Power supply optimization method and device based on power grid monitoring data, and power supply optimization system

Abstract

The invention discloses a power supply optimization method and device based on power grid monitoring data and a power supply optimization system. The method comprises the following steps: receiving monitoring data of a power system; inputting the monitoring data into a risk assessment model to obtain a risk level; determining the power utilization priority of the power utilization equipment according to the demand side risk level; obtaining the current total demand power supply quantity of each electric device and the current power supply quantity of the power grid side, and calculating the difference value; when the difference value is smaller than zero and / or the risk level of the power grid side is higher than a preset level threshold value, the power grid side is controlled to stop supplying power, and the power supply priority of each power supply device of the virtual power plant side is determined according to the risk level of the virtual power plant side; and controlling each power supply device to supply power in sequence according to the power supply priority by using the virtual power plant, so that each electric device is supplied with power in sequence according to the power utilization priority. According to the invention, the technical problem of unreasonable power supply to the demand side caused by difficulty in power consumption scheduling in combination with the power consumption risk of the power grid in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid environment monitoring, and in particular to a power supply optimization method and device based on power grid monitoring data, and a power supply optimization system. Background Art

[0002] Existing methods for monitoring the power grid environment have the following defects: 1) The current priority of power dispatch is generally set in advance, and it is difficult to automatically update the priority; it is impossible to analyze power consumption risks based on the power grid environment monitoring results; virtual power plants are dispatched and controlled according to priority, resulting in the power dispatch process being unable to automatically prioritize according to the current power consumption risk level, affecting the reasonable power supply response on the demand side; 2) The power grid environment monitoring results can be superimposed on the power grid monitoring video for compressed transmission, but the data decoding time is long, the storage space is large, and it is difficult to achieve targeted transmission and storage, resulting in greater viewing and storage pressure on the management platform.

[0003] Currently, no effective solution has been proposed to address the problem that the above-mentioned related technologies are difficult to carry out power dispatch in combination with the power consumption risks of the power grid, resulting in unreasonable power supply to the demand side. Summary of the invention

[0004] The embodiments of the present invention provide a power supply optimization method and device, and a power supply optimization system based on power grid monitoring data, so as to at least solve the technical problem in the related technology that it is difficult to carry out power dispatch in combination with the power consumption risk of the power grid, resulting in unreasonable power supply to the demand side.

[0005] According to one aspect of an embodiment of the present invention, a power supply optimization method based on power grid monitoring data is provided, comprising: receiving monitoring data obtained by monitoring a power system, wherein the monitoring data comprises: first monitoring data obtained by monitoring a power grid side of the power system, second monitoring data obtained by monitoring a virtual power plant side of the power system, and third monitoring data obtained by monitoring a power demand side of the power system; inputting the monitoring data into a risk assessment model, so as to process the monitoring data using the risk assessment model to obtain a risk level corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple sets of training data, each of the multiple sets of training data comprises: sample monitoring data, and a sample risk level corresponding to the sample monitoring data; determining the power priority of each power-consuming device on the power demand side according to the demand-side risk level, wherein the demand-side risk level is the risk level corresponding to the second monitoring data in the risk level. The risk level corresponding to the data; obtaining the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculating the demand difference between the total demand power supply and the power supply, wherein the total demand power supply is the sum of the current demand power supplies of each of the power-consuming devices; when the demand difference is less than zero and / or the risk level on the power grid side is higher than the preset level threshold, controlling the power grid side to stop power supply, and determining the power supply priority of each power supply device on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the power grid side is the risk level in the risk level corresponding to the first monitoring data, and the risk level on the virtual power plant side is the risk level in the risk level corresponding to the third monitoring data; sending the power consumption priority and the power supply priority to the virtual power plant, so as to use the virtual power plant to control each of the power supply devices to supply power to each of the power-consuming devices in turn according to the power supply priority, so that each of the power-consuming devices can be powered in turn according to the power consumption priority.

[0006] Optionally, before inputting the monitoring data into a risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, the power supply optimization method based on power grid monitoring data also includes: obtaining multiple groups of historical monitoring data within a historical time period, wherein each of the multiple groups of historical monitoring data includes multiple items of the historical monitoring data; performing data cleaning on the multiple groups of historical monitoring data to remove invalid data and duplicate data in the multiple groups of historical monitoring data; performing format conversion on the multiple groups of historical monitoring data to obtain multiple groups of historical monitoring data in the same format; separately determining the historical risk level of the historical monitoring data corresponding to each group of the multiple groups of historical monitoring data; and training using the multiple groups of historical monitoring data and the historical risk levels corresponding to the historical monitoring data through a support vector machine classification algorithm to obtain the risk assessment model.

[0007] Optionally, the historical risk level of the historical monitoring data corresponding to each group of the multiple groups of historical monitoring data is determined separately, including: determining the combination of multiple items of the historical monitoring data in each group of the historical monitoring data as a historical monitoring data group; comparing each item of the historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; and determining the historical risk level corresponding to the historical monitoring data group based on the comparison result.

[0008] Optionally, determining the historical risk level corresponding to the historical monitoring data group according to the comparison result includes: when the comparison result indicates that each item of the historical monitoring data in the historical monitoring data group is within the predetermined range, determining that the historical risk level corresponding to the historical monitoring data group is a safe level; when the comparison result indicates that there is historical monitoring data in the historical monitoring data group that is not within the predetermined range, determining the degree of deviation of the historical monitoring data exceeding the predetermined range; when the degree of deviation of at least two items of the historical monitoring data in the historical monitoring data group is not greater than a first deviation threshold or the degree of deviation of at least one item of the historical monitoring data is greater than a second deviation threshold and not greater than a third deviation threshold, determining that the historical risk level corresponding to the historical monitoring data group is a low risk level, wherein the second deviation threshold is smaller than the first deviation threshold, and the first deviation threshold is smaller than the third deviation threshold; when the deviation degree of at least two of the historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or when the deviation degree of at least one of the historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, it is determined that the historical risk level corresponding to the historical monitoring data group is a medium risk level, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; when the deviation degree of at least two of the historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold, or when the deviation degree of at least one of the historical monitoring data is greater than the fifth deviation threshold, it is determined that the historical risk level corresponding to the historical monitoring data group is a high risk level.

[0009] Optionally, determining the power consumption priority of each of the power consumption devices on the power consumption demand side according to the demand difference and the risk level on the demand side includes: obtaining the device type and the required power supply of each of the power consumption devices on the power consumption demand side; and calculating the power consumption demand degree of each of the power consumption devices based on the device type, the required power supply and the risk level on the demand side using a first formula, wherein the first formula is: Y represents the demand level, D represents the equipment type, E represents the first risk value of the demand side risk level, C represents the required power supply, 总 Representing the demand difference; sorting each of the electrical devices in descending order according to the degree of electricity demand to obtain a first sorting result; determining the electricity priority of each of the electrical devices according to the first sorting result, wherein the electrical device that is ranked higher in the first sorting result has a higher electricity priority.

[0010] Optionally, the power supply priority of each power supply device on the virtual power plant side is determined according to the risk level on the virtual power plant side, including: obtaining the current electricity price and the stored power of each power supply device; calculating the power supply capacity index of each power supply device based on the electricity price, the stored power and the risk level on the virtual power plant side using a second formula, wherein the second formula is: Z = (H*10% + G*40%) / (F*50%), Z represents the power supply capacity index, H represents the second risk value of the risk level on the virtual power plant side, G represents the stored power, and F represents the electricity price; sorting each power supply device in descending order according to the power supply capacity index to obtain a second sorting result; determining the power supply priority of each power supply device according to the second sorting result, wherein the power supply device that is ranked higher in the second sorting result has a higher power supply priority.

[0011] Optionally, the power supply optimization method based on power grid monitoring data also includes: dividing the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safety monitoring data according to the risk level; removing the safety monitoring data from the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: the high-risk monitoring data, the medium-risk monitoring data and the low-risk monitoring data; transmitting the risk monitoring data to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes the high-risk monitoring data and / or the medium-risk monitoring data.

