Dynamic active power distribution method and device based on load amplitude variation, computer equipment, storage medium and computer program product

Abstract

The invention relates to a dynamic active power distribution method and device based on load amplitude variation, computer equipment, a storage medium and a computer program product. The method comprises the following steps: determining load variation of a power plant according to a current active set value and a historical active set value of the power plant; under the condition that the load variation is smaller than a load threshold value corresponding to the power plant, determining a load adjustment margin of the joint control unit according to a current load value and a load constraint parameter of the joint control unit in the power plant; according to the load adjustment margin, obtaining a predicted load priority of the joint control unit, and according to the predicted load priority, generating load distribution information of the joint control unit; performing verification processing on the load distribution information to obtain a verification result corresponding to the load distribution information; and under the condition that the verification result meets a preset verification result, performing load distribution processing on the joint control unit according to a load distribution instruction corresponding to the load distribution information. By adopting the method, the accuracy of unit load distribution can be improved.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a dynamic active power distribution method, apparatus, computer equipment, computer-readable storage medium, and computer program product based on load variation. Background Technology

[0002] In power plants, accurate load distribution to the generating units is crucial to ensuring their safe and stable operation.

[0003] In traditional technologies, load allocation for generating units is generally done manually. However, manual decision-making is subject to subjective factors and prone to errors, resulting in low accuracy in load allocation. Summary of the Invention

[0004] Therefore, it is necessary to provide a dynamic active power allocation method, device, computer equipment, computer-readable storage medium, and computer program product based on load amplitude that can improve the accuracy of unit load allocation, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a dynamic active power allocation method based on load variation, including:

[0006] Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant;

[0007] The load variation of the power plant is determined based on the current active power setpoint and the historical active power setpoint.

[0008] If the load fluctuation is less than the load threshold value corresponding to the power plant, the load regulation margin of the joint control unit is determined based on the current load value and the load constraint parameters.

[0009] The load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and the load allocation information of the joint control unit is generated based on the predicted load priority.

[0010] The load allocation information is verified based on the load constraint parameters to obtain the verification result corresponding to the load allocation information.

[0011] If the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the load allocation process is performed on the joint control unit according to the load allocation instruction.

[0012] In one embodiment, after determining the load variation of the jointly controlled unit based on the current active power setpoint and the historical active power setpoint, the method further includes:

[0013] When the load variation is greater than or equal to the load threshold, the current actual active power generated by the non-controlled units in the power plant is obtained.

[0014] Based on the current active power setpoint and the current actual active power generated, the total adjustable active power capacity corresponding to the power plant is determined;

[0015] Obtain the maximum active power capacity of the jointly controlled unit, and perform corresponding load allocation processing on the jointly controlled unit based on the total adjustable active power capacity and the maximum active power capacity.

[0016] In one embodiment, the step of performing corresponding load allocation processing on the jointly controlled generating units based on the total adjustable active power capacity and the maximum active power capacity includes:

[0017] Based on the maximum active power capacity, the active power allocation ratio of the jointly controlled units is determined;

[0018] The total adjustable active power capacity and the active power allocation ratio are fused together to obtain the unit adjustable active power capacity of the jointly controlled unit.

[0019] According to the adjustable active power capacity of the unit, the load distribution process is carried out on the jointly controlled unit.

[0020] In one embodiment, the load constraint parameters include the unit operating range of the interconnected unit;

[0021] The step of determining the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters includes:

[0022] Extract the upper limit and lower limit of the unit's operation from the unit's operating range;

[0023] Based on the current load value and the upper limit of unit operation, the increaseable capacity of the jointly controlled unit is determined, and based on the current load value and the lower limit of unit operation, the decreaseable capacity of the jointly controlled unit is determined.

[0024] Based on the increaseable capacity and the decreaseable capacity, the load regulation margin of the jointly controlled unit is obtained.

[0025] In one embodiment, before determining the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters when the load fluctuation is less than the load threshold value corresponding to the power plant, the method further includes:

[0026] Based on the current active power setpoint and the current load value, the current operating status data of the power plant is obtained;

[0027] The unit regulation performance parameters and external environment data of the power plant are obtained, and the current operating status data, the unit regulation performance parameters and the external environment data are input into multiple trained load threshold prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant.

[0028] The multiple predicted load thresholds are fused together according to the model weights of each trained load threshold prediction model to obtain the load threshold value.

[0029] In one embodiment, the step of inputting the load regulation margin into the trained load priority prediction model to obtain the predicted load priority of the coordinated generating units includes:

[0030] The regulation energy consumption and response speed of the jointly controlled unit are obtained;

[0031] Extract the first feature vector corresponding to the load regulation margin, the second feature vector corresponding to the regulation energy consumption, and the third feature vector corresponding to the response speed;

[0032] The first feature vector, the second feature vector, and the third feature vector are subjected to feature alignment processing to obtain the first aligned feature vector corresponding to the load regulation margin, the second aligned feature vector corresponding to the regulation energy consumption, and the third aligned feature vector corresponding to the response speed.

