Heterogeneous resource control method, device and equipment of virtual power plant and medium

Abstract

The present application relates to the technical field of data processing, and provides a heterogeneous resource control method, device and equipment of a virtual power plant and a medium, which is applied to an Internet of Things platform, and the method comprises the following steps: obtaining original data of each virtual group based on a scheduling instruction to obtain a plurality of virtual groups in the virtual power plant; converting the original data to obtain converted data; performing aggregate calculation on the converted data based on an aggregation strategy to obtain an aggregate data set; scheduling the scheduling instruction and the aggregate data set according to a scheduling strategy to determine a device control instruction; and controlling a plurality of heterogeneous resources in each virtual group based on the device control instruction. Therefore, the embodiment of the present application determines the device control instruction by processing the data such as conversion, aggregate calculation and scheduling, controls each heterogeneous resource based on the device control instruction, realizes the rapid conversion, real-time sensing and flexible control of the massive and high-frequency data stream, and thus improves the processing efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a heterogeneous resource control method, device and equipment of a virtual power plant and a medium. BACKGROUND

[0002] With the deepening of new energy transformation, the resources accessed to the virtual power plant present the characteristics of massification, decentralization and heterogeneity. At present, the existing technology usually has the following defects: "chimney type" vertical architecture: for different types of resources, independent access and monitoring subsystems often need to be developed, the coupling degree between systems is high, the expansibility is poor, and the construction and maintenance cost is high. Complex protocol conversion: lack of unified access standard, need to develop special conversion gateway or driver for each protocol, large workload, difficult to quickly adapt to new types of resources, and the data format accessed is not unified. Insufficient data processing capacity: traditional centralized data processing method is difficult to cope with massive and high-frequency Internet of Things data flow, leading to state perception delay, affecting the timeliness and accuracy of the virtual power plant responding to the grid dispatching instruction. Insufficient resource value mining: due to the lack of deep perception and unified modeling of underlying equipment data, it is difficult to accurately assess and flexibly control the potential of aggregated resources, limiting the expansion of commercial operation modes of virtual power plants.

[0003] Therefore, the existing virtual power plant control method has the problem of low processing efficiency due to vertical architecture, complex protocol conversion, insufficient data processing capacity and insufficient resource value mining. SUMMARY

[0004] The embodiments of the present application provide a heterogeneous resource control method, device, equipment and medium of a virtual power plant, aiming at solving the problem of low processing efficiency of the virtual power plant control method in the prior art due to vertical architecture, complex protocol conversion, insufficient data processing capacity and insufficient resource value mining.

[0005] In order to solve the above problems, in a first aspect, the embodiments of the present application provide a heterogeneous resource control method of a virtual power plant, applied to an Internet of Things platform, the method comprising:

[0006] Based on the dispatching instruction, the original data of each virtual group in the virtual power plant is obtained and processed to obtain the original data of each virtual group;

[0007] The original data of each virtual group is converted and processed to obtain conversion data;

[0008] Based on the aggregation strategy, the conversion data is aggregated and calculated to obtain an aggregated data set;

[0009] According to the dispatching strategy, the dispatching instruction and the aggregated data set are dispatched to determine a device control instruction;

[0010] The control unit controls a plurality of heterogeneous resources in each virtual group based on the device control instruction.

[0011] In a second aspect, the embodiments of the present application provide a heterogeneous resource control device of a virtual power plant, applied to an Internet of Things platform, the device comprising:

[0012] An acquisition unit is configured to acquire a plurality of virtual groups in the virtual power plant based on a scheduling instruction to obtain original data of each virtual group.

[0013] A conversion unit is configured to convert the original data of each virtual group to obtain converted data.

[0014] An aggregation calculation unit is configured to aggregate and calculate the converted data based on an aggregation strategy to obtain an aggregated data set.

[0015] A scheduling unit is configured to schedule the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction.

[0016] The control unit controls a plurality of heterogeneous resources in each virtual group based on the device control instruction.

[0017] In a third aspect, the embodiments of the present application provide a computer device, comprising a memory and a processor connected to the memory; the memory is configured to store a computer program, and the processor is configured to run the computer program stored in the memory to execute the method of the first aspect.

[0018] In a fourth aspect, the embodiments of the present application provide a storage medium, which stores a computer program, the computer program comprising program instructions, the program instructions being executed by a processor to implement the method of the first aspect.

[0019] The embodiment of the present application provides a heterogeneous resource control method, device and equipment of a virtual power plant and a medium, which is applied to an Internet of Things platform. The method comprises the following steps: obtaining and processing a plurality of virtual groups in the virtual power plant based on a scheduling instruction to obtain original data of each virtual group; converting and processing the original data of each virtual group to obtain converted data; performing aggregate calculation and processing on the converted data based on an aggregation strategy to obtain an aggregate data set; performing scheduling processing on the scheduling instruction and the aggregate data set according to a scheduling strategy to determine a device control instruction; and performing control processing on a plurality of heterogeneous resources in each virtual group based on the device control instruction. Therefore, the embodiment of the present application determines the device control instruction by converting, aggregate calculating and scheduling the original data, performs fine control processing on each heterogeneous resource based on the device control instruction, realizes rapid conversion, real-time sensing and flexible control of a mass and high-frequency data stream, and thus improves processing efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 A flowchart of a heterogeneous resource control method of a virtual power plant provided by the embodiment of the present application is shown in the figure.