[0012] According to another aspect of an embodiment of the present invention, a power supply optimization device based on power grid monitoring data is also provided, including: a receiving unit, used to receive monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; a first acquisition unit, used to input the monitoring data into a risk assessment model, so as to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple groups of training data, each of the multiple groups of training data includes: sample monitoring data, and a sample risk level corresponding to the sample monitoring data; a first determination unit, used to determine the power priority of each power-consuming device on the power demand side according to the demand-side risk level, wherein the demand-side risk level is the risk level corresponding to the second monitoring data in the risk level. a risk level corresponding to the measured data; a second acquisition unit, used to obtain the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total demand power supply and the power supply, wherein the total demand power supply is the sum of the current demand power supplies of each of the power-consuming devices; a second determination unit, used to control the power grid side to stop power supply when the demand difference is less than zero and / or the risk level on the power grid side is higher than a preset level threshold, and determine the power supply priority of each power supply device on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the power grid side is the risk level corresponding to the first monitoring data in the risk level, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk level; a sending unit, used to send the power consumption priority and the power supply priority to the virtual power plant, so as to use the virtual power plant to control each of the power supply devices to supply power to each of the power-consuming devices in turn according to the power supply priority, so that each of the power-consuming devices is powered in turn according to the power consumption priority.

[0013] Optionally, the power supply optimization device based on power grid monitoring data also includes: a third acquisition unit, used to acquire multiple groups of historical monitoring data within a historical time period before inputting the monitoring data into a risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein each of the multiple groups of historical monitoring data includes multiple items of the historical monitoring data; a removal unit, used to perform data cleaning on the multiple groups of historical monitoring data to remove invalid data and duplicate data in the multiple groups of historical monitoring data; a fourth acquisition unit, used to perform format conversion on the multiple groups of historical monitoring data to obtain multiple groups of historical monitoring data in the same format; a third determination unit, used to separately determine the historical risk level of the historical monitoring data corresponding to each group of the multiple groups of historical monitoring data; a fifth acquisition unit, used to train using the multiple groups of historical monitoring data and the historical risk levels corresponding to the historical monitoring data through a support vector machine classification algorithm to obtain the risk assessment model.

[0014] Optionally, the third determination unit includes: a first determination module, used to determine that the combination of multiple historical monitoring data in each group of historical monitoring data is a historical monitoring data group; a first acquisition module, used to compare each item of historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; and a second determination module, used to determine the historical risk level corresponding to the historical monitoring data group based on the comparison result.

[0015] Optionally, the second determination module includes: a first determination submodule, used to determine that the historical risk level corresponding to the historical monitoring data group is a safe level when the comparison result indicates that each of the historical monitoring data in the historical monitoring data group is within the predetermined range; a second determination submodule, used to determine the degree of deviation of the historical monitoring data exceeding the predetermined range when the comparison result indicates that there is historical monitoring data in the historical monitoring data group that is not within the predetermined range; a third determination submodule, used to determine that the historical risk level corresponding to the historical monitoring data group is a low risk level when the degree of deviation of at least two of the historical monitoring data in the historical monitoring data group is not greater than a first deviation threshold or the degree of deviation of at least one of the historical monitoring data is greater than the second deviation threshold and not greater than a third deviation threshold, wherein the second deviation threshold is less than the first deviation threshold. A deviation threshold, the first deviation threshold is smaller than the third deviation threshold; a fourth determination submodule, used to determine that the historical risk level corresponding to the historical monitoring data group is a medium risk level when the deviation degree of at least two of the historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or the deviation degree of at least one of the historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; a fifth determination submodule, used to determine that the historical risk level corresponding to the historical monitoring data group is a high risk level when the deviation degree of at least two of the historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold, or the deviation degree of at least one of the historical monitoring data is greater than the fifth deviation threshold.

[0016] Optionally, the first determination unit includes: a second acquisition module, used to acquire the device type and the required power supply of each of the power-consuming devices on the power demand side; a first calculation module, used to calculate the power demand degree of each of the power-consuming devices using a first formula based on the device type, the required power supply and the risk level on the demand side, wherein the first formula is: Y represents the demand level, D represents the equipment type, E represents the first risk value of the demand side risk level, C represents the required power supply, 总 Represents the demand difference; a third acquisition module, used to sort each of the electrical devices in descending order according to the degree of electricity demand to obtain a first sorting result; a third determination module, used to determine the electricity priority of each of the electrical devices according to the first sorting result, wherein the electrical device that is ranked higher in the first sorting result has a higher electricity priority.

[0017] Optionally, the second determination unit includes: a fourth acquisition module, used to obtain the current electricity price and the stored power of each of the power supply devices; a second calculation module, used to calculate the power supply capacity index of each of the power supply devices based on the electricity price, the stored power and the risk level on the virtual power plant side using a second formula, wherein the second formula is: Z = (H*10% + G*40%) / (F*50%), Z represents the power supply capacity index, H represents the second risk value of the risk level on the virtual power plant side, G represents the stored power, and F represents the electricity price; a fifth acquisition module, used to sort each of the power supply devices in descending order according to the power supply capacity index to obtain a second sorting result; a fourth determination module, used to determine the power supply priority of each of the power supply devices according to the second sorting result, wherein the power supply device that is ranked higher in the second sorting result has a higher power supply priority.

[0018] Optionally, the power supply optimization device based on power grid monitoring data also includes: a division unit, used to divide the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safety monitoring data according to the risk level; a fifth acquisition unit, used to remove the safety monitoring data in the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: the high-risk monitoring data, the medium-risk monitoring data and the low-risk monitoring data; a transmission unit, used to transmit the risk monitoring data to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes the high-risk monitoring data and / or the medium-risk monitoring data.

[0019] According to another aspect of an embodiment of the present invention, a power supply optimization system based on power grid monitoring data is also provided. The power supply optimization system based on power grid monitoring data uses any of the power supply optimization methods based on power grid monitoring data described above, including: an environmental monitoring and acquisition module, used to collect monitoring data on the power grid side, the power demand side and the virtual power plant side in the power system; an edge intelligent gateway, used to receive the monitoring data collected by the environmental monitoring and acquisition module, and process the monitoring data to obtain the power priority of each power-consuming device on the power demand side, the power supply priority of each power supply device on the virtual power plant side, and the risk levels corresponding to the power grid side, the power demand side and the virtual power plant side; the virtual power plant, used to monitor the power supply priority of each power supply device on the power demand side and the power supply priority of each power supply device on the virtual power plant side according to the edge intelligent gateway; The electricity usage priority and the power supply priority obtained by processing the monitoring data control the power supply equipment on the virtual power plant side to supply power to the power equipment on the power demand side; a 5G base station is used to transmit the risk level, the electricity usage priority, the power supply priority and the risk monitoring data corresponding to the monitoring data, wherein the risk monitoring data is the data obtained by removing the data with the risk level as the safety level in the monitoring data; a management platform is used to receive the risk level, the electricity usage priority, the power supply priority and the risk monitoring data corresponding to the monitoring data transmitted by the 5G base station, and to issue a warning signal when the risk monitoring data contains the monitoring data of high risk level and medium risk level.

[0020] Optionally, the environmental monitoring and acquisition module includes: a video monitor for collecting video data on the grid side, the power demand side and the virtual power plant side in the power system; a temperature and humidity sensor for collecting temperature data and humidity data on the grid side, the power demand side and the virtual power plant side in the power system; a smoke sensor for collecting smoke data on the grid side, the power demand side and the virtual power plant side in the power system; a harmful gas sensor for collecting harmful gas data on the grid side, the power demand side and the virtual power plant side in the power system; and a power sensor for collecting power operation data on the grid side, the power demand side and the virtual power plant side in the power system.

[0021] Optionally, the edge intelligent gateway includes: a risk assessment module, used to evaluate the risk levels of the power grid side, the power demand side and the virtual power plant side according to the monitoring data; a power priority update module, used to update the power priority of each power device on the power demand side according to the risk level of the power demand side; and a power supply priority update module, used to update the power supply priority of each power supply device on the virtual power plant side according to the risk levels of the power grid side and the virtual power plant side.

[0022] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned power supply optimization methods based on power grid monitoring data.

[0023] According to another aspect of an embodiment of the present invention, a processor is further provided, the processor being used to run a program, wherein when the program is run, any one of the above-mentioned power supply optimization methods based on power grid monitoring data is executed.

[0024] According to another aspect of an embodiment of the present invention, a computer program product is further provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned power supply optimization methods based on power grid monitoring data is executed.

