Power distribution system

Abstract

The invention discloses a power distribution system. The system comprises a power distribution module, a control module and a data cloud platform, wherein the power distribution module is connected with a power supply and an electric appliance in series, the control module is configured in the power distribution module, and the control module establishes communication connection with the power distribution module and the data cloud platform respectively; the power distribution module is used for realizing electric energy distribution between the power supply and the electric appliances; the control module is used for periodically monitoring the working state of the power distribution system and sending the monitored working data to the data cloud platform; the data cloud platform is used for processing the working data by using a data analysis model when the working data is received, generating a control command and sending the control command to the control module; and the control module is used for controlling the power distribution module in response to the received control command. According to the technical scheme, automation of power distribution operation in the power grid system can be achieved, the power distribution efficiency of the power grid system is improved, and meanwhile the reliability of power distribution operation is improved.

Description

Technical Field

[0001] The present invention relates to the field of power grid control, and in particular to a power distribution system. Background Art

[0002] In today's society, the vigorous development of power systems and the rapid changes in power technology have led to the application scope of distribution devices and distribution systems gradually extending from the original regional power adjustment to household units. However, the existing household-based distribution devices and distribution systems still expose many problems in actual application and cannot fully meet the needs of household electricity consumption.

[0003] First, there are obvious deficiencies in reliability. Some traditional power distribution devices rely on mechanical switches and protective devices, which are easily corroded and affected under complex and changing environmental conditions, such as changes in temperature and humidity. Moreover, wear and tear will inevitably occur over time. The accumulation of such environmental impacts and wear greatly reduces the reliability of the power distribution device. Once a power failure occurs, these devices may not be able to cut off the power supply in a timely and effective manner, and thus fail to provide due protection for the connected electrical equipment, posing serious safety hazards to household electricity use.

[0004] Secondly, manual maintenance is a huge workload and inefficient. In order to maintain normal operation, traditional power distribution devices need to be inspected and maintained regularly. This process covers many links such as manual inspection, testing, and replacement of accessories. In addition, since it relies entirely on manual operation, it is easily interfered by human factors, resulting in omissions or errors. Moreover, this frequent and complex maintenance work requires high professional skills and experience of maintenance personnel, and also consumes a lot of manpower and time costs.

[0005] Furthermore, the lack of intelligent and automated functions has become a major shortcoming of traditional power distribution devices. Against the background of the rapid development of modern science and technology, the intelligence and automation of traditional power distribution devices are still at a low level. They cannot achieve remote monitoring, making it impossible for users to understand the status of household electricity consumption in real time. At the same time, potential faults cannot be effectively predicted and preventive measures cannot be taken in advance. In addition, the lack of automatic control functions makes it impossible to respond and adjust quickly and accurately when dealing with sudden power situations, which greatly limits the improvement of the efficiency and reliability of the power distribution system and cannot meet the needs of modern families for efficient, stable and convenient electricity use.

[0006] In summary, the existing power distribution system has problems such as poor reliability, poor distribution efficiency and inability to support automation. Summary of the invention

[0007] The present invention provides a power distribution system, which can solve the problems of poor reliability, poor power distribution efficiency and inability to support automation in the existing power distribution system.

[0008] According to one aspect of the present invention, there is provided a power distribution system, the system comprising: a power distribution module, a control module and a data cloud platform;

[0009] The power distribution module is connected in series with the power supply and the electrical appliances, the control module is arranged inside the power distribution module, and the control module establishes communication connections with the power distribution module and the data cloud platform respectively;

[0010] The power distribution module is used to realize the power distribution between the power source and the electrical appliances;

[0011] The control module is used to periodically monitor the working status of the power distribution system and send the monitored working data to the data cloud platform, so that the data cloud platform can generate control commands according to the working data;

[0012] The data cloud platform is used to process the working data using a pre-trained data analysis model when receiving the working data, generate a control command and send it to the control module;

[0013] The control module is further used to control the power distribution module in response to a received control command.

