The system of claim 4 , wherein the first prediction model is a machine learning model; wherein the first prediction model is obtained by a training process including:

training an initial first prediction model using a plurality of training samples with labels; wherein the training samples include historical first power-generation data, historical environmental data in a month, a quarter, and a year, the labels of the training samples are historical power supply data, and the labels of the training samples are obtained by manual marking;

updating parameters of the initial first prediction model;

ending training when the initial first prediction model satisfies a preset condition; and

obtaining the first prediction model.

11. The system of claim 6 , wherein the power consumption prediction model is obtained based on training, the training of the power consumption prediction model is performed by the urban power-supply management platform; wherein the training of the power consumption prediction model includes:

obtaining at least one training sample with a label and an initial power consumption prediction model; wherein the at least one training sample includes historical first power-generation data of different divided areas and historical environmental features corresponding to the different divided areas, and the label is historical first power demand for the different divided areas;

the initial power consumption prediction model is a power consumption prediction model without adjusting model parameters or not meeting a training requirement; and a count of the at least one training sample is determined according to accuracy requirements of the power consumption prediction model, actual application scenarios, and other factors;

inputting the at least one training sample into the initial power consumption prediction model;

iteratively updating parameters of the initial power consumption prediction model until meeting a preset condition; wherein the preset condition is a loss function less than a threshold, convergence of the loss function, or a training cycle reaching a threshold; and

obtaining the power consumption prediction model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 19, 2022
From: SHAO, ZEHUA; LI, YONG; LIU, BIN; QUAN, YAQIANG; LIANG, YONGZENG
To: CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD.
Reel/Frame 059956/0200 →
Continuity (1)
Related Publication 20230369857A1 · Nov 16, 2023
References Cited (12)
US 11431169B1 · Buttgenbach · 2022 [cited by examiner]
US 20160335377A1 · Yamashina · 2016 [cited by examiner]
US 20210234372A1 · Inoue · 2021 [cited by examiner]
CN 113837434A · 2021 [cited by examiner]
CN 114021420A · 2022 [cited by examiner]
CN 114169615A · 2022 [cited by examiner]
JP 2017121133A · 2017 [cited by examiner]
KR 102444254B1 · 2022 [cited by examiner]
White Paper on Urban Brain Development, Smart City Standard Working Group of National Beacon Commission, 2022, 59 pages. [cited by applicant]
Shao, Zehua, Exploration and Research on the Structure of Internet of Things, Internet of Things Technologies Reliable Transmission, 2015, 10 pages. [cited by applicant]
Shao, Zehua, The Internet of Things sense the world beyond the world, China Renmin University Press, 2017, 30 pages. [cited by applicant]
Shao, Zehua, Smart City Architecture, Internet of Things Technologies Intelligent Processing and Application, 2016, 7 pages. [cited by applicant]