[0022] Figure 2 A schematic block diagram of a heterogeneous resource control device of a virtual power plant provided by the embodiment of the present application is shown in the figure.

[0023] Figure 3 A schematic block diagram of a computer device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0025] It should be understood that when used in the specification and the appended claims, the terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0026] It should also be understood that the terms used in the specification and the appended claims are intended to describe certain embodiments only and are not intended to limit the present application. As used in the specification and the appended claims, the singular forms "a," "an" and "the" are intended to include plural forms as well, unless the context clearly dictates otherwise.

[0027] It should further be understood that the term "and / or" used in the specification and the appended claims, means one or more of the associated listed items as well as all possible combinations of the items and includes the combinations.

[0028] Please refer to Figure 1 , Figure 1 The flowchart of the heterogeneous resource control method of the virtual power plant provided by the embodiment of the present application. As shown in Figure 1 The embodiment of the present application provides a heterogeneous resource control method of a virtual power plant, which is applied to an Internet of Things platform, and the method comprises the following steps S110-S150.

[0029] S110, based on the scheduling instruction, obtaining the original data of each virtual group by acquiring and processing a plurality of virtual groups in the virtual power plant.

[0030] In the embodiment, the scheduling instruction can be sent to the Internet of Things platform or the virtual power plant by the power grid dispatching center or the power trading market, so as to obtain the original data of each virtual group by acquiring and processing a plurality of virtual groups in the virtual power plant respectively according to the scheduling instruction.

[0031] The application can be applied to the scene of power system operation and auxiliary service market, realizes peak and frequency regulation: aggregates massive dispersed flexible load, energy storage and distributed power supply, provides fast and accurate power balance service for power grid, relieves peak electricity stress, improves power grid operation efficiency and reliability; also realizes demand side response: when there is emergency dispatching instruction of power grid, quickly issues instruction through the Internet of Things platform, adjusts the electricity consumption behavior of aggregated resources, realizes peak clipping and valley filling; also realizes that the total adjustable capacity of numerous distributed resources is used as standby capacity of virtual power plant, participates in reserve auxiliary service market transaction of power grid. The application can also be applied to the scene of power market transaction, realizes spot market transaction: based on accurate prediction and real-time control of aggregated resource power generation / electricity consumption capacity, participates in power purchase and sale transaction of power spot market as a whole unit of virtual power plant, realizes benefit maximization; also realizes green electricity and carbon transaction: aggregates distributed green energy such as photovoltaic and wind power, forms a large-scale green power supplier, participates in green certificate transaction and carbon transaction market, helps users to realize green electricity target. The application can also be applied to the scene of intelligent operation of new infrastructure, realizes electric vehicle charging network: aggregates widely distributed charging piles into a controllable load, realizes orderly charging, V2G (vehicle to grid) and other advanced applications, avoids impact on distribution network.

[0032] In an embodiment, before the obtaining and processing of the scheduling instruction to obtain the original data of each virtual group in the virtual power plant, comprising:

[0033] When each heterogeneous resource accesses, a resource identifier is generated, and the static attributes and initial scheduling capability model of each heterogeneous resource are recorded;

[0034] According to the resource identifier, the static attribute and the transaction demand, each heterogeneous resource is divided to determine a heterogeneous resource mapping table;

[0035] Each virtual group is determined by using the resource mapping table.

[0036] In this embodiment, the virtual power plant includes a plurality of virtual groups, and each virtual group includes a plurality of heterogeneous resources; the plurality of heterogeneous resources can include charging piles, energy storage cabinets, adjustable air conditioners, battery swap stations, cold storage and heat storage facilities, and photovoltaic (wind) systems and other physical devices.

[0037] The Internet of Things platform is used to install or configure an Internet of Things gateway or an embedded terminal for each heterogeneous resource to complete the access of each heterogeneous resource.

[0038] The resource identifier is a unique identifier for each heterogeneous resource; the static attribute can include device model, location, rated power and other data; the transaction demand can include specific electricity demand of the power dispatching center or the power transaction market.

[0039] The heterogeneous resource mapping table records the heterogeneous resources contained in each virtual group, geographical distribution, communication state, and weight or priority of each heterogeneous resource in the current group, so as to determine each virtual group by using the resource mapping table.

[0040] Further, after the determination of each virtual group by using the resource mapping table, the method further comprises:

[0041] In the Internet of Things platform, a corresponding digital twin is created for each heterogeneous resource, and historical data is formed by using the digital twin. The digital twin can include static attributes and dynamic telemetry data of each heterogeneous resource. The static attributes can include device model, location, rated power, and other data. The dynamic telemetry data can include real-time power, switch state, and real-time power, and other data.

