Household energy supervision system and method

Abstract

The invention provides a household energy supervision system and method, the system comprises a first sensor, a second sensor and a control terminal, the first sensor and the second sensor are in wireless communication with the control terminal, and the control terminal comprises a first collection module, a second collection module and a control module; the first collection module is used for collecting electricity consumption of household equipment in real time through the first sensor; the second collection module is used for collecting the current environment temperature and the number of families through the second sensor; the scheme generation module is used for generating an energy demand scheme adaptive to the current use scene through a preset deep learning model according to the electricity consumption, the current environment temperature and the number of families; and the intelligent scheduling module is used for generating an energy scheduling scheme according to the energy demand scheme, the power grid electricity price and the user preference, timely controlling the household equipment to work according to the energy scheduling scheme, and intelligently distributing and monitoring household energy according to the weather, the electricity price and the number of families.

Description

Technical Field

[0001] The present invention relates to the technical field of household energy management, and in particular to a household energy monitoring system and method. Background Art

[0002] With the gradual advancement of my country's carbon neutrality and carbon trading plans, the environmental protection concept of energy conservation and emission reduction has gradually become a reality. The traditional energy distribution system has many problems such as excessive voltage drop in the power distribution line causing energy loss and lack of dynamic management capabilities. The existence of these problems will limit its widespread promotion.

[0003] At present, some intelligent energy supervision systems have emerged to solve these problems, but the existing technology is not yet able to reasonably allocate energy in a refined and personalized manner, which makes it impossible to apply it to small energy management scenarios, especially in home energy management. The existing intelligent energy supervision system has a low degree of system integration and cannot better coordinate the generation, storage and use of home energy; the adjustment strategy is too simple and cannot select energy use strategies based on the personality or habits of users; there is no connection with the outside world and the region, and the strategy used cannot reasonably predict and dispatch according to local electricity prices, weather, peak and off-peak electricity consumption; the system architecture is too simple and vulnerable to network attacks.

[0004] In summary, there is an urgent need for a home energy monitoring system that is highly integrated, refined, personalized and not vulnerable to attacks. Summary of the invention

[0005] The present invention provides a household energy monitoring system and method to solve the defects of the prior art, such as low system integration, too single adjustment strategy, inability to reasonably predict and schedule, and too simple system architecture. The system integration is improved, refined, personalized, and not easy to be attacked, making it more suitable for household energy scenarios.

[0006] The present invention provides a household energy monitoring system, the system comprising: a first sensor, a second sensor and a control terminal, the first sensor, the second sensor and the control terminal perform wireless communication, wherein the control terminal comprises:

[0007] A first collection module, used to collect the power consumption of household devices in real time through the first sensor;

[0008] A second collecting module, used for collecting the current ambient temperature and the number of family members through the second sensor;

[0009] A solution generation module, used to generate an energy demand solution adapted to the current usage scenario through a preset deep learning model according to the power consumption, current ambient temperature and number of family members;

[0010] The intelligent scheduling module is used to generate an energy scheduling plan according to the energy demand plan, grid electricity prices and user preferences, and to control the household appliances to work in a timely manner according to the energy scheduling plan.

[0011] According to a household energy monitoring system provided by the present invention, the first collection module is specifically used to suppress the noise of the received first sensor signal, analyze the power consumption, and optimize the power consumption.

[0012] According to a household energy monitoring system provided by the present invention, the control terminal further includes:

[0013] The energy management module is used to select a lower-cost energy storage system for charging and discharging according to the power price of the power grid, the amount of solar power generation and the amount of stored power.

[0014] According to a household energy monitoring system provided by the present invention, the control terminal further includes:

[0015] The third collection module is used to obtain weather forecast data through an API interface;

[0016] The intelligent scheduling module is also used to automatically adjust the working mode of the heating or cooling system according to the weather forecast data and the current ambient temperature.