[0033] The first aligned feature vector, the second aligned feature vector, and the third aligned feature vector are fused to obtain a fused feature vector.

[0034] The fused feature vector is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit.

[0035] Secondly, this application also provides a dynamic active power distribution device based on load variation, comprising:

[0036] The data acquisition module is used to acquire the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant;

[0037] The load variation determination module is used to determine the load variation of the power plant based on the current active power setpoint and the historical active power setpoint.

[0038] The margin determination module is used to determine the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters when the load change is less than the load threshold value corresponding to the power plant.

[0039] The information generation module is used to input the load adjustment margin into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and generate the load allocation information of the joint control unit based on the predicted load priority.

[0040] The information verification module is used to verify the load allocation information according to the load constraint parameters and obtain the verification result corresponding to the load allocation information.

[0041] The load allocation module is used to generate a load allocation instruction corresponding to the load allocation information when the verification result meets the preset verification result, and to perform corresponding load allocation processing on the joint control unit according to the load allocation instruction.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0043] Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant;

[0044] The load variation of the power plant is determined based on the current active power setpoint and the historical active power setpoint.

[0045] If the load fluctuation is less than the load threshold value corresponding to the power plant, the load regulation margin of the joint control unit is determined based on the current load value and the load constraint parameters.

[0046] The load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and the load allocation information of the joint control unit is generated based on the predicted load priority.

[0047] The load allocation information is verified based on the load constraint parameters to obtain the verification result corresponding to the load allocation information.

[0048] If the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the load allocation process is performed on the joint control unit according to the load allocation instruction.

[0049] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0050] Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant;

[0051] The load variation of the power plant is determined based on the current active power setpoint and the historical active power setpoint.

[0052] If the load fluctuation is less than the load threshold value corresponding to the power plant, the load regulation margin of the joint control unit is determined based on the current load value and the load constraint parameters.

[0053] The load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and the load allocation information of the joint control unit is generated based on the predicted load priority.

[0054] The load allocation information is verified based on the load constraint parameters to obtain the verification result corresponding to the load allocation information.

[0055] If the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the load allocation process is performed on the joint control unit according to the load allocation instruction.

[0056] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0057] Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant;

[0058] The load variation of the power plant is determined based on the current active power setpoint and the historical active power setpoint.

[0059] If the load fluctuation is less than the load threshold value corresponding to the power plant, the load regulation margin of the joint control unit is determined based on the current load value and the load constraint parameters.

[0060] The load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and the load allocation information of the joint control unit is generated based on the predicted load priority.

[0061] The load allocation information is verified based on the load constraint parameters to obtain the verification result corresponding to the load allocation information.

[0062] If the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the load allocation process is performed on the joint control unit according to the load allocation instruction.

[0063] The aforementioned dynamic active power allocation method, device, computer equipment, storage medium, and computer program product based on load variation first acquires the current and historical active power setpoints of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant. Then, based on the current and historical active power setpoints, the load variation of the power plant is determined. If the load variation is less than the corresponding load threshold value of the power plant, the load regulation margin of the interconnected units is determined based on the current load value and load constraint parameters. Next, the load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the interconnected units. Based on the predicted load priority, load allocation information for the interconnected units is generated. Then, based on the load constraint parameters, the load allocation information is verified to obtain the verification result corresponding to the load allocation information. Finally, if the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the corresponding load allocation processing is performed on the interconnected units according to the load allocation instruction. In this way, when allocating load to the generating units, the load variation is objectively calculated based on the current and historical active power setpoints, avoiding errors from manual estimation. For small load variations, the load adjustment margin of the generating units is accurately determined by combining the current load value and load constraint parameters, ensuring that the allocation is within a safe framework. Then, through the trained priority prediction model, the optimal priority ranking is output by integrating multi-dimensional adjustment characteristics and verified by load constraint parameters to ensure the accuracy of the allocation results, which helps to improve the accuracy of generating unit load allocation. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur when using manual decision-making, which leads to lower accuracy of generating unit load allocation, further improving the accuracy of generating unit load allocation. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating a dynamic active power allocation method based on load variation in one embodiment.

[0066] Figure 2 This is a flowchart illustrating the steps for performing corresponding load allocation processing on the interconnected generating units in one embodiment;

[0067] Figure 3 This is a flowchart illustrating a dynamic active power allocation method based on load variation in another embodiment.

[0068] Figure 4 This is a structural block diagram of a dynamic active power distribution device based on load variation in one embodiment;

[0069] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0072] In one exemplary embodiment, such as Figure 1 As shown, a dynamic active power allocation method based on load variation is provided. This embodiment illustrates the application of this method to a server; it is understood that this method can also be applied to terminals, and can also be applied to systems including terminals and servers, and implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, and tablets; the servers can be independent servers or server clusters composed of multiple servers. In this embodiment, the method includes the following steps:

[0073] Step S101: Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant.

[0074] Among them, a power plant refers to an integrated system with complete power production capabilities, including jointly controlled units and non-jointly controlled units.