[0042] Meanwhile, the Internet of Things platform monitors the state changes (such as offline, failure) of each heterogeneous resource and other physical devices in real time, dynamically adjusts the mapping relationship, and ensures the executability of the control instruction and the system robustness.

[0043] Through the above embodiments, it can be seen that when each heterogeneous resource is accessed, a resource identifier is generated, and the static attributes and initial scheduling capability model of each heterogeneous resource are recorded. Each heterogeneous resource is divided according to the resource identifier, the static attributes, and the transaction demand to determine a heterogeneous resource mapping table. Each virtual group is determined by using the resource mapping table. The original data of each virtual group is obtained by processing the virtual groups in the virtual power plant based on the scheduling instruction, so as to ensure the association between the heterogeneous resources and the virtual groups, and to quickly obtain the original data to realize efficient processing of massive and high-frequency Internet of Things data, to provide low-latency and high-precision resource state perception for the virtual power plant, and to ensure the real-time control.

[0044] S120, converting the original data of each virtual group to obtain converted data.

[0045] In this embodiment, after obtaining the original data of each virtual group, the original data of each virtual group can be converted to obtain converted data.

[0046] In an embodiment, the converting the original data of each virtual group to obtain converted data comprises:

[0047] The protocol parser is configured based on the configuration data to obtain a configured protocol parser.

[0048] The original data of each virtual group is subjected to protocol extraction processing by using the configured protocol parser to obtain extraction data.

[0049] The extraction data is subjected to reorganization conversion processing according to a mapping rule script to obtain intermediate data.

[0050] The intermediate data is subjected to validity verification processing according to a detection rule to obtain the conversion data.

[0051] In the embodiment, the protocol parser is configured based on the configuration data to obtain a configured protocol parser, specifically including: the configured protocol parser is pre-configured by the configuration data on the Internet of Things platform; the configuration data can include configuration protocol type, register address, data point definition and other information; the configured protocol parser can be a parser of an Internet of Things protocol (such as Modbus, BACNet, MQTT, etc.).

[0052] The original data of each virtual group is subjected to protocol extraction processing by using the configured protocol parser to obtain extraction data, specifically including: the original data is subjected to extraction processing by the configured protocol parser respectively to obtain the extraction data; the extraction data can include power, voltage, state and other data.

[0053] The extraction data is subjected to reorganization conversion processing according to a mapping rule script to obtain intermediate data, specifically including: the extraction data is subjected to format reorganization by the mapping rule script to convert the extraction data into the intermediate data; the mapping rule script can be a preset JavaScript script; the intermediate data is JSON format data, that is, a unified data format inside the Internet of Things platform.

[0054] In an embodiment, the intermediate data is subjected to validity verification processing according to a detection rule to obtain the conversion data, including:

[0055] The intermediate data is subjected to cleaning processing to obtain first data.

[0056] The first data is subjected to filtering and smoothing processing to obtain second data.

[0057] The second data is subjected to abnormality detection to obtain the conversion data.

[0058] In the embodiment, the intermediate data is cleaned to obtain the first data, specifically including: the data range and data type of the intermediate data are verified to obtain invalid values; the invalid values are removed from the intermediate data to obtain the first data. The verification rules can include range checking, type checking, etc.

[0059] The first data is filtered and smoothed to obtain the second data, specifically including: the first data is smoothed to smooth the data curve to obtain the second data. The second data is detected for abnormalities to obtain the conversion data, specifically including: the data range and data type of the second data are re-verified to obtain abnormal values; the abnormal values are filled in the second data to obtain the conversion data; the filling can be the average value or adjacent value of real-time data. Meanwhile, the conversion data is published through a unified data bus for subsequent storage, analysis or control use.

[0060] Through the above embodiment, it can be known that the original data of each virtual group is converted to obtain conversion data, relying on the protocol decoupling capability of the Internet of Things platform, new types of resources can be quickly accessed and converted "plug and play", greatly reducing the technical threshold and cost of expanding the scale of the virtual power plant, thereby improving the processing efficiency.

[0061] In S130, the conversion data is aggregated based on an aggregation policy to obtain an aggregated data set.

[0062] In the embodiment, after the multi-source data is determined, the conversion data can be aggregated based on an aggregation policy to obtain an aggregated data set.

[0063] In an embodiment, the conversion data is aggregated based on an aggregation policy to obtain an aggregated data set, including:

[0064] The number of first heterogeneous resources in each virtual group and the real-time power corresponding to each first heterogeneous resource are obtained;

[0065] The first heterogeneous resource quantity and the real-time power corresponding to each first heterogeneous resource are first aggregated based on a first aggregation calculation strategy to obtain first aggregated data;

[0066] The current energy percentage and the corresponding rated capacity of each second heterogeneous resource in each virtual group are obtained;

[0067] The current energy percentage and the corresponding rated capacity of each second heterogeneous resource are second aggregated based on a second aggregation calculation strategy to obtain second aggregated data;

[0068] The first aggregated data and the second aggregated data are combined to obtain the aggregated data set.