[0017] According to a household energy monitoring system provided by the present invention, the system further comprises a mobile control terminal which wirelessly communicates with the control terminal. The mobile control terminal comprises

[0018] A remote control module, used to remotely control the household device by sending instructions; and / or

[0019] Energy consumption reporting module, used to provide real-time household energy consumption reports.

[0020] According to a household energy monitoring system provided by the present invention, the mobile control terminal further includes:

[0021] A maintenance prediction module is used to collect operating data of the household appliance, predict possible failures of the household appliance through a first machine learning model based on the operating data, and inform the user of the predicted equipment maintenance schedule in advance through the control terminal to reduce energy waste caused by failures, wherein the operating data includes operating time, energy consumption and historical failure records.

[0022] According to a household energy monitoring system provided by the present invention, the mobile control terminal further includes:

[0023] A preference analysis module, configured to analyze user behavior through a second machine learning model based on the power consumption, current ambient temperature, family size, and user interaction data to obtain user preferences;

[0024] The energy-saving suggestion module is used to provide energy-saving suggestions to the user according to the user preferences, and the energy-saving suggestions include timing to shut down the household appliances and adjusting the settings of the household appliances.

[0025] According to a household energy monitoring system provided by the present invention, the system further comprises a smart socket, and the smart socket communicates wirelessly with a control terminal, wherein:

[0026] The intelligent scheduling module is specifically used to enable the household appliance to work in a timely manner by controlling the switch of the intelligent socket or by sending a control instruction to the household appliance.

[0027] According to a household energy monitoring system provided by the present invention, the control terminal further includes: a model training module for training the preset convolutional neural network model, wherein the model training module includes:

[0028] An initialization submodule is used to initialize the submodule, load the pre-trained model, set the user preference parameters and set the household equipment, initialize the use status of the storage battery and solar energy equipment and read the energy storage parameters, which include power generation, load and power storage status;

[0029] A data preprocessing submodule is used to collect historical household electricity consumption, and sequentially perform data cleaning, fill in missing values ​​and normalize the historical household electricity consumption;

[0030] A feature extraction submodule, used for extracting features with high correlation from the historical household electricity consumption after the normalization process;

[0031] A model training submodule, used to use the historical household electricity consumption to train a pre-trained model of the time series to generate a preset deep learning model;

[0032] The model evaluation submodule is used to evaluate the accuracy of the preset deep learning model using the test power consumption, and optimize and iterate the preset deep learning model according to the evaluation result, wherein the optimization includes model parameter optimization and model structure optimization.

[0033] According to a home energy supervision system provided by the present invention, the wireless communication includes any one or more combinations of 4G, 5G, Wi-Fi, Zigbee or Bluetooth Low Energy (BLE).

[0034] The present invention provides a household energy monitoring method, which includes: collecting the power consumption of household appliances in real time through a first sensor; collecting the current ambient temperature and the number of family members through a second sensor; generating an energy demand plan adapted to the current usage scenario through a preset deep learning model based on the power consumption, the current ambient temperature and the number of family members; generating an energy scheduling plan based on the energy demand plan, grid electricity prices and user preferences, and controlling the household appliances to work in a timely manner according to the energy scheduling plan.

[0035] The present invention provides a household energy monitoring system and method, the system includes a first sensor, a second sensor and a control terminal, the first sensor and the second sensor communicate wirelessly with the control terminal, wherein the control terminal includes: a first collection module, used to collect the power consumption of household appliances in real time through the first sensor; a second collection module, used to collect the current ambient temperature and the number of family members through the second sensor; a solution generation module, used to generate an energy demand solution adapted to the current usage scenario according to the power consumption, the current ambient temperature and the number of family members through a preset deep learning model; an intelligent scheduling module, used to generate an energy scheduling solution according to the energy demand solution, the power grid electricity price and the user's preference, and according to the energy scheduling solution, timely control the household appliances to work, and realize intelligent distribution and monitoring of household energy according to the weather, electricity price and the number of family members, with high integration, refinement, personalization and not easy to be attacked. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a structural schematic diagram of the household energy monitoring system provided by the present invention.