[0014] The power distribution module specifically includes: a main switch, a regulating switch, sub-switches and a backup power supply; wherein the input end of the main switch is connected to the power supply to control the on / off circuit with the power supply; the regulating switch is connected to the output end of the main switch to control the discharge of the backup power supply to the electrical appliance after power failure; the sub-switches are arranged in parallel, the input end of each sub-switch is connected to the output end of the regulating switch, and the output end of each sub-switch is respectively connected to the electrical appliance to control the electrical appliance individually;

[0015] The backup power supply is connected to the output end of the regulating switch, and is used to provide power to the power distribution module when the main switch or the regulating switch is disconnected, and to charge itself when both the main switch and the regulating switch are not disconnected.

[0016] The backup power supply specifically includes: a two-way power supply automatic conversion controller, a charger, an inverter and a battery; wherein one input end of the two-way power supply automatic conversion controller is connected to the output end of the inverter, the other input end is connected to the input end of the charger, the output end is connected to the output end of the regulating switch unit, and the output end of the charger and the input end of the inverter are both connected to the battery; the inverter is used to convert the direct current of the battery into alternating current when the power is off and supply power to the electrical appliances through the two-way power supply automatic conversion controller; the charger is used to charge the battery when the power is normally supplied; and the battery is used to supply power to the inverter when the power is off.

[0017] Among them, the control module includes a sensor unit and a control unit, the output end of the sensor unit is connected to the input end of the control unit, the input end of the sensor is connected to the sub-switch, the output end of the control unit is connected to the electrical appliance, and the number of the control modules is the same as the number of sub-switches in the distribution module; the sensor unit is used to collect various parameter data in the distribution system in real time to obtain the working data of the distribution system and send it to the control unit; the control unit is used to send the control data to the data cloud platform; the control unit is also used to control the on and off of the regulating switch or the sub-switch based on the received control command.

[0018] Optionally, the control unit further includes: a modem, a router, a wifi transceiver module, a central control processor and a memory; wherein the central control processor communicates with the memory bidirectionally, the wifi transceiver module communicates with the central control processor bidirectionally, and the modem establishes a communication connection with the sensor unit and the central control processor; the modem is used to perform modulation and demodulation on the received working data, and send the processed working data to the central control processor; the central control processor is used to send the working data to the data cloud platform via the wifi transceiver module, and send the working data to the memory; the memory is used to store the received working data.

[0019] Furthermore, the data cloud platform includes at least one base classification unit, a meta classification unit and a command generation unit, each base classification unit establishes a data connection with the meta classification unit, and the meta classification unit establishes a data connection with the command generation unit; the base classification unit is used to receive the working data sent by the control unit, and preprocess the received working data to obtain multiple preprocessing results and send them to the meta classification unit; the meta classification unit is used to process each prediction result through an adaptive boosting extreme learning machine model to obtain a monitoring result when it is detected that the number of preprocessing results received within a cycle is consistent with the number of base classification units; the command generation unit is used to generate a control command according to the monitoring result and send it to the control unit.

[0020] Optionally, the command generating unit is specifically used to: when it is detected that the monitoring result is normal, not generate a control command; when it is detected that the monitoring result is abnormal, generate a circuit breaker command so that the control unit controls each sub-switch and the regulating switch based on the control command.

[0021] Wherein, the base classification unit includes at least one of a back propagation neural network subunit, a long short-term memory network subunit, a random forest subunit and an extreme gradient boosting subunit.

[0022] Furthermore, the data cloud platform is also used to: train the integrated learning model based on pre-stored training data to obtain a data analysis model.

[0023] Optionally, the regulating switch and each sub-switches are wifi circuit breakers with wifi control function, which are used to receive and execute control commands sent by the control unit.