[0069] In the embodiment, the types of the plurality of heterogeneous resources can include a first heterogeneous resource, a second heterogeneous resource, and the like; the first heterogeneous resource can include a photovoltaic system, a charging pile, an adjustable air conditioner, a battery swapping station, a cold storage and heat storage facility, and the like; and the second heterogeneous resource can include a physical device such as an energy storage cabinet.

[0070] The number of first heterogeneous resources in each virtual group and real-time power corresponding to each first heterogeneous resource are obtained; first aggregated calculation processing is performed on the number of first heterogeneous resources and the real-time power corresponding to each first heterogeneous resource based on a first aggregation calculation strategy to obtain first aggregated data; the formula corresponding to the first aggregation calculation strategy can include a total power generation or power consumption calculation formula , an average power calculation formula , maximum / minimum power statistics, and the like; wherein Pi is the real-time power (kW) of the ith resource; n is the number of first heterogeneous resources; the average power calculation formula is used to evaluate the average power of a certain resource in the region; and the maximum / minimum power statistics record the power extreme value in the region in the current period, which is used for over-limit early warning. The first aggregated data can include total power generation, power consumption, average power, maximum power, minimum power, and the like.

[0071] The current energy percentage and the corresponding rated capacity of each second heterogeneous resource in each virtual group are obtained; second aggregated calculation processing is performed on the current energy percentage and the corresponding rated capacity of each second heterogeneous resource based on a second aggregation calculation strategy to obtain second aggregated data; the available capacity estimation formula corresponding to the second aggregation calculation strategy is ; wherein SOCi is the current energy percentage of the ith energy storage device; Capacityi is the rated capacity (kWh); and n is the number of second heterogeneous resources. The second aggregated data can include available capacity, and the like.

[0072] The first aggregated data and the second aggregated data are combined to obtain the aggregated data set; the aggregated data set further includes an average response delay, and the average response delay (such as the average time from instruction to power change) of each virtual group is calculated.

[0073] According to the above embodiment, the conversion data is aggregated and calculated based on the aggregation strategy to obtain the aggregated data set, the first aggregation calculation and the second aggregation calculation of the conversion data are performed to obtain the aggregated data set, and the accuracy of the processing efficiency is ensured.

[0074] S140, performing scheduling processing on the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction.

[0075] In this embodiment, after obtaining the aggregated data set, the scheduling instruction and the aggregated data set can be subjected to scheduling processing according to a scheduling strategy to determine a device control instruction.

[0076] In an embodiment, before performing scheduling processing on the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction, the method comprises:

[0077] Obtaining historical data of each virtual group, and performing analysis processing on a plurality of heterogeneous resources of each virtual group to obtain physical characteristic data;

[0078] Performing feature extraction processing on the historical data, the physical characteristic data and the aggregated data set to obtain key data;

[0079] Based on the key data, performing construction processing on the initial scheduling capability model to obtain a target scheduling capability model of each virtual group.

[0080] In this embodiment, a plurality of heterogeneous resources of each virtual group are respectively subjected to analysis processing to obtain physical characteristic data of each heterogeneous resource; the physical characteristic data can include adjustable capacity, response speed, duration, etc. The historical data, the physical characteristic data and the aggregated data set are subjected to feature extraction processing to obtain key data; the key data can include maximum / minimum power limit, ramp rate, sustainable time, response delay, etc. Based on the key data, the initial scheduling capability model is subjected to construction processing to obtain a target scheduling capability model of each virtual group, i.e. the target scheduling capability model is constructed using the key data and the initial scheduling capability model, so as to describe the schedulable capacity of each virtual group using the target scheduling capability model: ; Pmax, Pmin are power upper and lower limits; Rup, Rdown are power rise / fall rates (kW / min); Tsustain is sustainable regulation time; τ is response time constant. At the same time, actual response behavior of each heterogeneous resource can be monitored, and model parameters are dynamically adjusted through a machine learning algorithm (such as a regression model) to improve prediction accuracy.

[0081] In an embodiment, performing scheduling processing on the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction comprises:

[0082] Generating processing according to the scheduling instruction and the aggregated data set to obtain an initial instruction;

[0083] Call the target scheduling capability model, and decompose the initial instruction according to the plurality of heterogeneous resources of each virtual group and the corresponding heterogeneous resource mapping table to obtain the device control instruction.

[0084] In this embodiment, the generating processing according to the scheduling instruction and the aggregated data set to obtain the initial instruction specifically includes: analyzing and processing the scheduling instruction to determine target scheduling data, that is, obtaining specific demand data from the scheduling instruction, and the target scheduling data can be "total power of virtual group A and virtual group B increases by 100kW"; generating processing is performed on the target scheduling data and the aggregated data set to obtain the initial instruction; the initial instruction is a standardized instruction for a virtual group, for example, the initial instruction can be "total power of virtual group A and virtual group B increases by 100kW within 10 minutes".