[0038] Figure 2 It is a flow chart of the household energy monitoring method provided by the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the embodiments of the present invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In the textual description of the present invention, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship. In addition, it should be noted that the serial numbers themselves, such as "first", "second", etc., used to distinguish the objects described in the present invention are only used to distinguish the objects described, and do not have any order or technical meaning.

[0041] Reference Figure 1 , which is one of the structural diagrams of the household energy monitoring system provided by the present invention, such as Figure 1 As shown, the system includes a first sensor 1, a second sensor 2 and a control terminal 3, wherein the first sensor 1, the second sensor 2 and the control terminal 3 perform wireless communication, wherein the wireless communication includes any one or more combinations of 4G, 5G, Wi-Fi, Zigbee or Bluetooth Low Energy (BLE), wherein the control terminal 3 includes:

[0042] The first collection module is used to collect the power consumption of household appliances in real time through the first sensor, and the household appliances include any one or more combinations of heaters, fans, air conditioners, humidifiers, lights, washing machines, dryers, sweeping robots, and housework robots; the first sensor includes a current and voltage sensor. Specifically, the first collection module is used to suppress the noise of the received first sensor signal and then analyze the power consumption to optimize the power consumption.

[0043] The second collection module is used to collect the current ambient temperature and the number of family members through the second sensor, where the second sensor includes a temperature sensor, an infrared sensor, a camera or a radar.

[0044] A solution generation module is used to generate an energy demand solution adapted to the current usage scenario based on the power consumption, current ambient temperature and number of family members through a preset deep learning model; the preset deep learning model is a pre-trained embedded convolutional neural network model. The control terminal 3 also includes: a model training module, which is used to train the preset convolutional neural network model, wherein the model training module includes:

[0045] An initialization submodule is used to initialize the submodule, load the pre-trained model, set the user preference parameters and set the household equipment, initialize the use status of the storage battery and solar energy equipment and read the energy storage parameters, which include power generation, load and power storage status;

[0046] A data preprocessing submodule is used to collect historical household electricity consumption, and sequentially perform data cleaning, fill in missing values ​​and normalize the historical household electricity consumption;

[0047] A feature extraction submodule, used for extracting features with high correlation from the historical household electricity consumption after the normalization process;

[0048] A model training submodule, used to use the historical household electricity consumption to train a pre-trained model of the time series to generate a preset deep learning model;

[0049] The model evaluation submodule is used to evaluate the accuracy of the preset deep learning model using the test power consumption, and optimize and iterate the preset deep learning model according to the evaluation result, wherein the optimization includes model parameter optimization and model structure optimization.

[0050] The intelligent scheduling module is used to generate an energy scheduling plan according to the energy demand plan, the power grid electricity price and the user's preference, and control the household appliances to work in a timely manner according to the energy scheduling plan. Preferably, the system also includes a smart socket 4, and the smart socket 4 communicates wirelessly with the control terminal 3, wherein the intelligent scheduling module is specifically used to control the switch of the smart socket 4 or send a control instruction to the household appliance to realize the timely operation of the household appliance. For example, when it is detected that the number of family members is zero, the lights, air conditioners and other equipment are controlled to be turned off; when the electricity price is low, the washing machine, dryer, etc. are turned on to work.

[0051] Furthermore, the control terminal 3 also includes: an energy management module, which is used to select a lower-cost energy storage system for charging and discharging according to the grid electricity price, solar power generation and storage capacity. The energy storage system includes a municipal power grid, solar power generation equipment and storage batteries. By intelligently selecting different energy storage systems for power supply, while ensuring efficient use of renewable energy, it is given priority when renewable energy is sufficient, and automatically switches to grid power supply when it is insufficient, which can effectively reduce electricity costs.