[0024] The technical solution of the embodiment of the present invention realizes the distribution of electric energy between the power supply and the electrical appliances through the power distribution module, and periodically monitors the working status of the power distribution system through the control module and sends the monitored working data to the data cloud platform, so that the data cloud platform can generate control commands according to the working data. After that, the data cloud platform uses the pre-trained data analysis model to process the working data when receiving the working data, generates a control command and sends it to the control module, and finally controls the power distribution module in response to the received control command through the control module, thereby solving the problems of poor reliability, poor distribution efficiency and inability to support automation of the existing power distribution system, realizing the automation of the power distribution operation in the power grid system, improving the power distribution efficiency of the power grid system, and improving the reliability of the power distribution operation.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a structural schematic diagram of a power distribution system provided according to Embodiment 1 of the present invention;

[0028] Figure 2 It is a structural diagram of a data cloud platform provided according to the second embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 This is a schematic diagram of the structure of a power distribution system provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of distributing power to a power grid and electrical appliances connected to the power grid.

[0033] like Figure 1 As shown, the system includes: a power distribution module 110 , a control module 120 and a data cloud platform 130 .

[0034] The power distribution module 110 is connected in series with the power source and the electrical appliances, the control module 120 is arranged inside the power distribution module 110, and the control module 120 establishes communication connections with the power distribution module 110 and the data cloud platform 130 respectively;

[0035] The power distribution module 110 is used to realize the power distribution between the power source and the electrical appliances.

[0036] The power source may be a distribution box in a power grid system, and the electrical appliance may be a device or equipment that consumes electrical energy in a circuit.

[0037] The control module 120 is used to periodically monitor the working state of the power distribution system 110 and send the monitored working data to the data cloud platform 130, so that the data cloud platform 130 can generate control commands according to the working data; wherein the working data includes: the voltage value of the branch matched with the control module, the current value and other electrical parameters.

[0038] The data cloud platform 130 is used to process the working data using a pre-trained data analysis model when receiving the working data, generate a control command and send it to the control module 120;

[0039] The control module 120 is further configured to control the power distribution module 110 in response to a received control command.

[0040] In a specific implementation of this embodiment, the data collected by the control module 120 is transmitted to the data cloud platform 130 through the network for centralized storage and further analysis and processing. On the data cloud platform 130, the collected data is processed and analyzed using a pre-trained data analysis model to identify the system operating status, predict the risk of equipment failure, and provide decision support, that is, generate control commands. Based on the results of the data analysis and the generated control commands, the control module 120 automatically makes decisions and operations such as load regulation, fault handling, and equipment status optimization on the power distribution module 110. For example, when a fault is found in an electrical appliance connected to the power distribution system 110, the control module 120 can automatically control the power distribution system 110 to cut off the branch circuit matching the electrical appliance according to the control command to protect the safety of the equipment and users.

[0041] In this embodiment, the power distribution module 110 specifically includes: a main switch, a regulating switch, sub-switches and a backup power supply; wherein the input end of the main switch is connected to the power supply for controlling the on and off of the power supply; the regulating switch is connected to the output end of the main switch for controlling the discharge of the backup power supply to the electrical appliance after power failure; the sub-switches are arranged in parallel, the input end of each sub-switch is connected to the output end of the regulating switch, and the output end of each sub-switch is respectively connected to the electrical appliance for individual control of the electrical appliance; the backup power supply is connected to the output end of the regulating switch for providing electrical energy to the power distribution module 110 when the main switch or the regulating switch is disconnected, and for charging itself when both the main switch and the regulating switch are not disconnected.