[0075] Among them, the joint control unit refers to the unit in the power plant that can receive automatic control commands to adjust its output.

[0076] Non-controlled units refer to units in power plants that cannot receive automatic control commands to adjust their output.

[0077] The current active power setpoint refers to the latest total power generation target value issued by the power grid dispatch center to the power plant.

[0078] Among them, the historical active power setpoint refers to the total power generation target value of the previous cycle issued by the power grid dispatch center to the power plant.

[0079] The current load value refers to the actual output value of the controlled unit at the current moment.

[0080] Among them, load constraint parameters refer to the key parameters corresponding to the safe operating boundary of the unit under joint control, including the unit operating range and the unit vibration range (also known as the vibration zone).

[0081] The operating range of the unit refers to the range of active power that the unit is allowed to output, such as 100~300MW.

[0082] Among them, the unit vibration range refers to the specific active power range that the unit must strictly avoid (for example, due to mechanical resonance). For example, 200~220MW. Even in the operating range of 100~300MW, the unit output must not fall into this range.

[0083] For example, in response to an active power allocation request for the interconnected units in a power plant, the server obtains the current active power setpoint and historical active power setpoint of the power plant based on the power plant's identification information, and obtains the current load value and load constraint parameters of the interconnected units in the power plant based on the interconnected unit's identification information.

[0084] Step S102: Determine the load variation of the power plant based on the current active power setpoint and the historical active power setpoint.

[0085] Among them, load variation refers to the change in the active power setpoint received by the power plant between two adjacent time periods.

[0086] For example, the server subtracts the historical active power setpoint from the current active power setpoint to obtain the change in the active power setpoint, which is used as the load change of the power plant.

[0087] Step S103: If the load variation is less than the load threshold value corresponding to the power plant, determine the load regulation margin of the joint control unit based on the current load value and load constraint parameters.

[0088] Among them, the load threshold value refers to the critical value used to distinguish the degree of load variation.

[0089] Among them, load adjustment margin refers to the load space that can be safely adjusted, including the capacity that can be increased and the capacity that can be decreased.

[0090] For example, when the load variation is less than the load threshold value corresponding to the power plant, the server extracts the feature vector of the current load value and the feature vector of the load constraint parameter, respectively, and inputs the feature vector of the current load value and the feature vector of the load constraint parameter into the trained load regulation margin prediction model to obtain the load regulation margin corresponding to the current load value and the load constraint parameter, which is used as the load regulation margin of the joint control unit.

[0091] Step S104: Input the load regulation margin into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and generate the load allocation information of the joint control unit based on the predicted load priority.

[0092] Among them, the load priority prediction model refers to a network model that can use the load adjustment margin to obtain the predicted load priority of the joint control unit, such as a convolutional neural network model.

[0093] Among them, the predicted load priority refers to the predicted value corresponding to the load priority of the jointly controlled unit.

[0094] Among them, load allocation information refers to the load allocation status of the joint control units, including the load allocation objects, load adjustment directions, and specific load values ​​in the joint control units.

[0095] For example, the server inputs the load regulation margin into a feature extraction model for feature extraction processing to obtain a feature vector of the load regulation margin. Then, the server inputs the feature vector of the load regulation margin into a trained load priority prediction model to obtain the prediction probability of the coordinated units under each preset load priority. From these preset load priorities, the server selects the preset load priority with the highest prediction probability as the predicted load priority of the coordinated units. Finally, based on the predicted load priority, the load regulation margin, and the current active power setpoint, the server generates the load allocation object, load adjustment direction, and specific parameters for the coordinated units. The load value is used as the load allocation information for the coordinated control units. For example, when the load adjustment margin is the capacity that can be increased, the unit with the highest predicted load priority is assigned the incremental capacity according to its capacity: if the unit's capacity can be increased by ≥ the remaining demand (e.g., Unit #1 can increase by 25MW, and the remaining demand is 30MW, then 25MW is allocated, and 5MW is left); if the unit's capacity can be increased by < the remaining demand (e.g., Unit #2 can increase by 10MW, and the remaining demand is 5MW, then 5MW is allocated, and the remaining demand is 0); the load is then allocated downwards according to the predicted load priority until the current active power setpoint is completely allocated.

[0096] Step S105: Based on the load constraint parameters, perform verification processing on the load allocation information to obtain the verification result corresponding to the load allocation information.

[0097] The verification result is used to indicate whether the load allocation information meets the load constraint parameters, such as whether the load allocation information exceeds the unit operating range or falls into the vibration zone.

[0098] For example, the server extracts the unit operating range and unit vibration range of the coordinated unit from the load constraint parameters; then, the server performs verification processing on the load allocation information according to the unit operating range to obtain the first verification result corresponding to the load allocation information, and performs verification processing on the load allocation information according to the unit vibration range to obtain the second verification result corresponding to the load allocation information; then, the server combines the first verification result and the second verification result to obtain the verification result corresponding to the load allocation information.