[0052] Furthermore, the control terminal 3 also includes:

[0053] The third collection module is used to obtain weather forecast data through an API interface;

[0054] The intelligent scheduling module is also used to automatically adjust the working mode of the heating or cooling system according to the weather forecast data and the current ambient temperature. The weather forecast data is obtained through the API interface so that the system can automatically adjust the working mode of the heating or cooling system according to the weather forecast data.

[0055] Furthermore, the system further comprises a mobile control terminal 5 which wirelessly communicates with the control terminal 3, and the mobile control terminal 5 comprises

[0056] A remote control module, used to remotely control the household device by sending instructions; and / or

[0057] The energy consumption report module is used to provide real-time household energy consumption reports. By remotely controlling smart devices at home and providing real-time energy consumption reports, users can view their household energy usage. At the same time, the application will protect user account security through security measures such as passwords, fingerprints or facial recognition, and use blockchain technology for data transmission.

[0058] Furthermore, the mobile control terminal 5 also includes:

[0059] A maintenance prediction module is used to collect the operating data of the household appliance, predict the possible failure of the household appliance through a first machine learning model based on the operating data, and inform the user of the predicted equipment maintenance schedule in advance through the control terminal to reduce energy waste caused by failures, wherein the operating data includes operating time, energy consumption and historical failure records. The first machine learning model is a machine learning model obtained by training with historical operating data, and is used to obtain possible failures based on historical operating data. The predicted equipment maintenance schedule is informed to the user through a smartphone application to help the user make better arrangements in order to reduce energy waste caused by failures.

[0060] Furthermore, the mobile control terminal 5 also includes:

[0061] The preference analysis module is used to analyze user behavior through the power consumption, current ambient temperature, family size and user interaction data through a second machine learning model to obtain user preferences; the second machine learning model is a machine learning model obtained by training historical power consumption, family size and user interaction data, and is used to obtain user preferences based on real-time data.

[0062] The energy-saving suggestion module is used to provide energy-saving suggestions to the user according to the user preferences, and the energy-saving suggestions include timing to shut down the household appliances and adjusting the settings of the household appliances.

[0063] The household energy monitoring system provided by the embodiment of the present invention comprises a first sensor, a second sensor and a control terminal, wherein the first sensor and the second sensor perform wireless communication with the control terminal, wherein the control terminal comprises: a first collection module, used to collect the power consumption of household appliances in real time through the first sensor; a second collection module, used to collect the current ambient temperature and the number of family members through the second sensor; a solution generation module, used to generate an energy demand solution adapted to the current usage scenario according to the power consumption, the current ambient temperature and the number of family members through a preset deep learning model; an intelligent scheduling module, used to generate an energy scheduling solution according to the energy demand solution, the power price of the power grid and the user's preference, and according to the energy scheduling solution, timely control the household appliances to work, and realize intelligent distribution and monitoring of household energy according to the weather, the power price and the number of family members, with high integration, refinement, personalization and no easy attack.

[0064] Reference Figure 2 , which is a flow chart of the household energy monitoring method provided by the present invention, such as Figure 2 As shown, the home energy supervision method is applicable to the above-mentioned home energy supervision system, the system comprising: a first sensor, a second sensor and a control terminal, the first sensor, the second sensor and the control terminal perform wireless communication, the wireless communication comprises any one or more combinations of 4G, 5G, Wi-Fi, Zigbee or Bluetooth Low Energy (Bluetooth Low Energy, BLE), the method comprises:

[0065] Step S201, collecting the power consumption of household appliances in real time through a first sensor, wherein the household appliances include any one or more combinations of heaters, fans, air conditioners, humidifiers, lights, washing machines, dryers, sweeping robots, and household robots; the first sensor includes a current and voltage sensor. Specifically, noise is suppressed on the received first sensor signal, and the power consumption is analyzed to optimize the power consumption.