[0085] The calling of the target scheduling capability model and the decomposition of the initial instruction according to the plurality of heterogeneous resources of each virtual group and the corresponding heterogeneous resource mapping table to obtain the device control instruction specifically includes: calculating the capability proportion of each heterogeneous resource in the corresponding virtual group according to the target scheduling capability model, and obtaining the priority, geographical distribution and communication state by using the heterogeneous resource mapping table; based on the priority, the geographical distribution, the communication state and the capability proportion, the power adjustment amount is allocated to obtain the specific device control instruction; the device control instruction is a device-level control sequence, for example, the device control instruction can be to reduce the air conditioner setting value by 1 degree Celsius, start the energy storage discharge by 50kW, and suspend the charging pile.

[0086] Through the above embodiments, it can be known that the scheduling instruction and the aggregated data set are scheduled according to the scheduling strategy to determine the device control instruction, which realizes the rich real-time and historical data based on the Internet of Things platform, can establish a more accurate scheduling capability model, deeply excavates the adjustment potential of distributed resources, improves the overall performance and market competitiveness of the virtual power plant, and intelligently decomposes into microscopic and differentiated control commands for each single heterogeneous resource in the virtual group, thereby improving the processing efficiency.

[0087] S150, control processing is performed on the plurality of heterogeneous resources in each virtual group based on the device control instruction.

[0088] In this embodiment, after the device control instruction is obtained, control processing can be performed on the plurality of heterogeneous resources in each virtual group based on the device control instruction, so as to realize fine control processing on the dispersed heterogeneous resources.

[0089] In summary, this embodiment of the invention acquires and processes the raw data of several virtual groups in a virtual power plant based on scheduling instructions; transforms the raw data of each virtual group to obtain transformed data; performs aggregation calculations on the transformed data based on an aggregation strategy to obtain an aggregated dataset; performs scheduling processing on the scheduling instructions and the aggregated dataset according to the scheduling strategy to determine equipment control instructions; and performs control processing on several heterogeneous resources in each virtual group based on the equipment control instructions. Therefore, this embodiment of the invention determines equipment control instructions by performing transformation, aggregation calculations, and scheduling on the raw data, and performs refined control processing on each heterogeneous resource based on the equipment control instructions, thereby achieving rapid transformation, real-time perception, and flexible control of massive and high-frequency data streams, and thus improving processing efficiency.

[0090] Figure 2 This is a schematic block diagram of a heterogeneous resource control device for a virtual power plant provided in an embodiment of the present invention. Figure 2 As shown, this embodiment of the invention provides a heterogeneous resource control device 700 for a virtual power plant that implements the method described above, applied to an Internet of Things (IoT) platform. For details, please refer to... Figure 2 The heterogeneous resource control device 700 of the virtual power plant includes:

[0091] The acquisition unit 701 is used to acquire and process several virtual groups in the virtual power plant based on the scheduling instructions to obtain the original data of each virtual group;

[0092] The conversion unit 702 is used to convert the original data of each virtual group to obtain converted data;

[0093] The aggregation calculation unit 703 is used to perform aggregation calculation processing on the transformed data based on the aggregation strategy to obtain an aggregated dataset.

[0094] Scheduling unit 704 is used to perform scheduling processing on the scheduling instructions and the aggregated dataset according to the scheduling strategy to determine device control instructions;

[0095] The control unit 705 is used to control and process several heterogeneous resources in each virtual group based on the device control instructions.

[0096] In some embodiments, when performing the processing step of converting the original data of each virtual group to obtain converted data, the conversion unit 702 is specifically used for:

[0097] The protocol parser is configured by performing configuration processing on the configuration data to obtain the configured protocol parser.

[0098] The configured protocol parser is used to perform protocol extraction processing on the raw data of each virtual group to obtain extracted data;

[0099] reorganize and convert the extracted data according to the mapping rule script to obtain intermediate data;

[0100] perform validity check processing on the intermediate data according to the detection rule to obtain the converted data.

[0101] In some embodiments, the conversion unit 702, when performing the processing step of performing validity check processing on the intermediate data according to the detection rule to obtain the converted data, is further specifically used for:

[0102] perform cleaning processing on the intermediate data to obtain first data;

[0103] perform filtering and smoothing processing on the first data to obtain second data;

[0104] perform anomaly detection on the second data to obtain the converted data.

[0105] In some embodiments, the aggregation calculation unit 703, when performing the processing step of performing aggregation calculation processing on the converted data based on the aggregation strategy to obtain an aggregated data set, is specifically used for:

[0106] obtain the number of first heterogeneous resources in each virtual group and the real-time power corresponding to each first heterogeneous resource;

[0107] perform first aggregation calculation processing on the number of first heterogeneous resources and the real-time power corresponding to each first heterogeneous resource based on a first aggregation calculation strategy to obtain first aggregated data;

[0108] obtain the current energy percentage and the corresponding rated capacity of each second heterogeneous resource in each virtual group;

[0109] perform second aggregation calculation processing on the current energy percentage and the corresponding rated capacity of each second heterogeneous resource based on a second aggregation calculation strategy to obtain second aggregated data;

[0110] combine the first aggregated data and the second aggregated data to obtain the aggregated data set.