[0025] In an embodiment of the present invention, monitoring data obtained by monitoring an electric power system is received, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the electric power system, second monitoring data obtained by monitoring the virtual power plant side of the electric power system, and third monitoring data obtained by monitoring the power demand side of the electric power system; the monitoring data is input into a risk assessment model, so as to process the monitoring data using the risk assessment model to obtain risk levels corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple sets of training data, and each of the multiple sets of training data includes: sample monitoring data, and sample risk levels corresponding to the sample monitoring data; the power consumption priority of each electric equipment on the power demand side is determined according to the demand side risk level, wherein the demand side risk level is the risk level corresponding to the second monitoring data in the risk level. Risk level; obtain the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total demand power supply and the power supply, wherein the total demand power supply is the sum of the current demand power supplies of each power-consuming device; when the demand difference is less than zero and / or the risk level on the power grid side is higher than the preset level threshold, control the power grid side to stop power supply, and determine the power supply priority of each power supply device on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the power grid side is the risk level corresponding to the first monitoring data in the risk level, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk level; send the power consumption priority and the power supply priority to the virtual power plant, so as to use the virtual power plant to control each power supply device to supply power to each power consumer in turn according to the power supply priority, so that each power consumer can be powered in turn according to the power consumption priority. Through the above technical scheme, the grid risk is analyzed according to the grid monitoring data, and the priority of power dispatch is updated in combination with the risk level obtained by the analysis, so as to control the power supply equipment to supply power to the power equipment in sequence according to the power supply priority, and the power equipment is also powered in sequence according to the power supply priority. The technical effect of automatically updating the priority of power dispatch in combination with the power consumption risk of the power grid so as to supply power to the demand side more reasonably is achieved, thereby solving the technical problem in related technologies that it is difficult to carry out power dispatch in combination with the power consumption risk of the power grid, resulting in unreasonable power supply to the demand side. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 It is a hardware structure block diagram of a mobile terminal of a power supply optimization method based on power grid monitoring data according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of a power supply optimization method based on power grid monitoring data according to an embodiment of the present invention;

[0029] Figure 3 is a flow chart of determining power usage priority according to an embodiment of the present invention;

[0030] Figure 4 is a flow chart of determining power supply priority according to an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of a power supply optimization device based on power grid monitoring data according to an embodiment of the present invention;

[0032] Figure 6 is a schematic diagram of a power supply optimization system based on power grid monitoring data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] As introduced in the background technology, it is difficult to combine the power consumption risk of the power grid to perform power dispatch in the related technology, resulting in unreasonable power supply to the demand side. In view of the above defects, a power supply optimization method and device based on power grid monitoring data and a power supply optimization system are provided in the embodiments of the present invention.

[0036] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0037] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a power supply optimization method based on power grid monitoring data according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0038] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the power supply optimization method based on power grid monitoring data in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks and combinations thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] According to an embodiment of the present invention, a method embodiment of a power supply optimization method based on power grid monitoring data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] Figure 2 is a flow chart of a power supply optimization method based on power grid monitoring data according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0041] Step S202, receiving monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the electricity demand side of the power system.

[0042] In this embodiment, the environmental monitoring and collection system can be used to monitor the power system to obtain monitoring data on the grid side, the power demand side, and the virtual power plant side.

[0043] For example, the environmental monitoring and acquisition system may include video monitors and sensor components. The sensor components include temperature and humidity sensors, smoke sensors, harmful gas sensors, and power sensors. The environmental monitoring and acquisition system can obtain various detection information / data from the power grid, electricity demand side, and virtual power plant side, and then the collected data can be transmitted to the edge intelligent gateway. After receiving the monitoring data obtained by the environmental monitoring and acquisition system from monitoring the power system, the edge intelligent gateway can further analyze and process the monitoring data.

[0044] It should be noted that the monitoring data here include: first monitoring data obtained by monitoring the grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side, and third monitoring data obtained by monitoring the electricity demand side.

[0045] Specifically, the video monitor can record videos of the grid side, the power demand side, and the virtual power plant side to obtain video information; the temperature and humidity sensors detect the temperature and humidity data of the grid side, the power demand side, and the virtual power plant side; the smoke sensors detect the smoke data of the grid side, the power demand side, and the virtual power plant side; the harmful gas sensors detect the harmful gas data of the grid side, the power demand side, and the virtual power plant side; the power sensors detect the power operation status data of the grid side, the power demand side, and the virtual power plant side; and the detected information / data can be transmitted to the edge intelligent gateway.

[0046] Step S204, input the monitoring data into the risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein the risk assessment model is trained using multiple sets of training data through machine learning, and each of the multiple sets of training data includes: sample monitoring data, and sample risk levels corresponding to the sample monitoring data.

[0047] In this embodiment, the received monitoring data may be processed using a risk assessment model to obtain a risk level of a possible risk in the power system.

[0048] It should be noted that here, in fact, three risk assessment models are used to monitor the grid side of the power system to obtain the first monitoring data, the second monitoring data is obtained by monitoring the virtual power plant side, and the third monitoring data is obtained by monitoring the electricity demand side. That is, the first monitoring data is processed by the grid side risk assessment model to obtain the risk level of the grid side; the third monitoring data is processed by the electricity demand side risk assessment model to obtain the risk level of the electricity demand side; the second monitoring data is processed by the virtual power plant side risk assessment model to obtain the risk level of the virtual power plant side.

[0049] In essence, these three models are all risk assessment models, and their establishment and training methods are the same. Below, they are collectively referred to as risk assessment models and their establishment and training methods are described in detail.

[0050] In an optional embodiment of the present invention, before the monitoring data is input into a risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, the power supply optimization method based on power grid monitoring data also includes: obtaining multiple groups of historical monitoring data within a historical time period, wherein each of the multiple groups of historical monitoring data includes multiple items of historical monitoring data; performing data cleaning on the multiple groups of historical monitoring data to remove invalid data and duplicate data in the multiple groups of historical monitoring data; performing format conversion on the multiple groups of historical monitoring data to obtain multiple groups of historical monitoring data in the same format; respectively determining the historical risk level of each group of historical monitoring data corresponding to the multiple groups of historical monitoring data; and training using the multiple groups of historical monitoring data and the historical risk levels corresponding to the historical monitoring data through a support vector machine classification algorithm to obtain a risk assessment model.

[0051] Specifically, the historical monitoring data can be preprocessed to remove invalid values ​​and duplicate data; then the historical monitoring data can be mapped to a unified attribute through a mapping module (for example, "voltage 3 Ford" and "U 3V" are unified as "voltage 3V"); then the risk level corresponding to the group of historical monitoring data is determined according to the number of items in each group of historical monitoring data that exceed a predetermined range; finally, the historical monitoring data is classified according to the risk level (also known as the power state type) obtained above, and each of them is used as a training sample, and various training samples are used to train the SVM classifier support vector machine classification algorithm to obtain a power state SVM classification algorithm model (i.e., a risk assessment model) corresponding to each power state type.

[0052] Each set of historical monitoring data here may include video data, temperature and humidity data, smoke data, harmful gas data within the same historical monitoring time period, power operation status data on the power grid side, power demand side, and virtual power plant side, etc. Of course, other data that may be collected during the monitoring of the power grid may also be included here, and there is no specific restriction here.

[0053] The risk levels here can be specifically divided into: high risk level, medium risk level, low risk level and safety level, and their priority is: high risk level > medium risk level > low risk level > safety level. The higher the priority, the higher the risk.

[0054] In the above-mentioned embodiment of the present invention, the historical risk level of each group of historical monitoring data corresponding to multiple groups of historical monitoring data is determined respectively, including: determining the combination of multiple historical monitoring data in each group of historical monitoring data as a historical monitoring data group; comparing each historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; and determining the historical risk level corresponding to the historical monitoring data group according to the comparison result.

[0055] Specifically, each item of historical monitoring data in each group of historical monitoring data can be compared with the corresponding conventional standard range (predetermined range, the same below), and the risk level corresponding to the group of historical monitoring data can be specifically judged by judging the number and degree of historical monitoring data exceeding the conventional standard range.

[0056] In a specific embodiment of the present invention, the historical risk level corresponding to the historical monitoring data group is determined according to the comparison result, including: when the comparison result indicates that each historical monitoring data in the historical monitoring data group is within a predetermined range, determining that the historical risk level corresponding to the historical monitoring data group is a safe level; when the comparison result indicates that there is historical monitoring data in the historical monitoring data group that is not within the predetermined range, determining the deviation of the historical monitoring data beyond the predetermined range; when the deviation of at least two historical monitoring data in the historical monitoring data group is not greater than a first deviation threshold or the deviation of at least one historical monitoring data is greater than a second deviation threshold and not greater than a third deviation threshold, determining that the historical risk level corresponding to the historical monitoring data group is a low risk level, Among them, the second deviation threshold is smaller than the first deviation threshold, and the first deviation threshold is smaller than the third deviation threshold; when the deviation degree of at least two historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or the deviation degree of at least one historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, the historical risk level corresponding to the historical monitoring data group is determined to be a medium risk level, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; when the deviation degree of at least two historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold, or the deviation degree of at least one historical monitoring data is greater than the fifth deviation threshold, the historical risk level corresponding to the historical monitoring data group is determined to be a high risk level.