[0099] Step S106: If the verification result meets the preset verification result, generate the load allocation instruction corresponding to the load allocation information, and perform the corresponding load allocation processing on the joint control unit according to the load allocation instruction.

[0100] Among them, the preset verification result refers to the pre-set verification result, such as the load distribution information not exceeding the unit's operating range or falling into the vibration zone.

[0101] Among them, the load allocation instruction refers to the instruction for load allocation processing of the interconnected generating units.

[0102] For example, the server judges the verification result based on the preset verification result; if the verification result meets the preset verification result, the server inputs the load allocation information into the instruction encapsulation model, performs instruction encapsulation processing on the load allocation information through the instruction encapsulation model, and obtains the load allocation instruction corresponding to the load allocation information; then, the server performs the corresponding load allocation processing on the linked control units according to the load allocation instruction.

[0103] In the aforementioned dynamic active power allocation method based on load variation, the current and historical active power setpoints of the power plant, as well as the current load values ​​and load constraint parameters of the interconnected units within the power plant, are first obtained. Then, based on the current and historical active power setpoints, the load variation of the power plant is determined. If the load variation is less than the corresponding load threshold of the power plant, the load regulation margin of the interconnected units is determined based on the current load value and load constraint parameters. Next, the load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the interconnected units. Based on the predicted load priority, load allocation information of the interconnected units is generated. Then, based on the load constraint parameters, the load allocation information is verified to obtain the verification results corresponding to the load allocation information. Finally, if the verification results meet the preset verification results, a load allocation instruction corresponding to the load allocation information is generated, and the corresponding load allocation processing is performed on the interconnected units according to the load allocation instruction. In this way, when allocating load to the generating units, the load variation is objectively calculated based on the current and historical active power setpoints, avoiding errors from manual estimation. For small load variations, the load adjustment margin of the generating units is accurately determined by combining the current load value and load constraint parameters, ensuring that the allocation is within a safe framework. Then, through the trained priority prediction model, the optimal priority ranking is output by integrating multi-dimensional adjustment characteristics and verified by load constraint parameters to ensure the accuracy of the allocation results, which helps to improve the accuracy of generating unit load allocation. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur when using manual decision-making, which leads to lower accuracy of generating unit load allocation, further improving the accuracy of generating unit load allocation.

[0104] In one exemplary embodiment, such as Figure 2 As shown, step S102 above, after determining the load variation of the jointly controlled unit based on the current active power setpoint and the historical active power setpoint, specifically includes the following steps:

[0105] Step S201: When the load variation is greater than or equal to the load threshold value, obtain the current actual active power generated by the non-controlled units in the power plant.

[0106] Step S202: Determine the total adjustable active power capacity of the power plant based on the current active power setpoint and the current actual active power generated.

[0107] Step S203: Obtain the maximum active capacity of the jointly controlled units, and perform corresponding load allocation processing on the jointly controlled units based on the total adjustable active capacity and the maximum active capacity.

[0108] The current actual active power output refers to the actual active power output of the non-controlled generating units at the current moment.

[0109] The total adjustable active power capacity refers to the total output value that needs to be shared by all the jointly controlled units.

[0110] Among them, the maximum active capacity refers to the maximum output value that a single controlled unit can achieve.

[0111] For example, when the load variation is greater than or equal to the load threshold, the server obtains the current actual active power generated by the non-controlled units in the power plant; then, the server subtracts the current actual active power generated from the current active power setpoint and uses the difference as the total adjustable active power capacity of the power plant; then, the server determines the maximum active power capacity of the controlled units according to the load constraint parameters; then, the server performs corresponding load allocation processing on the controlled units according to the total adjustable active power capacity and the maximum active power capacity.

[0112] In this embodiment, by prioritizing the fixed output of non-controlled units, the total adjustable task to be undertaken by the controlled units is accurately calculated. Then, combined with the safe operating limit of each unit, the load is allocated. This ensures that the total load can quickly respond to the grid dispatch requirements while strictly adhering to the unit safety constraints, avoiding exceeding equipment limits due to large load adjustments. This is beneficial to improving response efficiency and operational safety during large load changes.

[0113] In an exemplary embodiment, step S203 above, which involves performing corresponding load allocation processing on the jointly controlled generating units based on the total adjustable active power capacity and the maximum active power capacity, specifically includes the following: determining the active power allocation ratio of the jointly controlled generating units based on the maximum active power capacity; performing fusion processing on the total adjustable active power capacity and the active power allocation ratio to obtain the unit adjustable active power capacity of the jointly controlled generating units; and performing corresponding load allocation processing on the jointly controlled generating units according to the unit adjustable active power capacity.

[0114] Among them, the active power allocation ratio refers to the allocation weight of the jointly controlled generating units in the total adjustable active power capacity.

[0115] Among them, the adjustable active power capacity of the unit refers to the specific output target value allocated from the total adjustable active power capacity to the jointly controlled units.