[0111] In some embodiments, the obtaining unit 701, before performing the processing step of obtaining each virtual group's original data by performing obtaining processing on a number of virtual groups in a virtual power plant based on scheduling instructions, is further specifically used for:

[0112] When each heterogeneous resource is accessed, generate a resource identifier and record the static attributes and initial scheduling capability model of each heterogeneous resource;

[0113] According to the resource identifier, the static attribute and transaction demand, each heterogeneous resource is divided to determine a heterogeneous resource mapping table;

[0114] Each virtual group is determined by using the resource mapping table.

[0115] In some embodiments, the scheduling unit 704 is further configured to, before performing the scheduling step of scheduling the scheduling instruction and the aggregated data set according to the scheduling strategy to determine the device control instruction, specifically:

[0116] Obtain historical data of each virtual group, and analyze and process a plurality of heterogeneous resources of each virtual group to obtain physical feature data;

[0117] Feature extraction processing is performed on the historical data, the physical feature data and the aggregated data set to obtain key data;

[0118] Based on the key data, the initial scheduling capability model is constructed to obtain a target scheduling capability model of each virtual group.

[0119] In some embodiments, the scheduling unit 704 is configured to, when performing the scheduling step of scheduling the scheduling instruction and the aggregated data set according to the scheduling strategy to determine the device control instruction, specifically:

[0120] According to the scheduling instruction and the aggregated data set, an initial instruction is generated;

[0121] The target scheduling capability model is called, and the initial instruction is decomposed according to a plurality of heterogeneous resources of each virtual group and the corresponding heterogeneous resource mapping table to obtain the device control instruction.

[0122] It should be noted that the specific implementation process of the above device can be clearly understood by those skilled in the art, which can refer to the corresponding description in the foregoing method embodiments. For the convenience and brevity of description, it will not be repeated here.

[0123] The above device can be implemented in the form of a computer program, which can run on a computer device such as Figure 3 as shown in the figure.

[0124] Please refer to Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided by an embodiment of the present application. The electronic device 800 can be a terminal or a server, wherein the terminal can be an electronic device with communication function. The server can be a stand-alone server or a server cluster composed of multiple servers.

[0125] Referring toFigure 3 The electronic device 800 includes a processor 802, a memory, and a network interface 805 connected through a system bus 801, wherein the memory can include a non-volatile storage medium 803 and an internal memory 804.

[0126] The non-volatile storage medium 803 can store an operating system 8031 and a computer program 8032. The computer program 8032 includes program instructions that, when executed, cause the processor 802 to perform a heterogeneous resource control method for a virtual power plant.

[0127] The processor 802 is configured to provide computing and control capabilities to support the operation of the entire electronic device 800.

[0128] The internal memory 804 provides an environment for the operation of the computer program 8032 in the non-volatile storage medium 803, which, when executed by the processor 802, causes the processor 802 to perform a heterogeneous resource control method for a virtual power plant.

[0129] The network interface 805 is configured to communicate with other devices over a network. Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device 800 to which the scheme of the present application is applied. The specific electronic device 800 can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. Figure 3

[0130] The processor 802 is configured to run the computer program 8032 stored in the memory to implement the following steps:

[0131] Based on the scheduling instructions, the original data of each virtual group is obtained by processing the virtual groups in the virtual power plant;

[0132] The original data of each virtual group is converted to obtain conversion data;

[0133] Based on the aggregation strategy, the conversion data is aggregated and calculated to obtain an aggregated data set;

[0134] According to the scheduling strategy, the scheduling instructions and the aggregated data set are scheduled to determine a device control instruction;

[0135] Based on the device control instruction, the heterogeneous resources in each virtual group are controlled.

[0136] In some embodiments, when implementing the processing step of converting the original data of each virtual group to obtain conversion data, the processor 802 is specifically configured to: ​

[0137] The protocol parser is configured based on the configuration data to obtain a configured protocol parser;

[0138] The original data of each virtual group is subjected to protocol extraction processing by using the configured protocol parser to obtain extraction data;

[0139] The extraction data is subjected to reorganization conversion processing according to a mapping rule script to obtain intermediate data;

[0140] The intermediate data is subjected to validity verification processing according to a detection rule to obtain the conversion data.

[0141] In some embodiments, the processor 802, when implementing the processing step of obtaining the conversion data by subjecting the intermediate data to validity verification processing according to a detection rule, is specifically configured to:

[0142] The intermediate data is subjected to cleaning processing to obtain first data;

[0143] The first data is subjected to filtering and smoothing processing to obtain second data;

[0144] The second data is subjected to abnormality detection to obtain the conversion data.

[0145] In some embodiments, the processor 802, when implementing the processing step of obtaining the aggregated data set by subjecting the conversion data to aggregated calculation processing based on an aggregation strategy, is specifically configured to:

[0146] The number of first heterogeneous resources in each virtual group and real-time power corresponding to each first heterogeneous resource are obtained;

[0147] The number of first heterogeneous resources and real-time power corresponding to each first heterogeneous resource are subjected to first aggregated calculation processing based on a first aggregated calculation strategy to obtain first aggregated data;

[0148] The current energy percentage and corresponding rated capacity of each second heterogeneous resource in each virtual group are obtained;

[0149] The current energy percentage and corresponding rated capacity of each second heterogeneous resource are subjected to second aggregated calculation processing based on a second aggregated calculation strategy to obtain second aggregated data;

[0150] The first aggregated data and the second aggregated data are subjected to combination processing to obtain the aggregated data set.