[0057] For example, when at least one of the monitoring data exceeds the conventional standard range by 10%, or at least two of the monitoring data exceed the conventional standard range by 6%, it indicates a high risk level; when at least one of the monitoring data exceeds the conventional standard range by 4% but less than or equal to 10%, or at least two of the monitoring data exceed the conventional standard range by 3% but less than or equal to 6%, it indicates a medium risk level; when at least one of the monitoring data exceeds the conventional standard range by 2% but less than or equal to 4%, or at least two of the monitoring data exceed the conventional standard range but less than or equal to 3%, it indicates a low risk level; when the monitoring data is within the conventional standard range, it indicates a safe level.

[0058] It should be noted that when the characteristics of the monitoring data correspond to both low-risk level SVM classifier and medium-risk level SVM classifier, that is, when it meets both the low-risk level and the medium-risk level types, the medium-risk level SVM classifier is selected for identification to obtain the power status type, and the medium-risk level is used as the power status type; for other monitoring data whose characteristics correspond to certain two types, they can also be processed in this way.

[0059] Step S206, determining the power usage priority of each power-consuming device on the power demand side according to the demand side risk level, wherein the demand side risk level is the risk level in the risk level corresponding to the second monitoring data.

[0060] In this embodiment, the power priority of each power-consuming device on the power demand side may be updated according to the power state type (ie, risk level on the power demand side) on the power demand side obtained by analyzing in the above steps.

[0061] According to the above embodiment of the present invention, in the above step S206, the power consumption priority of each power-consuming device on the power demand side is determined according to the demand difference and the risk level on the demand side, including: obtaining the device type and the required power supply of each power-consuming device on the power demand side; and calculating the power consumption demand degree of each power-consuming device based on the device type, the required power supply and the risk level on the demand side using the first formula, wherein the first formula is: Y represents the degree of demand, D represents the type of equipment, E represents the first risk value of the demand side risk level, C represents the required power supply, and C represents the 总 Represents the demand difference; sorts each electrical device in descending order according to the degree of electricity demand to obtain a first sorting result; determines the electricity priority of each electrical device according to the first sorting result, wherein the electrical device with a higher ranking in the first sorting result has a higher electricity priority.

[0062] Combine the following Figure 3 The above embodiments of the present invention are described in detail. Figure 3 is a flow chart of determining power usage priority according to an embodiment of the present invention.

[0063] like Figure 3 As shown, the specific steps for updating the power priority of each power-consuming device on the power demand side are as follows: 1) According to the current power consumption situation and the expected power consumption time, the total power supply demand A on the power demand side is estimated in real time. The expected power consumption time here is based on the historical usage time; 2) The demand difference C between the power supply B on the power grid side within the expected power consumption time and the total power supply demand A on the power demand side is calculated 总 ; When the demand difference C 总 When <0, it means that the power supply on the grid side is expected to be insufficient; 3) Combined with the power state type, required power supply, and object type on the power demand side, according to the formula: Calculate the importance coefficient Y of each device on the power demand side, where the object types include four categories: residential, commercial, industrial and others, and assign them D: residential = 10, commercial = 7, industrial = 5, other = 1, and the power status type on the power demand side, assign them E: high risk level = 0, medium risk level = 3, low risk level = 5, safe power = 10, and C represents the required power supply of a single power device on the power demand side within the expected power consumption time; 4) After calculating the importance coefficient Y of each device on the power demand side, and sort them from large to small, according to this sorting, set the power priority of each power device from high to low; so that the power demand side devices with high power priority can be powered first.

[0064] For example, when the power supply can be limited to meeting the needs of the first 100 power demand-side devices with high priority, these 100 devices will be powered first; the remaining devices will not be powered temporarily, and will be powered when it is determined later that the needs of the subsequent power demand-side devices can continue to be met.

[0065] Step S208, obtaining the total power demand of each power-consuming device on the power demand side and the current power supply on the grid side, and calculating the demand difference between the total power demand and the power supply, wherein the total power demand is the sum of the current power demand of each power-consuming device.

[0066] In this embodiment, the total power demand A of each power-consuming device on the power demand side and the current power supply B on the power grid side can be obtained, and the demand difference C between them can be calculated. 总 , by the demand difference C 总 Make a judgment and estimate whether the current power supply on the grid side is sufficient.

[0067] Step S210, when the demand difference is less than zero and / or the risk level on the grid side is higher than the preset level threshold, control the grid side to stop power supply, and determine the power supply priority of each power supply equipment on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the grid side is the risk level in the risk level corresponding to the first monitoring data, and the risk level on the virtual power plant side is the risk level in the risk level corresponding to the third monitoring data.

[0068] In this embodiment, the demand difference C 总Less than zero (that is, the power supply on the grid side cannot meet the total power supply demand of each power-consuming device on the power demand side), or the power status type on the grid side is high or medium risk level (that is, higher than the preset level threshold, the preset level threshold here can be a low risk level, and higher than the preset level threshold is a high risk level or a medium risk level), or these two states occur at the same time, it means that the current grid side is no longer suitable for continuing to supply power, and it is necessary to control the grid side to stop power supply and send an early warning report to the 5G base station, so that the early warning report can be transmitted to the management platform through the 5G base station; at the same time, the power supply equipment on the virtual power plant side is controlled to continue power supply; here it is necessary to further update the power supply priority of each power supply equipment on the virtual power plant side according to the power status type on the virtual power plant side (that is, the risk level on the virtual power plant side) obtained by analyzing the above steps.

[0069] According to the above embodiment of the present invention, in the above step S210, the power supply priority of each power supply equipment on the virtual power plant side is determined according to the risk level on the virtual power plant side, including: obtaining the current electricity price and the stored power of each power supply equipment; calculating the power supply capacity index of each power supply equipment based on the electricity price, the stored power and the risk level on the virtual power plant side using the second formula, wherein the second formula is: Z = (H*10% + G*40%) / (F*50%), Z represents the power supply capacity index, H represents the second risk value of the risk level on the virtual power plant side, G represents the stored power, and F represents the electricity price; sorting each power supply equipment in descending order according to the power supply capacity index to obtain a second sorting result; determining the power supply priority of each power supply equipment according to the second sorting result, wherein the power supply equipment with a higher ranking in the second sorting result has a higher power supply priority.

[0070] Combine the following Figure 4 The above embodiments of the present invention are described in detail. Figure 4 is a flow chart of determining power supply priority according to an embodiment of the present invention.

[0071] like Figure 4 As shown, the specific steps for updating the power supply priority of each power supply equipment on the virtual power plant side are as follows: 1) In combination with the power status type on the virtual power plant side, the stored electricity G and the price F, the priority coefficient Z of each power supply equipment on the virtual power plant side is calculated according to the formula: Z = (H*10% + G*40%) / (F|50%), wherein the risk level corresponding to the power status type on the virtual power plant side is assigned a value H: high risk level = 0, medium risk level = 0, low risk level = 5, safe power = 10; 2) After calculating the priority coefficient Z of each device on the virtual power plant side, and sorting them from large to small, according to this sorting, the power supply priority is set from high to low; so as to give priority to the power supply equipment on the virtual power plant side with high power supply priority for power supply.

[0072] Here, you can first roughly determine how many power supply devices on the virtual power plant side are needed for power supply based on the demand difference, and then select the corresponding number of power supply devices for power supply according to the power supply priority; for example, based on the demand difference, it is concluded that the first 10 virtual power plant side power supply devices with high power supply priority need to be used for power supply; it may also be necessary to use all the virtual power plant side power supply devices for power supply.

[0073] Step S212, sending the power consumption priority and the power supply priority to the virtual power plant, so as to utilize the virtual power plant to control each power supply device to supply power to each power consumption device in turn according to the power supply priority, so that each power consumption device can be supplied with power in turn according to the power consumption priority.