[0066] Step S202, collecting the current ambient temperature and the number of family members through a second sensor, where the second sensor includes a temperature sensor, an infrared sensor, a camera or a radar;

[0067] Step S203, generating an energy demand plan adapted to the current usage scenario through a preset deep learning model according to the power consumption, current ambient temperature and number of family members;

[0068] Step S204, generating an energy scheduling plan according to the energy demand plan, grid electricity prices and user preferences, and controlling the home appliances to work in a timely manner according to the energy scheduling plan.

[0069] Furthermore, the method also includes: selecting a lower-cost energy storage system for charging and discharging according to the grid electricity price, solar power generation and storage capacity.

[0070] Furthermore, the method also includes obtaining weather forecast data through an API interface; the intelligent scheduling module is also used to automatically adjust the working mode of the heating or cooling system according to the weather forecast data and the current ambient temperature.

[0071] Furthermore, the system further comprises a mobile control terminal in wireless communication with the control terminal, and the method further comprises remotely controlling the household device by sending instructions; and / or

[0072] Provides real-time reports on home energy consumption.

[0073] Furthermore, the method also includes: collecting operating data of the household appliance, predicting possible failures of the household appliance through a first machine learning model based on the operating data, and informing the user of the predicted equipment maintenance schedule in advance through the control terminal to reduce energy waste caused by failures, the operating data including operating time, energy consumption and historical fault records.

[0074] Furthermore, the method also includes: analyzing user behavior through the power consumption, current ambient temperature, family size and user interaction data through a second machine learning model to obtain user preferences; providing energy-saving suggestions to the user based on the user preferences, and the energy-saving suggestions include timed shutdown of the household appliances and adjustment of the settings of the household appliances.

[0075] Furthermore, the system also includes a smart socket, which communicates wirelessly with the control terminal, wherein the household appliance is enabled to work in a timely manner by controlling the switch of the smart socket or by sending a control instruction to the household appliance.

[0076] Furthermore, the method further includes: training the preset convolutional neural network model, specifically, loading the pre-trained model, setting the user preference parameters and setting the household device, initializing the use status of the storage battery and the solar energy device and reading the energy storage parameters, the energy storage parameters including power generation, load, and power storage status;

[0077] Collect historical household electricity consumption, and perform data cleaning, missing value filling and normalization on the historical household electricity consumption in turn;

[0078] Extracting features with high correlation from the historical household electricity consumption after the normalization process;

[0079] Generate a preset deep learning model using the pre-trained model of the historical household electricity consumption training time series;

[0080] The accuracy of the preset deep learning model is evaluated using the test power consumption, and the preset deep learning model is optimized and iterated according to the evaluation result, wherein the optimization includes model parameter optimization and model structure optimization.

[0081] The household energy monitoring method provided by the embodiment of the present invention includes collecting the power consumption of household appliances in real time through the first sensor; collecting the current ambient temperature and the number of family members through the second sensor; generating an energy demand plan adapted to the current usage scenario through a preset deep learning model based on the power consumption, the current ambient temperature and the number of family members; generating an energy scheduling plan based on the energy demand plan, the power grid electricity price and the user's preference, and controlling the household appliances to work in a timely manner according to the energy scheduling plan, realizing intelligent distribution and monitoring of household energy according to the weather, electricity price and the number of family members, with high integration, refinement, personalization and not easy to be attacked.

[0082] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A household energy monitoring system, characterized in that: The system comprises: a first sensor, a second sensor and a control terminal, wherein the first sensor, the second sensor and the control terminal perform wireless communication, wherein the control terminal comprises: A first collection module, used to collect the power consumption of household devices in real time through the first sensor; A second collecting module, used for collecting the current ambient temperature and the number of family members through the second sensor; A solution generation module, used to generate an energy demand solution adapted to the current usage scenario through a preset deep learning model according to the power consumption, current ambient temperature and number of family members; The intelligent scheduling module is used to generate an energy scheduling plan according to the energy demand plan, grid electricity prices and user preferences, and to control the household appliances to work in a timely manner according to the energy scheduling plan.