[0151] In some embodiments, before implementing the processing step of obtaining the original data of each virtual group by subjecting the virtual power plant to obtaining processing based on scheduling instructions, the processor 802 is further specifically configured to:

[0152] When each heterogeneous resource is accessed, a resource identifier is generated, and static attributes and an initial scheduling capability model of each heterogeneous resource are recorded;

[0153] Each heterogeneous resource is divided according to the resource identifier, the static attributes and transaction demand to determine a heterogeneous resource mapping table;

[0154] Each virtual group is determined by using the resource mapping table.

[0155] In some embodiments, the processor 802, before implementing the processing step of scheduling processing the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction, is specifically configured to:

[0156] Obtain historical data of each virtual group, and analyze and process a plurality of heterogeneous resources of each virtual group to obtain physical feature data;

[0157] Feature extraction processing is performed on the historical data, the physical feature data and the aggregated data set to obtain key data;

[0158] Based on the key data, the initial scheduling capability model is constructed to obtain a target scheduling capability model of each virtual group.

[0159] In some embodiments, the processor 802, when implementing the processing step of scheduling processing the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction, is specifically configured to:

[0160] According to the scheduling instruction and the aggregated data set, initial instructions are generated;

[0161] The target scheduling capability model is called, and the initial instructions are decomposed according to a plurality of heterogeneous resources of each virtual group and a corresponding heterogeneous resource mapping table to obtain the device control instruction.

[0162] It should be understood that in the embodiments of the present application, the processor 802 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0163] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by instructing related hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to realize the process steps of the above-mentioned embodiment of the method.

[0164] Therefore, the present application also provides a storage medium. The storage medium can be a computer readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. The program instructions are executed by the processor to make the processor execute the following steps:

[0165] Based on the scheduling instructions, the original data of each virtual group is obtained by processing the virtual groups in the virtual power plant;

[0166] The original data of each virtual group is converted to obtain conversion data;

[0167] Based on the aggregation strategy, the conversion data is aggregated and calculated to obtain an aggregated data set;

[0168] According to the scheduling strategy, the scheduling instructions and the aggregated data set are scheduled to determine the device control instructions;

[0169] Based on the device control instructions, the control processing is performed on the plurality of heterogeneous resources in each virtual group.

[0170] In an embodiment, when the processor executes the program instructions to realize the processing step of converting the original data of each virtual group to obtain conversion data, the processor is specifically used for:

[0171] Based on the configuration data, the protocol parser is configured to obtain a configured protocol parser;

[0172] performing protocol extraction processing on the raw data of each virtual group by using the configured protocol parser to obtain extraction data;

[0173] performing reorganization conversion processing on the extraction data according to a mapping rule script to obtain intermediate data;

[0174] performing validity verification processing on the intermediate data according to a detection rule to obtain the conversion data.

[0175] In an embodiment, when the processor executes the program instructions to implement the processing step of performing validity verification processing on the intermediate data according to a detection rule to obtain the conversion data, the processor is specifically configured to:

[0176] performing cleaning processing on the intermediate data to obtain first data;

[0177] performing filtering and smoothing processing on the first data to obtain second data;

[0178] performing anomaly detection on the second data to obtain the conversion data.

[0179] In an embodiment, when the processor executes the program instructions to implement the processing step of performing aggregation calculation processing on the conversion data based on an aggregation strategy to obtain an aggregated data set, the processor is specifically configured to:

[0180] obtaining a number of first heterogeneous resources in each virtual group and real-time power corresponding to each first heterogeneous resource;

[0181] performing first aggregation calculation processing on the number of first heterogeneous resources and the real-time power corresponding to each first heterogeneous resource based on a first aggregation calculation strategy to obtain first aggregated data;

[0182] obtaining a current energy percentage and a corresponding rated capacity of each second heterogeneous resource in each virtual group;

[0183] performing second aggregation calculation processing on the current energy percentage and the corresponding rated capacity of each second heterogeneous resource based on a second aggregation calculation strategy to obtain second aggregated data;

[0184] performing combination processing on the first aggregated data and the second aggregated data to obtain the aggregated data set.

[0185] In an embodiment, before the processor executes the program instructions to implement the processing step of performing acquisition processing on a plurality of virtual groups in a virtual power plant based on a scheduling instruction to obtain raw data of each virtual group, the processor is specifically configured to:

[0186] When each heterogeneous resource is accessed, a resource identifier is generated, and static attributes and an initial scheduling capability model of each heterogeneous resource are recorded;

[0187] Each heterogeneous resource is divided according to the resource identifier, the static attributes and transaction demand to determine a heterogeneous resource mapping table;

[0188] Each virtual group is determined by using the resource mapping table.