[0074] In this embodiment, the virtual power plant and the edge intelligent gateway can be communicated with each other, and the edge intelligent gateway can send the analyzed power consumption priority of each power consumption device on the power demand side and the power supply priority of each power supply device on the virtual power plant side to the virtual power plant, so that the virtual power plant can be used to control the power supply equipment on the virtual power plant side to supply power to the power consumption devices on the power demand side in turn according to the power supply priority, and each power consumption device on the power demand side can be powered in turn according to the power consumption priority; in addition, the virtual power plant can also charge and store electricity from the power grid during off-peak hours.

[0075] In an optional embodiment of the present invention, the power supply optimization method based on power grid monitoring data also includes: dividing the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safety monitoring data according to the risk level; removing the safety monitoring data in the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: high-risk monitoring data, medium-risk monitoring data and low-risk monitoring data; transmitting the risk monitoring data to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes high-risk monitoring data and / or medium-risk monitoring data.

[0076] In this embodiment, the edge intelligent gateway can intercept the video information recorded by the video monitors on the grid side, the power demand side, and the virtual power plant side according to the time parameters corresponding to the power status type, and obtain high-risk fragments, medium-risk fragments, low-risk fragments and safe fragments respectively; eliminate the safe fragments, and combine the remaining fragments with the corresponding power status type and time, compress them and send them to the 5G base station, and the 5G base station transmits them to the management platform; after receiving the data transmitted by the 5G base station, the management platform can monitor the power grid in real time. In addition, if the data received by the management platform includes high-risk fragments or medium-risk fragments on the grid side, an early warning signal is issued to prompt the staff to perform maintenance; in addition, the management platform only receives high-risk fragments, medium-risk fragments, and low-risk fragments, and can quickly obtain the corresponding power status type, which is convenient for maintenance personnel to obtain the monitoring results, which is beneficial to subsequent maintenance. By eliminating a large number of safe fragments, the data decoding time and the storage space occupied are reduced, targeted transmission and storage are achieved, and the viewing and storage pressure of the management platform is reduced.

[0077] It can be seen from the above steps that through the technical solution provided by the above embodiments of the present invention, it is possible to receive monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; the monitoring data is input into the risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein the risk assessment model is trained using multiple groups of training data by machine learning, and each of the multiple groups of training data includes: sample monitoring data, and sample risk levels corresponding to the sample monitoring data; the power priority of each power-consuming device on the power demand side is determined according to the demand-side risk level, wherein the demand-side risk level is the risk level corresponding to the second monitoring data in the risk level; the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side are obtained, and the demand difference between the total demand power supply and the power supply is calculated, wherein the total demand power supply The power quantity is the sum of the current power demand of each power-consuming device; when the demand difference is less than zero and / or the risk level on the grid side is higher than the preset level threshold, the grid side is controlled to stop power supply, and the power supply priority of each power supply device on the virtual power plant side is determined according to the risk level on the virtual power plant side, wherein the risk level on the grid side is the risk level corresponding to the first monitoring data in the risk level, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk level; the power consumption priority and the power supply priority are sent to the virtual power plant, so that the virtual power plant can be used to control each power supply device to supply power to each power-consuming device in turn according to the power supply priority, so that each power-consuming device can be powered in turn according to the power consumption priority, thereby achieving the purpose of analyzing the power grid risk according to the grid monitoring data, and updating the priority of power dispatching in combination with the risk level obtained by the analysis, so as to control the power supply equipment to supply power to the power-consuming device in turn according to the power supply priority, and the power-consuming device can also be powered in turn according to the power consumption priority, thereby achieving the technical effect of automatically updating the priority of power dispatching in combination with the power consumption risk of the grid to supply power to the demand side more reasonably.

[0078] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that it is difficult to carry out power dispatch in combination with the power consumption risk of the power grid, resulting in unreasonable power supply to the demand side.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0081] According to an embodiment of the present invention, there is also provided a power supply optimization device based on power grid monitoring data for implementing the above-mentioned power supply optimization method based on power grid monitoring data. Figure 5 is a schematic diagram of a power supply optimization device based on power grid monitoring data according to an embodiment of the present invention, such as Figure 5 As shown, the device includes: a receiving unit 501, a first acquiring unit 503, a first determining unit 505, a second acquiring unit 507, a second determining unit 509 and a sending unit 511. The power supply optimization device based on power grid monitoring data is described in detail below.

[0082] The receiving unit 501 is used to receive monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the electricity demand side of the power system.

[0083] The first acquisition unit 503 is used to input the monitoring data into the risk assessment model so as to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple sets of training data, and each of the multiple sets of training data includes: sample monitoring data and sample risk level corresponding to the sample monitoring data.

[0084] The first determination unit 505 is used to determine the power consumption priority of each power-consuming device on the power demand side according to the demand side risk level, wherein the demand side risk level is the risk level in the risk level corresponding to the second monitoring data.

[0085] The second acquisition unit 507 is used to obtain the current total power demand of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total power demand and the power supply, wherein the total power demand is the sum of the current power demand of each power-consuming device.

[0086] The second determination unit 509 is used to control the grid side to stop power supply when the demand difference is less than zero and / or the risk level on the grid side is higher than a preset level threshold, and determine the power supply priority of each power supply equipment on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the grid side is the risk level in the risk level corresponding to the first monitoring data, and the risk level on the virtual power plant side is the risk level in the risk level corresponding to the third monitoring data.

[0087] The sending unit 511 is used to send the power consumption priority and the power supply priority to the virtual power plant, so as to use the virtual power plant to control each power supply device to supply power to each power consumption device in turn according to the power supply priority, so that each power consumption device can be powered in turn according to the power consumption priority.

[0088] It should be noted here that the above-mentioned receiving unit 501, first acquisition unit 503, first determination unit 505, second acquisition unit 507, second determination unit 509 and sending unit 511 correspond to steps S202 to S212 in the above-mentioned embodiments, and the six units are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0089] As can be seen from the above, in the scheme recorded in the above-mentioned embodiment of the present invention, a receiving unit can be used to receive monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; then the first acquisition unit is used to input the monitoring data into the risk assessment model, so as to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple groups of training data, and each of the multiple groups of training data includes: sample monitoring data, and sample risk levels corresponding to the sample monitoring data; then the first determination unit is used to determine the power priority of each power-consuming device on the power demand side according to the demand side risk level, wherein the demand side risk level is the risk level in the risk level corresponding to the second monitoring data; then the second acquisition unit is used to obtain the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side, and the demand difference between the total demand power supply and the power supply is calculated, wherein, The total demand power supply is the sum of the current demand power supply of each power-consuming device; then, the second determination unit is used to control the power grid to stop power supply when the demand difference is less than zero and / or the risk level on the grid is higher than the preset level threshold, and the power supply priority of each power supply device on the virtual power plant side is determined according to the risk level on the virtual power plant side, wherein the risk level on the grid side is the risk level corresponding to the first monitoring data in the risk level, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk level; finally, the power consumption priority and the power supply priority are sent to the virtual power plant by the sending unit, so that the virtual power plant is used to control each power supply device to supply power to each power-consuming device in turn according to the power supply priority, so that each power-consuming device is supplied with power in turn according to the power consumption priority, thereby achieving the purpose of analyzing the power grid risk according to the power grid monitoring data, and updating the priority of power dispatching in combination with the risk level obtained by the analysis, so as to control the power supply equipment to supply power to the power-consuming device in turn according to the power supply priority, and the power-consuming device is also supplied with power in turn according to the power consumption priority, thereby achieving the technical effect of automatically updating the priority of power dispatching in combination with the power consumption risk of the power grid to supply power to the demand side more reasonably.

[0090] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that it is difficult to carry out power dispatch in combination with the power consumption risk of the power grid, resulting in unreasonable power supply to the demand side.

[0091] Optionally, the power supply optimization device based on power grid monitoring data also includes: a third acquisition unit, which is used to acquire multiple groups of historical monitoring data within a historical time period before inputting the monitoring data into a risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, wherein each of the multiple groups of historical monitoring data includes multiple items of historical monitoring data; a removal unit, which is used to perform data cleaning on the multiple groups of historical monitoring data to remove invalid data and duplicate data in the multiple groups of historical monitoring data; a fourth acquisition unit, which is used to format the multiple groups of historical monitoring data to obtain multiple groups of historical monitoring data in the same format; a third determination unit, which is used to separately determine the historical risk level of each group of corresponding historical monitoring data in the multiple groups of historical monitoring data; and a fifth acquisition unit, which is used to train using a support vector machine classification algorithm using multiple groups of historical monitoring data and the historical risk levels corresponding to the historical monitoring data to obtain a risk assessment model.