[0042] Among them, the main switch is a key control element in the entire circuit system. Its input end is directly connected to the power supply, and its main function is to control the on-off path between the power supply and the main switch; further, the regulating switch is connected to the output end of the main switch, and bears the important responsibility of controlling the backup power supply to release electric energy to the electrical appliances after power failure. For example, some electronic switches with intelligent control functions can act as regulating switches; further, each sub-switches are set in parallel, and the input ends of these sub-switches are connected to the output ends of the regulating switches, and their output ends are respectively connected to different electrical appliances. Its function is to be able to control each electrical appliance separately. For example, the common switches that control a single lamp or a single socket belong to sub-switches; further, the backup power supply is connected to the output end of the regulating switch. When the main switch or the regulating switch is in the off-circuit state, the backup power supply can supply the required electric energy to the power distribution module 110 to ensure the continuous operation of important electrical appliances. At the same time, when the main switch and the regulating switch are not in the off-circuit state, that is, when the power is normally supplied, the backup power supply can charge itself to prepare for sudden power failures. For example, a common battery pack or a small uninterruptible power supply (UPS) can be used as a backup power source here.

[0043] Furthermore, the backup power supply specifically includes: a two-way power supply automatic conversion controller, a charger, an inverter and a battery; wherein, one input end of the two-way power supply automatic conversion controller is connected to the output end of the inverter, the other input end is connected to the input end of the charger, the output end is connected to the output end of the regulating switch unit, and the output end of the charger and the input end of the inverter are both connected to the battery; the inverter is used to convert the direct current of the battery into alternating current when the power is off and supply power to the electrical appliances through the two-way power supply automatic conversion controller; the charger is used to charge the battery when the power is normally supplied; and the battery is used to supply power to the inverter when the power is off.

[0044] Among them, the two-way power supply automatic conversion controller is a device that can automatically detect and switch between two power supplies to ensure the continuity and stability of power supply. For example, intelligent switching between the mains and the backup power supply is performed to ensure that power consumption is not affected; further, the charger is a device specifically used to replenish power for the battery. Its working principle is to provide appropriate voltage and current according to the characteristics of the battery so that the battery can be charged safely and efficiently; further, the inverter is an electronic device that can convert direct current into alternating current. In the power system, when a power outage occurs, the inverter plays a key role in converting the direct current stored in the battery into alternating current, and providing power support for electrical appliances through the two-way power supply automatic conversion controller.

[0045] Exemplarily, in this embodiment, the input voltage of the charger can be specifically 220±20V, the output voltage of the charger is 13.76-13.84V, the battery can be a lead-acid battery or a lithium battery, and the battery voltage is 12±3V, the input voltage of the inverter is DC12V, and the output voltage of the inverter is AC220V.

[0046] In this embodiment, the control module 120 includes a sensor unit and a control unit, the output end of the sensor unit is connected to the input end of the control unit, the input end of the sensor is connected to the sub-switch, the output end of the control unit is connected to the electrical appliance, and the number of the control modules 120 is the same as the number of sub-switches in the distribution module; the sensor unit is used to collect various parameter data in the distribution system in real time to obtain the working data of the distribution system and send it to the control unit; the control unit is used to send the control data to the data cloud platform 130; the control unit is also used to control the on and off of the regulating switch or the sub-switch based on the received control command.

[0047] Exemplarily, the control module 120 is composed of a sensor unit and a control unit. The output end of the sensor unit is closely connected to the input end of the control unit, and the input end of the sensor is interconnected with the sub-switch. At the same time, the output end of the control unit is connected to the electrical appliance. It is worth noting that the number of control modules 120 is exactly the same as the number of sub-switches set in the power distribution module; wherein the sensor unit can collect various parameter data in the power distribution system in real time, and obtain the working data of the power distribution system by collecting and processing these data, and send them to the control unit in time, for example, it can collect data of key parameters such as current, voltage, and power; further, on the one hand, it is responsible for transmitting the acquired control data to the data cloud platform 130 to realize remote storage and analysis of data, and on the other hand, it can also accurately control the on-off of the regulating switch or sub-switch based on the received control command, thereby effectively realizing the intelligent management and optimization regulation of the power distribution system.