[0189] In an embodiment, before the processor executes the program instructions to implement the processing step of scheduling the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction, specifically for:

[0190] Historical data of each virtual group is obtained, and physical characteristic data of a plurality of heterogeneous resources of each virtual group is obtained through analysis and processing;

[0191] Key data is obtained through feature extraction processing on the historical data, the physical characteristic data and the aggregated data set;

[0192] A target scheduling capability model of each virtual group is obtained through construction processing on the initial scheduling capability model based on the key data.

[0193] In an embodiment, when the processor executes the program instructions to implement the processing step of scheduling the scheduling instruction and the aggregated data set according to a scheduling strategy to determine a device control instruction, specifically for:

[0194] An initial instruction is obtained through generation processing according to the scheduling instruction and the aggregated data set;

[0195] The target scheduling capability model is called, and the initial instruction is decomposed to obtain the device control instruction according to a plurality of heterogeneous resources of each virtual group and a corresponding heterogeneous resource mapping table.

[0196] The storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, and various computer readable storage media that can store program codes.

[0197] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0198] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0199] The steps in the method embodiments of the present application can be sequentially adjusted, combined and deleted according to actual needs. The units in the device embodiments of the present application can be combined, divided and deleted according to actual needs. In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0200] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing an electronic device (which can be a personal computer, a terminal or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0201] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any skilled person in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims. The software tools, models or components appearing in the embodiments of the present application are only illustrative and do not represent actual use.

Claims

1. A method for controlling heterogeneous resources in a virtual power plant, characterized in that, Applications in IoT platforms, including: Based on the scheduling instructions, the raw data of each virtual group in the virtual power plant is obtained by acquiring and processing the data of several virtual groups. The original data for each virtual group is transformed to obtain the transformed data; The transformed data is processed using an aggregation strategy to obtain an aggregated dataset. The scheduling instructions and the aggregated dataset are processed according to the scheduling strategy to determine the device control instructions. Based on the device control commands, control and process several heterogeneous resources in each virtual group; The process of transforming the original data for each virtual group to obtain transformed data includes: The protocol parser is configured by performing configuration processing on the configuration data to obtain the configured protocol parser. The configured protocol parser is used to perform protocol extraction processing on the raw data of each virtual group to obtain extracted data; The extracted data is reorganized and transformed according to the mapping rule script to obtain intermediate data; The intermediate data is validated according to the detection rules to obtain the transformed data. The aggregation calculation processing of the transformed data based on the aggregation strategy to obtain the aggregated dataset includes: Obtain the number of first heterogeneous resources in each virtual group and the real-time power corresponding to each first heterogeneous resource; Based on the first aggregation calculation strategy, the first aggregation calculation is performed on the number of the first heterogeneous resources and the real-time power corresponding to each first heterogeneous resource to obtain the first aggregation data; Obtain the current energy percentage and corresponding rated capacity of each second heterogeneous resource in each virtual group; The second aggregation data is obtained by performing second aggregation calculation on the current energy percentage and corresponding rated capacity of each second heterogeneous resource based on the second aggregation calculation strategy. The aggregated dataset is obtained by combining the first aggregated data and the second aggregated data. The step of scheduling the scheduling instructions and the aggregated dataset according to the scheduling strategy to determine the device control instructions includes: The initial instruction is obtained by generating the initial instruction based on the scheduling instruction and the aggregated dataset. The target scheduling capability model is invoked, and the initial instruction is decomposed and processed according to several heterogeneous resources of each virtual group and the corresponding heterogeneous resource mapping table to obtain the device control instruction.

2. The method according to claim 1, characterized in that, The process of validating the intermediate data according to the detection rules to obtain the transformed data includes: The intermediate data is cleaned to obtain the first data; The first data is filtered and smoothed to obtain the second data; The transformed data is obtained by performing anomaly detection on the second data.

3. The method according to claim 1, characterized in that, Before obtaining the raw data of each virtual group by acquiring and processing several virtual groups in the virtual power plant based on scheduling instructions, the process includes: When each heterogeneous resource is accessed, a resource identifier is generated, and the static attributes and initial scheduling capability model of each heterogeneous resource are recorded. Each heterogeneous resource is partitioned based on the resource identifier, the static attributes, and the transaction requirements to determine a heterogeneous resource mapping table; Each virtual group is determined using the resource mapping table.

4. The method according to claim 3, characterized in that, Before performing scheduling processing on the scheduling instructions and the aggregated dataset according to the scheduling policy to determine the device control instructions, the process includes: Historical data for each virtual group is acquired, and physical characteristic data is obtained by analyzing and processing several heterogeneous resources in each virtual group. Key data are obtained by performing feature extraction processing on the historical data, the physical feature data, and the aggregated dataset; Based on the key data, the initial scheduling capability model is constructed and processed to obtain the target scheduling capability model for each virtual group.

5. A heterogeneous resource control device for a virtual power plant, characterized in that, Applied to an Internet of Things (IoT) platform, it includes a unit for performing the method as described in any one of claims 1-4.

6. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-4.

7. A storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, can implement the method as described in any one of claims 1-4.

Images