[0092] Optionally, the third determination unit includes: a first determination module, used to determine the combination of multiple historical monitoring data in each group of historical monitoring data as a historical monitoring data group; a first acquisition module, used to compare each historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; and a second determination module, used to determine the historical risk level corresponding to the historical monitoring data group based on the comparison result.

[0093] Optionally, the second determination module includes: a first determination submodule, which is used to determine that the historical risk level corresponding to the historical monitoring data group is a safe level when the comparison result indicates that each historical monitoring data in the historical monitoring data group is within a predetermined range; a second determination submodule, which is used to determine the degree of deviation of the historical monitoring data beyond the predetermined range when the comparison result indicates that there is historical monitoring data in the historical monitoring data group that is not within the predetermined range; and a third determination submodule, which is used to determine that the historical risk level corresponding to the historical monitoring data group is a low risk level when the degree of deviation of at least two historical monitoring data in the historical monitoring data group is not greater than a first deviation threshold or the degree of deviation of at least one historical monitoring data is greater than the second deviation threshold and not greater than the third deviation threshold, wherein the second deviation threshold is less than at the first deviation threshold, the first deviation threshold is less than the third deviation threshold; the fourth determination submodule is used to determine that the historical risk level corresponding to the historical monitoring data group is a medium risk level when the deviation of at least two historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or the deviation of at least one historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; the fifth determination submodule is used to determine that the historical risk level corresponding to the historical monitoring data group is a high risk level when the deviation of at least two historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold, or the deviation of at least one historical monitoring data is greater than the fifth deviation threshold.

[0094] Optionally, the first determination unit includes: a second acquisition module, used to obtain the device type and required power supply of each power-consuming device on the power demand side; a first calculation module, used to calculate the power demand degree of each power-consuming device using a first formula based on the device type, the required power supply and the risk level on the demand side, wherein the first formula is: Y represents the degree of demand, D represents the type of equipment, E represents the first risk value of the demand side risk level, C represents the required power supply, and C represents the 总 Represents the demand difference; a third acquisition module is used to sort the electrical devices in descending order according to the degree of electricity demand to obtain a first sorting result; a third determination module is used to determine the electricity priority of each electrical device according to the first sorting result, wherein the electrical device with a higher ranking in the first sorting result has a higher electricity priority.

[0095] Optionally, the second determination unit includes: a fourth acquisition module, used to obtain the current electricity price and the storage power of each power supply device; a second calculation module, used to calculate the power supply capacity index of each power supply device based on the electricity price, the storage power and the risk level on the virtual power plant side using a second formula, wherein the second formula is: Z = (H*10% + G*40%) / (F*50%), Z represents the power supply capacity index, H represents the second risk value of the virtual power plant side risk level, G represents the storage power, and F represents the electricity price; a fifth acquisition module, used to sort each power supply device in descending order according to the power supply capacity index to obtain a second sorting result; a fourth determination module, used to determine the power supply priority of each power supply device according to the second sorting result, wherein the power supply device with a higher ranking in the second sorting result has a higher power supply priority.

[0096] Optionally, the power supply optimization device based on power grid monitoring data also includes: a division unit, used to divide the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safety monitoring data according to the risk level; a fifth acquisition unit, used to remove the safety monitoring data in the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: high-risk monitoring data, medium-risk monitoring data and low-risk monitoring data; a transmission unit, used to transmit the risk monitoring data to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes high-risk monitoring data and / or medium-risk monitoring data.

[0097] According to another aspect of an embodiment of the present invention, a power supply optimization system based on power grid monitoring data is further provided. The power supply optimization system based on power grid monitoring data uses any of the above-mentioned power supply optimization methods based on power grid monitoring data. Figure 6 is a schematic diagram of a power supply optimization system based on power grid monitoring data according to an embodiment of the present invention. Figure 6 As shown, the system includes: an environmental monitoring and acquisition module, an edge intelligent gateway, a virtual power plant, a 5G base station and a management platform. The following is a detailed description of the power supply optimization system based on power grid monitoring data. The power supply optimization system based on power grid monitoring data includes:

[0098] The environmental monitoring and acquisition module is used to collect monitoring data from the grid side, electricity demand side and virtual power plant side of the power system.

[0099] The edge intelligent gateway is used to receive the monitoring data collected by the environmental monitoring collection module and process the monitoring data to obtain the power priority of each power-consuming equipment on the power demand side, the power supply priority of each power supply equipment on the virtual power plant side, and the corresponding risk levels on the grid side, the power demand side, and the virtual power plant side.

[0100] The virtual power plant is used to control the power supply equipment on the virtual power plant side to supply power to the power equipment on the power demand side according to the power consumption priority and power supply priority obtained by processing the monitoring data by the edge intelligent gateway.

[0101] The 5G base station is used to transmit the risk level, power consumption priority, power supply priority and risk monitoring data corresponding to the monitoring data, among which the risk monitoring data is the data obtained by removing the data with the risk level of the safety level in the monitoring data.

[0102] The management platform is used to receive the risk level, power consumption priority, power supply priority and risk monitoring data corresponding to the monitoring data transmitted by the 5G base station, and to issue a warning signal when the risk monitoring data contains monitoring data of high risk level and medium risk level.

[0103] From the above, it can be seen that in the scheme recorded in the above embodiments of the present invention, a power supply optimization system composed of an environmental monitoring and acquisition module, an edge intelligent gateway, a virtual power plant, a 5G base station and a management platform can be used to optimize power scheduling in combination with the analysis of power grid power consumption risks, wherein the environmental monitoring and acquisition module can be used to collect monitoring data on the power grid side, the power demand side and the virtual power plant side in the power system; then the edge intelligent gateway is used to receive the monitoring data collected by the environmental monitoring and acquisition module, and the monitoring data is processed to obtain the power priority of each power-consuming equipment on the power demand side, the power supply priority of each power supply equipment on the virtual power plant side, and the corresponding risk levels of the power grid side, the power demand side and the virtual power plant side; then the virtual power plant is used to control the power supply equipment on the virtual power plant side to supply power to the power-consuming equipment on the power demand side according to the power priority and power supply priority obtained by processing the monitoring data by the edge intelligent gateway; and then the power supply equipment on the virtual power plant side is used to control the power supply equipment on the power demand side to supply power to the power-consuming equipment on the power demand side. The risk level, power consumption priority, power supply priority and risk monitoring data corresponding to the monitoring data transmitted by 5G base stations are transmitted by 5G base stations, wherein the risk monitoring data is the data obtained by removing the data with the risk level of the safety level in the monitoring data; the risk level, power consumption priority, power supply priority and risk monitoring data corresponding to the monitoring data transmitted by 5G base stations are received by the management platform, and a warning signal is issued when the risk monitoring data contains monitoring data of high risk level and medium risk level, thereby analyzing the grid risk according to the grid monitoring data, and updating the priority of power dispatching in combination with the risk level obtained by the analysis, so as to control the power supply equipment to supply power to the power equipment in sequence according to the power supply priority, and enable the power equipment to be powered in sequence according to the power supply priority, thereby achieving the technical effect of automatically updating the priority of power dispatching in combination with the power consumption risk of the power grid, so as to supply power to the demand side more reasonably.

[0104] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that it is difficult to carry out power dispatch in combination with the power consumption risk of the power grid, resulting in unreasonable power supply to the demand side.

[0105] Specifically, according to the above-mentioned embodiment of the present invention, the environmental monitoring and acquisition module includes: a video monitor for collecting video data on the grid side, the power demand side and the virtual power plant side in the power system; a temperature and humidity sensor for collecting temperature data and humidity data on the grid side, the power demand side and the virtual power plant side in the power system; a smoke sensor for collecting smoke data on the grid side, the power demand side and the virtual power plant side in the power system; a harmful gas sensor for collecting harmful gas data on the grid side, the power demand side and the virtual power plant side in the power system; and a power sensor for collecting power operation data on the grid side, the power demand side and the virtual power plant side in the power system.

[0106] During the specific implementation process, the video monitor and various sensor components in the environmental monitoring and acquisition module can be used to conduct real-time monitoring of the grid side, virtual power plant side and electricity demand side in the power system and collect monitoring data.