2. The home energy monitoring system according to claim 1, characterized in that: The first collection module is specifically used to suppress the noise of the received first sensor signal, analyze the power consumption, and optimize the power consumption.

3. The home energy monitoring system according to claim 1, characterized in that: The control terminal also includes: The energy management module is used to select a lower-cost energy storage system for charging and discharging according to the power price of the power grid, the amount of solar power generation and the amount of stored power.

4. The home energy monitoring system according to claim 1, characterized in that: The control terminal also includes: The third collection module is used to obtain weather forecast data through an API interface; The intelligent scheduling module is also used to automatically adjust the working mode of the heating or cooling system according to the weather forecast data and the current ambient temperature.

5. The home energy monitoring system according to claim 1, characterized in that: The system also includes a mobile control terminal that wirelessly communicates with the control terminal, and the mobile control terminal includes A remote control module, used to remotely control the household device by sending instructions; and / or Energy consumption reporting module, used to provide real-time household energy consumption reports.

6. The home energy monitoring system according to claim 1, characterized in that: The mobile control terminal also includes: A maintenance prediction module is used to collect operating data of the household appliance, predict possible failures of the household appliance through a first machine learning model based on the operating data, and inform the user of the predicted equipment maintenance schedule in advance through the control terminal to reduce energy waste caused by failures, wherein the operating data includes operating time, energy consumption and historical failure records.

7. The home energy monitoring system according to claim 1, characterized in that: The mobile control terminal also includes: A preference analysis module, configured to analyze user behavior through a second machine learning model based on the power consumption, current ambient temperature, family size, and user interaction data to obtain user preferences; The energy-saving suggestion module is used to provide energy-saving suggestions to the user according to the user preferences, and the energy-saving suggestions include timing to shut down the household appliances and adjusting the settings of the household appliances.

8. The home energy monitoring system according to claim 1, characterized in that: The system also includes a smart socket, which communicates wirelessly with the control terminal, wherein: The intelligent scheduling module is specifically used to enable the household appliance to work in a timely manner by controlling the switch of the intelligent socket or by sending a control instruction to the household appliance.

9. The home energy monitoring system according to claim 1, characterized in that: The control terminal further includes: a model training module, which is used to train the preset convolutional neural network model, wherein the model training module includes: An initialization submodule is used to initialize the submodule, load the pre-trained model, set the user preference parameters and set the household equipment, initialize the use status of the storage battery and solar energy equipment and read the energy storage parameters, which include power generation, load and power storage status; A data preprocessing submodule is used to collect historical household electricity consumption, and sequentially perform data cleaning, fill in missing values ​​and normalize the historical household electricity consumption; A feature extraction submodule, used for extracting highly relevant features from the historical household electricity consumption after the normalization process; A model training submodule, used to use the historical household electricity consumption to train a pre-trained model of the time series to generate a preset deep learning model; The model evaluation submodule is used to evaluate the accuracy of the preset deep learning model using the test power consumption, and optimize and iterate the preset deep learning model according to the evaluation result, wherein the optimization includes model parameter optimization and model structure optimization.

10. The home energy monitoring system according to any one of claims 1 to 9, characterized in that: The wireless communication includes any one or more combinations of 4G, 5G, Wi-Fi, Zigbee or Bluetooth Low Energy (BLE).

11. A household energy monitoring method, characterized in that: The method comprises: The power consumption of household devices is collected in real time by a first sensor; The current ambient temperature and the number of family members are collected by a second sensor, wherein the second sensor includes a temperature sensor, an infrared sensor, a camera or a radar; According to the power consumption, current ambient temperature and number of family members, an energy demand plan adapted to the current usage scenario is generated through a preset deep learning model; An energy scheduling plan is generated according to the energy demand plan, grid electricity prices and user preferences, and the household appliances are controlled to work in a timely manner according to the energy scheduling plan.

Images