[0048] Optionally, in this embodiment, the control unit further includes: a modem, a router, a wifi transceiver module, a central control processor and a memory; wherein the central control processor communicates bidirectionally with the memory, the wifi transceiver module communicates bidirectionally with the central control processor, and the modem establishes a communication connection with the sensor unit and the central control processor; the modem is used to perform modulation and demodulation on the received working data, and send the processed working data to the central control processor; the central control processor is used to send the working data to the data cloud platform 130 via the wifi transceiver module, and send the working data to the memory; the memory is used to store the received working data.

[0049] The modem is a device that can convert digital signals and analog signals into each other. It plays a key role in communication, allowing different types of signals to be accurately transmitted in the network. The router is a network device that connects multiple networks or network segments. It can translate data information between different networks to achieve interconnection between different networks. The wifi transceiver module is a component used to realize wireless network connection and data transceiver, allowing devices to wirelessly access the network and exchange data.

[0050] Optionally, the data cloud platform 130 is also used to: train the integrated learning model based on pre-stored training data to obtain a data analysis model.

[0051] Furthermore, the regulating switch and each sub-switch are wifi circuit breakers with wifi control function, which are used to receive and execute control commands sent by the control unit; wherein, the "wifi circuit breaker" is a circuit breaker device combined with wifi communication technology; wherein, the circuit breaker is a switch device that can close, carry and break the current under normal circuit conditions, and can close, carry and break the current under abnormal circuit conditions within a specified time, and the wifi circuit breaker adds a wifi communication module on the basis of the traditional circuit breaker, so that it can connect and communicate with other devices (such as mobile phones, computers, intelligent control systems, etc.) through the wifi network, so that users can remotely control the opening and closing state of the circuit breaker through the corresponding application or system, monitor the current, voltage and other parameters of the circuit in real time, and receive information such as the fault alarm of the circuit breaker. Thereby, intelligent and convenient management and monitoring of the circuit can be realized, and the safety and reliability of electricity use can be improved.

[0052] The technical solution of the embodiment of the present invention realizes the distribution of electric energy between the power supply and the electrical appliances through the power distribution module, and periodically monitors the working status of the power distribution system through the control module and sends the monitored working data to the data cloud platform, so that the data cloud platform can generate control commands according to the working data. After that, the data cloud platform uses the pre-trained data analysis model to process the working data when receiving the working data, generates a control command and sends it to the control module, and finally controls the power distribution module in response to the received control command through the control module, thereby realizing the automation of the power distribution operation in the power grid system, improving the power distribution efficiency of the power grid system, and improving the reliability of the power distribution operation.

[0053] Embodiment 2

[0054] Figure 2 This is a structural diagram of a data cloud platform provided in Embodiment 2 of the present invention. This embodiment is applicable to the situation where, when work data is received, a pre-trained data analysis model is used to process the work data, generate control commands and send them to a control module.

[0055] like Figure 2 As shown, the data cloud platform includes: a base classification unit 210, a meta classification unit 220 and a command generation unit 230.

[0056] Each base classification unit 210 establishes a data connection with the meta classification unit 220 , and the meta classification unit 220 establishes a data connection with the command generation unit 230 .

[0057] Among them, the base classification unit 210 is used to receive the working data sent by the control unit, and preprocess the received working data to obtain multiple preprocessing results and send them to the meta-classification unit 220; the meta-classification unit 220 is used to process each prediction result through an adaptive boosting extreme learning machine model to obtain a monitoring result when it is detected that the number of preprocessing results received within a cycle is consistent with the number of base classification units 210; the command generation unit 230 is used to generate a control command according to the monitoring result and send it to the control unit.