[0107] Specifically, according to the above embodiment of the present invention, the edge intelligent gateway includes: a risk assessment module, which is used to evaluate the risk levels of the power grid side, the power demand side and the virtual power plant side according to the monitoring data; a power priority update module, which updates the power priority of each power device on the power demand side according to the risk level of the power demand side; and a power supply priority update module, which is used to update the power supply priority of each power supply device on the virtual power plant side according to the risk levels of the power grid side and the virtual power plant side.

[0108] During the specific implementation process, the edge intelligent gateway can be used to conduct risk analysis on the monitoring data collected by the environmental monitoring and collection module, so as to update the power priority of each power-consuming equipment on the power demand side, and control the power grid side to stop power supply when the power grid side is insufficient to supply power to the power-consuming equipment on the power demand side, and update the power supply priority of each power supply equipment on the virtual power plant side, so as to use the power supply equipment on the virtual power plant side to continue to supply power to the power-consuming equipment on the power demand side.

[0109] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned power supply optimization methods based on power grid monitoring data.

[0110] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0111] Optionally, in this embodiment, a computer-readable storage medium is configured to store program codes for executing the following steps: receiving monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; inputting the monitoring data into a risk assessment model to process the monitoring data using the risk assessment model to obtain a risk level corresponding to the monitoring data, wherein the risk assessment model is trained using multiple sets of training data by machine learning, and each of the multiple sets of training data includes: sample monitoring data, and a sample risk level corresponding to the sample monitoring data; determining the power priority of each power-consuming equipment on the power demand side according to the demand-side risk level, wherein the demand-side risk level is a risk level corresponding to the power demand side. The risk level corresponding to the second monitoring data in the risk level; obtain the current total demand power supply of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total demand power supply and the power supply, wherein the total demand power supply is the sum of the current demand power supplies of each power-consuming device; when the demand difference is less than zero and / or the risk level on the power grid side is higher than the preset level threshold, control the power grid side to stop power supply, and determine the power supply priority of each power supply device on the virtual power plant side according to the risk level on the virtual power plant side, wherein the risk level on the power grid side is the risk level corresponding to the first monitoring data in the risk level, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk level; send the power consumption priority and the power supply priority to the virtual power plant, so as to use the virtual power plant to control each power supply device to supply power to each power consumer in turn according to the power supply priority, so that each power consumer is powered in turn according to the power consumption priority.

[0112] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining multiple groups of historical monitoring data within a historical time period, wherein each of the multiple groups of historical monitoring data includes multiple items of historical monitoring data; performing data cleaning on the multiple groups of historical monitoring data to remove invalid data and duplicate data in the multiple groups of historical monitoring data; performing format conversion on the multiple groups of historical monitoring data to obtain multiple groups of historical monitoring data in the same format; respectively determining the historical risk level of each group of historical monitoring data corresponding to the multiple groups of historical monitoring data; and using the multiple groups of historical monitoring data and the historical risk levels corresponding to the historical monitoring data to train through a support vector machine classification algorithm to obtain a risk assessment model.

[0113] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: determining that a combination of multiple historical monitoring data in each group of historical monitoring data is a historical monitoring data group; comparing each item of historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; and determining the historical risk level corresponding to the historical monitoring data group based on the comparison result.

[0114] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: when the comparison result indicates that each item of historical monitoring data in the historical monitoring data group is within a predetermined range, determining that the historical risk level corresponding to the historical monitoring data group is a safe level; when the comparison result indicates that there is historical monitoring data in the historical monitoring data group that is not within the predetermined range, determining the degree of deviation of the historical monitoring data beyond the predetermined range; when the degree of deviation of at least two items of historical monitoring data in the historical monitoring data group is not greater than a first deviation threshold or the degree of deviation of at least one item of historical monitoring data is greater than a second deviation threshold and not greater than a third deviation threshold, determining that the historical risk level corresponding to the historical monitoring data group is a low risk level, wherein , the second deviation threshold is less than the first deviation threshold, and the first deviation threshold is less than the third deviation threshold; when the deviation of at least two historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or the deviation of at least one historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, the historical risk level corresponding to the historical monitoring data group is determined to be a medium risk level, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; when the deviation of at least two historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold, or the deviation of at least one historical monitoring data is greater than the fifth deviation threshold, the historical risk level corresponding to the historical monitoring data group is determined to be a high risk level.

[0115] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining the device type and required power supply of each power-consuming device on the power demand side; and calculating the power demand degree of each power-consuming device using a first formula based on the device type, required power supply and demand-side risk level, wherein the first formula is: Y represents the degree of demand, D represents the type of equipment, E represents the first risk value of the demand side risk level, C represents the required power supply, and C represents the 总 Represents the demand difference; sorts each electrical device in descending order according to the degree of electricity demand to obtain a first sorting result; determines the electricity priority of each electrical device according to the first sorting result, wherein the electrical device with a higher ranking in the first sorting result has a higher electricity priority.

[0116] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining the current electricity price and the stored power of each power supply device; calculating the power supply capacity index of each power supply device based on the electricity price, the stored power and the risk level on the virtual power plant side using a second formula, wherein the second formula is: Z = (H*10% + G*40%) / (F*50%), Z represents the power supply capacity index, H represents the second risk value of the virtual power plant side risk level, G represents the stored power, and F represents the electricity price; sorting each power supply device in descending order according to the power supply capacity index to obtain a second sorting result; determining the power supply priority of each power supply device based on the second sorting result, wherein the power supply device with a higher ranking in the second sorting result has a higher power supply priority.

[0117] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: dividing the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safety monitoring data according to the risk level; removing the safety monitoring data in the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: high-risk monitoring data, medium-risk monitoring data and low-risk monitoring data; transmitting the risk monitoring data to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes high-risk monitoring data and / or medium-risk monitoring data.

[0118] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned power supply optimization methods based on power grid monitoring data is executed.

[0119] According to another aspect of an embodiment of the present invention, a computer program product is provided, including computer instructions, which, when executed by a processor, execute any one of the above-mentioned power supply optimization methods based on power grid monitoring data.

[0120] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0121] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0126] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A power supply optimization method based on power grid monitoring data, characterized in that: include: Receiving monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; Inputting the monitoring data into a risk assessment model to process the monitoring data using the risk assessment model to obtain a risk level corresponding to the monitoring data, wherein the risk assessment model is trained using multiple sets of training data by machine learning, and each of the multiple sets of training data includes: sample monitoring data and a sample risk level corresponding to the sample monitoring data; Determine the power consumption priority of each power-consuming device on the power demand side according to the demand side risk level, wherein the demand side risk level is the risk level corresponding to the second monitoring data among the risk levels; Obtain the total power demand currently required by each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total power demand and the power supply, wherein the total power demand is the sum of the current power demand of each power-consuming device; When the demand difference is less than zero and / or the risk level on the grid side is higher than a preset level threshold, the grid side is controlled to stop power supply, and the power supply priority of each power supply device on the virtual power plant side is determined according to the risk level on the virtual power plant side, wherein the risk level on the grid side is the risk level corresponding to the first monitoring data in the risk levels, and the risk level on the virtual power plant side is the risk level corresponding to the third monitoring data in the risk levels; The power usage priority and the power supply priority are sent to a virtual power plant, so that the virtual power plant can be used to control each power supply device to supply power to each power consuming device in turn according to the power supply priority, so that each power consuming device can be powered in turn according to the power usage priority.

2. The power supply optimization method based on power grid monitoring data according to claim 1 is characterized in that: Before inputting the monitoring data into the risk assessment model to process the monitoring data using the risk assessment model to obtain the risk level corresponding to the monitoring data, the method further includes: Acquire multiple groups of historical monitoring data within a historical time period, wherein each of the multiple groups of historical monitoring data includes multiple items of the historical monitoring data; Performing data cleaning on the multiple sets of historical monitoring data to remove invalid data and duplicate data in the multiple sets of historical monitoring data; Converting the formats of the multiple sets of historical monitoring data to obtain multiple sets of historical monitoring data in the same format; Respectively determining a historical risk level of each group of the historical monitoring data corresponding to the historical monitoring data; The risk assessment model is obtained by training with a support vector machine classification algorithm using multiple groups of the historical monitoring data and the historical risk levels corresponding to the historical monitoring data.

3. The power supply optimization method based on power grid monitoring data according to claim 2 is characterized in that: Determining the historical risk level of each group of the historical monitoring data corresponding to the historical monitoring data respectively includes: Determine a combination of multiple historical monitoring data in each group of historical monitoring data as a historical monitoring data group; Comparing each item of the historical monitoring data in the historical monitoring data group with a predetermined range to obtain a comparison result; The historical risk level corresponding to the historical monitoring data group is determined according to the comparison result.