[0116] For example, the server normalizes the maximum active power capacity of the controlled units to obtain the normalized maximum active power capacity, which is used as the active power allocation ratio of the controlled units. Then, the server multiplies the total adjustable active power capacity and the active power allocation ratio to obtain the adjustable active power capacity of the controlled units. Next, the server verifies the adjustable active power capacity of the units according to the load constraint parameters to obtain the verification result of the adjustable active power capacity of the units. Then, if the verification result meets the preset verification result, the server performs the corresponding load allocation processing on the controlled units according to the adjustable active power capacity of the units.

[0117] In this embodiment, the active power allocation ratio is determined based on the maximum active power capacity, so that the load allocation weight of each control unit is directly linked to its actual carrying capacity. Then, the specific output target of a single unit is calculated in combination with the total adjustable active power capacity. This ensures that the total load demand is reasonably distributed among the control units, and makes full use of the maximum adjustment potential of each unit, taking into account both operational safety and dispatch response efficiency.

[0118] In one exemplary embodiment, the load constraint parameters include the unit operating range of the linked control unit.

[0119] Therefore, step S103 above, which determines the load regulation margin of the jointly controlled unit based on the current load value and load constraint parameters, specifically includes the following: extracting the upper and lower operating limits of the jointly controlled unit from the unit's operating range; determining the increaseable capacity of the jointly controlled unit based on the current load value and the upper operating limit, and determining the decreaseable capacity of the jointly controlled unit based on the current load value and the lower operating limit; and obtaining the load regulation margin of the jointly controlled unit based on the increaseable and decreaseable capacities.

[0120] Among them, the upper limit of unit operation refers to the maximum value of the unit's operating range.

[0121] Among them, the lower limit of unit operation refers to the minimum value of the unit's operating range.

[0122] The increaseable capacity refers to the maximum active power that can be safely increased based on the current load value, provided that it does not exceed the upper limit of unit operation. The calculation logic is "upper limit of unit operation - current load value".

[0123] The reducible capacity refers to the maximum active power that can be safely reduced based on the current load value, provided that it is not lower than the lower limit of unit operation. The calculation logic is "current load value - lower limit of unit operation".

[0124] For example, the server inputs the unit operating range into the information extraction model, and extracts the upper and lower operating limits of the unit from the unit operating range. Then, the server subtracts the current load value from the upper operating limit to obtain the increase capacity of the unit, and subtracts the lower operating limit from the current load value to obtain the decrease capacity of the unit. Finally, the server uses both the increase and decrease capacity as the load adjustment margin of the unit.

[0125] In this embodiment, by extracting core boundary parameters from the unit's operating range and using the current load value as a benchmark, the available capacity to be increased or decreased is directly calculated and integrated into the load adjustment margin. This can quickly clarify the unit's load adjustment potential within the safe operating range, providing a clear and intuitive basis for subsequent load allocation and ensuring that the unit can stably participate in load adjustment within the operating range.

[0126] In an exemplary embodiment, step S103, before determining the load regulation margin of the jointly controlled unit based on the current load value and load constraint parameters when the load variation is less than the load threshold value corresponding to the power plant, specifically includes the following: obtaining the current operating status data of the power plant based on the current active power setpoint and the current load value; acquiring the unit regulation performance parameters and external environment data of the power plant, and inputting the current operating status data, unit regulation performance parameters, and external environment data into multiple trained load threshold prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant; and fusing the multiple predicted load threshold values ​​according to the model weights of each trained load threshold prediction model to obtain the load threshold value.

[0127] Among them, the current operating status data is used to represent real-time data reflecting the overall current operating status of the power plant.

[0128] Among them, the unit regulation performance parameters refer to the inherent parameters that characterize the load regulation capability of the jointly controlled units, including parameters such as the ramp rate, minimum regulation amount, and regulation response delay of the jointly controlled units.

[0129] External environmental data refers to data on environmental factors that affect the regulation of the power plant units, including the power grid frequency and ambient temperature.

[0130] Among them, the load threshold prediction model refers to a network model that can use current operating status data, unit regulation performance parameters and external environment data to obtain the predicted load threshold value of the power plant, such as the random forest model.

[0131] Among them, the predicted load threshold value refers to the predicted value corresponding to the load threshold value output by the load threshold value prediction model.

[0132] Here, model weight refers to the weight coefficient of the load threshold prediction model.

[0133] For example, the server inputs the current active power setpoint and the current load value into a trained operating status data prediction model to obtain the current operating status data of the power plant. Next, the server acquires the unit regulation performance parameters and external environment data of the power plant, and preprocesses the current operating status data, unit regulation performance parameters, and external environment data to obtain preprocessed current operating status data, preprocessed unit regulation performance parameters, and preprocessed external environment data. Then, the server inputs the preprocessed current operating status data, preprocessed unit regulation performance parameters, and preprocessed external environment data into multiple trained load threshold prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant. Finally, the server sums the multiple predicted load threshold values ​​according to the model weights of each trained load threshold prediction model to obtain the load threshold value corresponding to the power plant.