[0058] Among them, the adaptive boosting extreme learning machine model is an extreme learning machine model that integrates an adaptive mechanism and a boosting algorithm. The extreme learning machine is a new type of single hidden layer feedforward neural network learning algorithm, which randomly sets the connection weights between the input layer and the hidden layer and the thresholds of the hidden layer neurons. No adjustment is required during the training process. Only the number of hidden layer neurons needs to be set. The weight of the output layer can be obtained by solving a least squares optimization problem, thereby greatly improving the learning speed; further, adaptability means that the model can automatically adjust its own parameters or structure according to the characteristics and changes of the input data to better adapt to different tasks and data distributions. The adaptive boosting extreme learning machine model can automatically adjust according to the characteristics of the data when processing data and combine the boosting algorithm to optimize the model performance, thereby showing better accuracy and robustness in tasks such as prediction and classification.

[0059] Furthermore, the command generation unit 230 is specifically used to: when it is detected that the monitoring result is normal, not generate a control command; when it is detected that the monitoring result is abnormal, generate a circuit breaker command so that the control unit controls each sub-switches and regulating switch based on the control command.

[0060] Furthermore, the base classification unit 210 includes at least one of a back propagation neural network subunit, a long short-term memory network subunit, a random forest subunit, and an extreme gradient boosting subunit.

[0061] Specifically, the back-propagation neural network subunit is a hardware device equipped with a back-propagation neural network model, the long short-term memory network subunit is a hardware device equipped with a long short-term memory network model, the random forest subunit is a hardware device equipped with a random forest model, and the extreme gradient boosting subunit is a hardware device equipped with an extreme gradient boosting model.

[0062] Furthermore, the back propagation neural network model, long short-term memory network model, random forest model and extreme gradient boosting model are all mature data processing models in the prior art, and this embodiment does not elaborate on the usage and characteristics of the models.

[0063] Specific implementation scenarios

[0064] In order to more clearly illustrate the technical solution provided by the embodiment of the present invention, this embodiment briefly introduces a scenario in which an integrated learning model is trained based on pre-stored training data to obtain a data analysis model.

[0065] 1) Obtain a data set containing multiple sets of working data, and use supervised learning methods to mark the data in the data set as normal or abnormal according to the actual situation;

[0066] 2) If four base classification units are set in the current control module, the data in the data set are evenly divided into four training sets 1-4 and one test set. At the same time, the data in each training set is divided into five equal parts, namely one verification segment and four training segments;

[0067] 3) First, use the four training segments in the first data set to train the first base classification unit, and after the training is completed, input the working data in the validation set into the base classification unit to obtain the output result X1 that matches the base classification unit;

[0068] 4) Similarly, the output results X2, X3 and X4 of the other three base classification units are obtained respectively;

[0069] 5) Take X1, X2, X3 and X4 as input and the label of the actual situation as output to train the ensemble learning model to obtain a trained adaptive boosting extreme learning machine model.

[0070] The technical solution of the embodiment of the present invention receives the working data sent by the control unit through the base classification unit, and preprocesses the received working data to obtain multiple preprocessing results and send them to the meta-classification unit. After that, when the meta-classification unit detects that the number of preprocessing results received within a cycle is consistent with the number of base classification units, the meta-classification unit processes each prediction result through an adaptive boosting extreme learning machine model to obtain a monitoring result. Finally, the command generation unit is used to generate a control command according to the monitoring result and send it to the control unit, thereby realizing the generation and sending of the control command, improving the generation efficiency of the control command, and at the same time realizing the automation of the distribution operation in the power grid system and improving the reliability of the distribution operation.

[0071] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A power distribution system, characterized in that: include: Power distribution module, control module and data cloud platform; The power distribution module is connected in series with the power supply and the electrical appliances, the control module is arranged inside the power distribution module, and the control module establishes communication connections with the power distribution module and the data cloud platform respectively; The power distribution module is used to realize the power distribution between the power source and the electrical appliances; The control module is used to periodically monitor the working status of the power distribution system and send the monitored working data to the data cloud platform, so that the data cloud platform can generate control commands according to the working data; The data cloud platform is used to process the working data using a pre-trained data analysis model when receiving the working data, generate a control command and send it to the control module; The control module is further used to control the power distribution module in response to a received control command.