4. The power supply optimization method based on power grid monitoring data according to claim 3 is characterized in that: Determining the historical risk level corresponding to the historical monitoring data group according to the comparison result includes: When the comparison result indicates that each item of the historical monitoring data in the historical monitoring data group is within the predetermined range, determining that the historical risk level corresponding to the historical monitoring data group is a safety level; When the comparison result indicates that the historical monitoring data group contains historical monitoring data that is not within the predetermined range, determining a degree of deviation of the historical monitoring data that exceeds the predetermined range; In the case where the degree of deviation of at least two of the historical monitoring data in the historical monitoring data group is not greater than the first deviation threshold or the degree of deviation of at least one of the historical monitoring data is greater than the second deviation threshold and not greater than the third deviation threshold, it is determined that the historical risk level corresponding to the historical monitoring data group is a low risk level, wherein the second deviation threshold is less than the first deviation threshold, and the first deviation threshold is less than the third deviation threshold; In the case where the deviation of at least two of the historical monitoring data in the historical monitoring data group is greater than the first deviation threshold and not greater than the fourth deviation threshold, or the deviation of at least one of the historical monitoring data is greater than the third deviation threshold and not greater than the fifth deviation threshold, it is determined that the historical risk level corresponding to the historical monitoring data group is a medium risk level, wherein the fourth deviation threshold is greater than the third deviation threshold, and the fifth deviation threshold is greater than the fourth deviation threshold; When the deviation degree of at least two of the historical monitoring data in the historical monitoring data group is greater than the fourth deviation threshold or the deviation degree of at least one of the historical monitoring data is greater than the fifth deviation threshold, it is determined that the historical risk level corresponding to the historical monitoring data group is a high risk level.

5. The power supply optimization method based on power grid monitoring data according to claim 1 is characterized in that: Determining the power consumption priority of each of the power consumption devices on the power consumption demand side according to the demand difference and the risk level on the demand side includes: Obtaining the device type and the required power supply of each of the power consuming devices on the power demand side; The power demand level of each power-consuming device is calculated using a first formula based on the device type, the required power supply and the demand-side risk level, wherein the first formula is: Y represents the demand level, D represents the equipment type, E represents the first risk value of the demand side risk level, C represents the required power supply, 总 represents the demand difference; Sorting the electrical devices in descending order according to the degree of their power demand to obtain a first sorting result; The power usage priority of each of the power-consuming devices is determined according to the first sorting result, wherein the power usage priority corresponding to the power-consuming device that is ranked higher in the first sorting result is higher.

6. The power supply optimization method based on power grid monitoring data according to claim 1 is characterized in that: Determining the power supply priority of each power supply device on the virtual power plant side according to the risk level on the virtual power plant side includes: Obtaining the current electricity price and the storage capacity of each of the power supply devices; The power supply capability index of each power supply device is calculated using a second formula based on the electricity price, the stored electricity, and the risk level on the virtual power plant side, wherein the second formula is: Z=(H*10%+G*40%) / (F*50%), Z represents the power supply capability index, H represents the second risk value of the risk level on the virtual power plant side, G represents the stored electricity, and F represents the electricity price; Sorting the power supply devices in descending order according to the power supply capability index to obtain a second sorting result; The power supply priority of each of the power supply devices is determined according to the second sorting result, wherein the power supply device that is ranked higher in the second sorting result has a higher power supply priority.

7. The power supply optimization method based on power grid monitoring data according to claim 1 is characterized in that: Also includes: Dividing the monitoring data into high-risk monitoring data, medium-risk monitoring data, low-risk monitoring data and safe monitoring data according to the risk level; Removing the safety monitoring data from the monitoring data to obtain risk monitoring data, wherein the risk monitoring data includes at least one of the following: the high-risk monitoring data, the medium-risk monitoring data, and the low-risk monitoring data; The risk monitoring data is transmitted to a management platform, wherein the management platform issues a warning signal when the received risk monitoring data includes the high-risk monitoring data and / or the medium-risk monitoring data.

8. A power supply optimization device based on power grid monitoring data, characterized in that: include: A receiving unit, configured to receive monitoring data obtained by monitoring the power system, wherein the monitoring data includes: first monitoring data obtained by monitoring the power grid side of the power system, second monitoring data obtained by monitoring the virtual power plant side of the power system, and third monitoring data obtained by monitoring the power demand side of the power system; A first acquisition unit is used to input the monitoring data into a risk assessment model, so as to process the monitoring data using the risk assessment model to obtain a risk level corresponding to the monitoring data, wherein the risk assessment model is trained by machine learning using multiple sets of training data, and each of the multiple sets of training data includes: sample monitoring data and a sample risk level corresponding to the sample monitoring data; A first determining unit, configured to determine the power consumption priority of each power-consuming device on the power demand side according to a demand side risk level, wherein the demand side risk level is a risk level among the risk levels corresponding to the second monitoring data; A second acquisition unit is used to obtain the current total power demand of each power-consuming device on the power demand side and the current power supply on the power grid side, and calculate the demand difference between the total power demand and the power supply, wherein the total power demand is the sum of the current power demand of each power-consuming device; A second determination unit is used to control the grid side to stop power supply when the demand difference is less than zero and / or the risk level of the grid side is higher than a preset level threshold, and determine the power supply priority of each power supply device on the virtual power plant side according to the risk level of the virtual power plant side, wherein the risk level of the grid side is the risk level corresponding to the first monitoring data among the risk levels, and the risk level of the virtual power plant side is the risk level corresponding to the third monitoring data among the risk levels; A sending unit is used to send the power consumption priority and the power supply priority to the virtual power plant, so that the virtual power plant can control each power supply device to supply power to each power consumption device in turn according to the power supply priority, so that each power consumption device can be powered in turn according to the power consumption priority.

9. A power supply optimization system based on power grid monitoring data, characterized in that: The power supply optimization system based on power grid monitoring data uses the power supply optimization method based on power grid monitoring data described in any one of claims 1 to 7, including: Environmental monitoring and acquisition module, used to collect monitoring data on the grid side, power demand side and virtual power plant side of the power system; The edge intelligent gateway is used to receive the monitoring data collected by the environmental monitoring collection module, and process the monitoring data to obtain the power priority of each power-consuming device on the power demand side, the power supply priority of each power supply device on the virtual power plant side, and the corresponding risk levels of the power grid side, the power demand side, and the virtual power plant side; A virtual power plant, configured to control the power supply device on the virtual power plant side to supply power to the power consumption device on the power demand side according to the power consumption priority and the power supply priority obtained by the edge intelligent gateway processing the monitoring data; A 5G base station, used for transmitting the risk level, the power consumption priority, the power supply priority and risk monitoring data corresponding to the monitoring data, wherein the risk monitoring data is the data obtained by removing the data whose risk level is a safety level in the monitoring data; The management platform is used to receive the risk level, the power usage priority, the power supply priority and the risk monitoring data corresponding to the monitoring data transmitted by the 5G base station, and to issue a warning signal when the risk monitoring data contains monitoring data of high risk level and medium risk level.

10. The power supply optimization system based on power grid monitoring data according to claim 9, characterized in that: The environmental monitoring and acquisition module comprises: A video monitor for collecting video data of the grid side, the power demand side and the virtual power plant side in the power system; Temperature and humidity sensors are used to collect temperature data and humidity data on the grid side, the power demand side and the virtual power plant side of the power system; A smoke sensor is used to collect smoke data on the grid side, the power demand side and the virtual power plant side of the power system; A harmful gas sensor, used to collect harmful gas data on the grid side, the power demand side and the virtual power plant side of the power system; The power sensor is used to collect power operation data on the power grid side, the power demand side and the virtual power plant side in the power system.

11. The power supply optimization system based on power grid monitoring data according to claim 9, characterized in that: Edge intelligent gateway, including: A risk assessment module, used to assess the risk levels of the power grid side, the power demand side and the virtual power plant side according to the monitoring data; A power priority updating module, which updates the power priority of each of the power consuming devices on the power demand side according to the risk level of the power demand side; A power supply priority updating module is used to update the power supply priority of each power supply device on the virtual power plant side according to the risk levels on the power grid side and the virtual power plant side.

12. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the power supply optimization method based on power grid monitoring data described in any one of claims 1 to 7 is performed.

Images