[0134] In this embodiment, by integrating multi-dimensional data on the current operating status, unit regulation performance, and external environment, multiple trained prediction models are used to output predicted load threshold values ​​from different perspectives. This fully explores the correlation between various influencing factors and the load threshold value, so that the final load threshold value can more accurately adapt to the actual operating scenario of the power plant, which is conducive to improving the accuracy of overall load regulation.

[0135] In an exemplary embodiment, step S104 above, which inputs the load regulation margin into the trained load priority prediction model to obtain the predicted load priority of the coordinated units, specifically includes the following: obtaining the regulation energy consumption and response speed of the coordinated units; extracting the first feature vector corresponding to the load regulation margin, the second feature vector corresponding to the regulation energy consumption, and the third feature vector corresponding to the response speed; performing feature alignment processing on the first feature vector, the second feature vector, and the third feature vector to obtain the first aligned feature vector corresponding to the load regulation margin, the second aligned feature vector corresponding to the regulation energy consumption, and the third aligned feature vector corresponding to the response speed; performing fusion processing on the first aligned feature vector, the second aligned feature vector, and the third aligned feature vector to obtain the fused feature vector; and inputting the fused feature vector into the trained load priority prediction model to obtain the predicted load priority of the coordinated units.

[0136] Among them, the regulation energy consumption is used to represent the energy cost consumed by the joint control unit during the load regulation process (such as the coal consumption of coal-fired units and the gas consumption of gas-fired units).

[0137] Among them, response speed refers to the time required for the control unit to complete the load adjustment from receiving the load adjustment command.

[0138] The first eigenvector refers to the representation vector corresponding to the load adjustment margin.

[0139] The second eigenvector refers to the representation vector corresponding to the adjustment of energy consumption.

[0140] The third eigenvector refers to the representation vector corresponding to the response speed.

[0141] Here, the first aligned feature vector refers to the first feature vector after feature alignment processing.

[0142] Here, the second aligned feature vector refers to the second feature vector after feature alignment processing.

[0143] The third aligned feature vector refers to the third feature vector after feature alignment processing.

[0144] The fused feature vector refers to the feature vector obtained by fusing the first aligned feature vector, the second aligned feature vector, and the third aligned feature vector.

[0145] For example, the server retrieves the regulation energy consumption and response speed of the jointly controlled generating unit from the database based on the unit identifier. Then, the server inputs the load regulation margin, regulation energy consumption, and response speed into a feature extraction model, which extracts a first feature vector corresponding to the load regulation margin, a second feature vector corresponding to the regulation energy consumption, and a third feature vector corresponding to the response speed. Next, the server performs normalization and dimension matching on the first, second, and third feature vectors to obtain a first aligned feature vector corresponding to the load regulation margin, a second aligned feature vector corresponding to the regulation energy consumption, and a third feature vector corresponding to the response speed. The server calculates the third aligned feature vector corresponding to the speed. Then, according to the first preset weight corresponding to the load adjustment margin, the second preset weight corresponding to the energy consumption adjustment, and the third preset weight corresponding to the response speed, the server sums the first aligned feature vector, the second aligned feature vector, and the third aligned feature vector to obtain the fused feature vector. Then, the server inputs the fused feature vector into the trained load priority prediction model to obtain the prediction probability of the joint control unit under each preset load priority. From each preset load priority, the preset load priority with the highest prediction probability is selected as the predicted load priority of the joint control unit.

[0146] In this embodiment, by integrating the three core dimensions of regulation potential, economy and timeliness of the joint control unit, the key capability indicators of the unit's participation in load allocation are fully covered, so that the final output of the predicted load priority can accurately reflect the adaptability of the unit in the current scenario, thereby improving the overall efficiency, economy and reliability of load regulation.

[0147] In one exemplary embodiment, such as Figure 3As shown, another dynamic active power allocation method based on load variation is provided. Taking the application of this method to a server as an example, the specific steps include:

[0148] Step S301: Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant; the load constraint parameters include the unit operating range of the interconnected units.

[0149] Step S302: Determine the load variation of the power plant based on the current active power setpoint and the historical active power setpoint.

[0150] Step S303: Based on the current active power setpoint and the current load value, obtain the current operating status data of the power plant.

[0151] Step S304: Obtain the unit regulation performance parameters and external environment data of the power plant, and input the current operating status data, unit regulation performance parameters and external environment data into multiple trained load threshold prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant.

[0152] Step S305: According to the model weights of each trained load threshold prediction model, multiple predicted load thresholds are fused to obtain the load threshold value corresponding to the power plant.

[0153] Step S306: If the load variation is less than the load threshold value corresponding to the power plant, extract the upper limit value and lower limit value of the unit operation of the joint control unit from the unit operation range.

[0154] Step S307: Determine the increaseable capacity of the jointly controlled unit based on the current load value and the upper limit of unit operation, and determine the decreaseable capacity of the jointly controlled unit based on the current load value and the lower limit of unit operation.

[0155] Step S308: Based on the capacity that can be increased and the capacity that can be decreased, the load regulation margin of the jointly controlled unit is obtained.