2. The system according to claim 1, characterized in that The power distribution module specifically includes: a main switch, a regulating switch, various sub-switches and a backup power supply; Wherein, the input end of the main switch is connected to the power supply to control the on and off circuit with the power supply; The regulating switch is connected to the output end of the main switch and is used to control the discharge of the backup power supply to the electrical appliances after power failure; The sub-switches are arranged in parallel, the input end of each sub-switch is connected to the output end of the regulating switch, and the output end of each sub-switch is connected to the electrical appliances respectively, so as to control the electrical appliances individually; The backup power supply is connected to the output end of the regulating switch, and is used to provide power to the power distribution module when the main switch or the regulating switch is disconnected, and to charge itself when both the main switch and the regulating switch are not disconnected.

3. The system according to claim 2, characterized in that The backup power supply specifically includes: a two-way power supply automatic conversion controller, a charger, an inverter and a battery; Wherein, one input end of the two-way power automatic conversion controller is connected to the output end of the inverter, the other input end is connected to the input end of the charger, the output end is connected to the output end of the regulating switch unit, and the output end of the charger and the input end of the inverter are both connected to the battery; The inverter is used to convert the direct current of the battery into alternating current when the power is off and to supply power to the electrical appliances through the two-way power automatic conversion controller; The charger is used to charge the battery during normal power supply; The battery is used to supply power to the inverter when power is off.

4. The system according to claim 1, characterized in that The control module includes a sensor unit and a control unit, the output end of the sensor unit is connected to the input end of the control unit, the input end of the sensor is connected to the sub-switch, the output end of the control unit is connected to the electrical appliance, and the number of the control modules is the same as the number of sub-switches in the power distribution module; The sensor unit is used to collect various parameter data in the power distribution system in real time to obtain the working data of the power distribution system and send it to the control unit; The control unit is used to send the control data to the data cloud platform; The control unit is also used to control the on / off of the regulating switch or the sub-switch based on the received control command.

5. The system according to claim 4, characterized in that The control unit further includes: a modem, a router, a wifi transceiver module, a central control processor and a memory; Wherein, the central control processor communicates with the memory in a two-way manner, the wifi transceiver module communicates with the central control processor in a two-way manner, and the modem establishes a communication connection with the sensor unit and the central control processor; The modem is used to perform modulation and demodulation processing on the received working data and send the processed working data to the central control processor; The central control processor is used to send the working data to the data cloud platform through the wifi transceiver module, and send the working data to the memory; The memory is used to store the received working data.

6. The system according to claim 1, characterized in that The data cloud platform includes at least one base classification unit, a meta classification unit and a command generation unit, each base classification unit establishes a data connection with the meta classification unit, and the meta classification unit establishes a data connection with the command generation unit; The base classification unit is used to receive the working data sent by the control unit, and pre-process the received working data to obtain a plurality of pre-processing results and send them to the meta-classification unit; The meta-classification unit is used to process each prediction result through an adaptive boosting extreme learning machine model to obtain a monitoring result when it is detected that the number of pre-processing results received in one cycle is consistent with the number of base classification units; The command generation unit is used to generate a control command according to the monitoring result and send it to the control unit.

7. The system according to claim 6, characterized in that The command generation unit is specifically used for: When it is detected that the monitoring result is normal, no control command is generated; When it is detected that the monitoring result is abnormal, a circuit breaker command is generated to enable the control unit to control each sub-switch and the regulating switch based on the control command.

8. The system according to claim 6, characterized in that The base classification unit includes at least one of a back propagation neural network subunit, a long short-term memory network subunit, a random forest subunit and an extreme gradient boosting subunit.

9. The system according to claim 1, characterized in that The data cloud platform is also used to: train the integrated learning model based on pre-stored training data to obtain a data analysis model.

10. The system according to claim 2, characterized in that The regulating switch and each sub-switches are wifi circuit breakers with wifi control function, which are used to receive and execute control commands sent by the control unit.

Images