[0156] Step S309: Obtain the regulation energy consumption and response speed of the jointly controlled unit; extract the first feature vector corresponding to the load regulation margin, the second feature vector corresponding to the regulation energy consumption, and the third feature vector corresponding to the response speed.

[0157] Step S310: Perform feature alignment processing on the first feature vector, the second feature vector, and the third feature vector to obtain the first aligned feature vector corresponding to the load regulation margin, the second aligned feature vector corresponding to the regulation energy consumption, and the third aligned feature vector corresponding to the response speed.

[0158] Step S311: The first aligned feature vector, the second aligned feature vector, and the third aligned feature vector are fused to obtain a fused feature vector; the fused feature vector is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit.

[0159] Step S312: Generate load allocation information for the coordinated units based on the predicted load priority.

[0160] Step S313: Based on the load constraint parameters, perform verification processing on the load allocation information to obtain the verification result corresponding to the load allocation information.

[0161] Step S314: If the verification result meets the preset verification result, generate the load allocation instruction corresponding to the load allocation information, and perform the corresponding load allocation processing on the joint control unit according to the load allocation instruction.

[0162] In the aforementioned dynamic active power allocation method based on load variation, when allocating load to the units, the load variation is objectively calculated based on the current and historical active power setpoints, avoiding errors from manual estimation. For small load variations, the unit load adjustment margin is accurately determined by combining the current load value and load constraint parameters to ensure that the allocation is within a safe framework. Then, through the trained priority prediction model, the optimal priority ranking is output by integrating multi-dimensional adjustment characteristics and verified by load constraint parameters to ensure the accuracy of the allocation results, which helps to improve the accuracy of unit load allocation. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur in manual decision-making, which leads to low accuracy of unit load allocation, further improving the accuracy of unit load allocation.

[0163] In one exemplary embodiment, to more clearly illustrate the dynamic active power allocation method based on load variation provided in this application, the following specific embodiment will be used to describe the method in detail. In one embodiment, this application also provides another dynamic active power allocation method based on load variation. Specifically, it includes the following:

[0164] 1. Obtain basic parameters: Collect the total active power setpoint of the whole plant, the actual active power generated by non-controlled units, and the current load and adjustable range (upper and lower limits of operating range, upper and lower limits of vibration zone) of each controlled unit.

[0165] 2. Determine the load change range: Calculate the difference between two consecutive active power setpoints and compare it with the preset "small load threshold value" to determine whether to use small load distribution or proportional distribution;

[0166] 3. Low load allocation logic activation: If the difference is less than the threshold value, enter low load allocation:

[0167] Calculate the increaseable capacity (upper limit - current load) and decreaseable capacity (current load - lower limit) within the current adjustable range of each control unit.

[0168] Based on the size of the capacity that can be increased / decreased, determine the priority of increasing / decreasing load (the larger the capacity, the higher the priority);

[0169] 4. Implement low load allocation: Prioritize allocating load increase commands to the units with the highest load increase priority, or allocate load reduction commands to the units with the highest load reduction priority; if a single unit cannot meet the regulation demand, expand to the next highest priority units in sequence;

[0170] 5. Activation of proportional distribution logic: If the difference is greater than or equal to the threshold value, proportional distribution is adopted: calculate the adjustable active power of the whole plant (set value - non-joint control actual value), and distribute the load to each joint control unit according to the "maximum active power capacity ratio of the unit";

[0171] 6. Safety verification: Ensure that the allocation results do not exceed the unit's operating range or fall into the vibration zone. If they do, readjust the allocation until the safety constraints are met.

[0172] In the above embodiments, when allocating load to the generating units, the load variation is objectively calculated based on the current and historical active power setpoints, avoiding errors from manual estimation. For small load variations, the load adjustment margin of the generating units is accurately determined by combining the current load value and load constraint parameters, ensuring that the allocation is within a safe framework. Then, through the trained priority prediction model, the optimal priority ranking is output by integrating multi-dimensional adjustment characteristics and verified by load constraint parameters to ensure the accuracy of the allocation results, which helps to improve the accuracy of generating unit load allocation. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur when using manual decision-making, which leads to low accuracy of generating unit load allocation, further improving the accuracy of generating unit load allocation.

[0173] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0174] Based on the same inventive concept, this application also provides a dynamic active power allocation device based on load amplitude for implementing the dynamic active power allocation method based on load amplitude described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the dynamic active power allocation device based on load amplitude provided below can be found in the limitations of the dynamic active power allocation method based on load amplitude above, and will not be repeated here.

[0175] In one exemplary embodiment, such as Figure 4 As shown, a dynamic active power distribution device based on load variation is provided, comprising: a data acquisition module 401, a variation determination module 402, a margin determination module 403, an information generation module 404, an information verification module 405, and a load distribution module 406, wherein:

[0176] The data acquisition module 401 is used to acquire the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant.

[0177] The variable determination module 402 is used to determine the load variation of the power plant based on the current active power setpoint and the historical active power setpoint.

[0178] The margin determination module 403 is used to determine the load regulation margin of the joint control unit based on the current load value and load constraint parameters when the load change is less than the load threshold value corresponding to the power plant.

[0179] The information generation module 404 is used to input the load regulation margin into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and generate the load allocation information of the joint control unit based on the predicted load priority.

[0180] The information verification module 405 is used to verify the load allocation information according to the load constraint parameters and obtain the verification result corresponding to the load allocation information.

[0181] The load allocation module 406 is used to generate a load allocation instruction corresponding to the load allocation information when the verification result meets the preset verification result, and to perform corresponding load allocation processing on the joint control unit according to the load allocation instruction.

[0182] In an exemplary embodiment, the dynamic active power allocation device based on load variation further includes a load processing module, used to obtain the current actual active power value of non-controlled units in the power plant when the load variation is greater than or equal to the load threshold value; determine the total adjustable active power capacity of the power plant based on the current active power setpoint and the current actual active power value; obtain the maximum active power capacity of the controlled units; and perform corresponding load allocation processing on the controlled units based on the total adjustable active power capacity and the maximum active power capacity.

[0183] In an exemplary embodiment, the load processing module is further configured to determine the active power allocation ratio of the jointly controlled units based on the maximum active power capacity; perform fusion processing on the total adjustable active power capacity and the active power allocation ratio to obtain the unit adjustable active power capacity of the jointly controlled units; and perform corresponding load allocation processing on the jointly controlled units according to the unit adjustable active power capacity.

[0184] In an exemplary embodiment, the margin determination module 403 is further configured to extract the upper limit and lower limit of the unit operation of the jointly controlled unit from the unit operation range; determine the increaseable capacity of the jointly controlled unit based on the current load value and the upper limit of the unit operation, and determine the decreaseable capacity of the jointly controlled unit based on the current load value and the lower limit of the unit operation; and obtain the load regulation margin of the jointly controlled unit based on the increaseable capacity and the decreaseable capacity.

[0185] In an exemplary embodiment, the dynamic active power allocation device based on load variation further includes a threshold value determination module, used to obtain the current operating status data of the power plant based on the current active power setpoint and the current load value; acquire the unit regulation performance parameters and external environment data of the power plant, and input the current operating status data, unit regulation performance parameters and external environment data into multiple trained load threshold value prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant; and perform fusion processing on the multiple predicted load threshold values ​​according to the model weight of each trained load threshold value prediction model to obtain the load threshold value.

[0186] In an exemplary embodiment, the information generation module 404 is further configured to acquire the regulation energy consumption and response speed of the jointly controlled unit; extract a first feature vector corresponding to the load regulation margin, a second feature vector corresponding to the regulation energy consumption, and a third feature vector corresponding to the response speed; perform feature alignment processing on the first feature vector, the second feature vector, and the third feature vector to obtain a first aligned feature vector corresponding to the load regulation margin, a second aligned feature vector corresponding to the regulation energy consumption, and a third aligned feature vector corresponding to the response speed; perform fusion processing on the first aligned feature vector, the second aligned feature vector, and the third aligned feature vector to obtain a fused feature vector; and input the fused feature vector into the trained load priority prediction model to obtain the predicted load priority of the jointly controlled unit.

[0187] Each module in the aforementioned dynamic active power distribution device based on load variation can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0188] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as current active power setpoints and historical active power setpoints. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a dynamic active power allocation method based on load variation.

[0189] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0190] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0191] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0192] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0193] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0194] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A dynamic active power allocation method based on load variation, characterized in that, The method includes: Obtain the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant; The load variation of the power plant is determined based on the current active power setpoint and the historical active power setpoint. If the load variation is less than the load threshold value corresponding to the power plant, the load regulation margin of the joint control unit is determined based on the current load value and the load constraint parameters. The load regulation margin is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and the load allocation information of the joint control unit is generated based on the predicted load priority. The load allocation information is verified based on the load constraint parameters to obtain the verification result corresponding to the load allocation information. If the verification result meets the preset verification result, a load allocation instruction corresponding to the load allocation information is generated, and the load allocation process is performed on the joint control unit according to the load allocation instruction.

2. The method according to claim 1, characterized in that, After determining the load variation of the jointly controlled unit based on the current active power setpoint and the historical active power setpoint, the method further includes: When the load variation is greater than or equal to the load threshold, the current actual active power generated by the non-controlled units in the power plant is obtained. Based on the current active power setpoint and the current actual active power generated, the total adjustable active power capacity corresponding to the power plant is determined; Obtain the maximum active power capacity of the jointly controlled unit, and perform corresponding load allocation processing on the jointly controlled unit based on the total adjustable active power capacity and the maximum active power capacity.

3. The method according to claim 2, characterized in that, The step of performing corresponding load allocation processing on the jointly controlled generating units based on the total adjustable active power capacity and the maximum active power capacity includes: Based on the maximum active power capacity, the active power allocation ratio of the jointly controlled units is determined; The total adjustable active power capacity and the active power allocation ratio are fused together to obtain the unit adjustable active power capacity of the jointly controlled unit. According to the adjustable active power capacity of the unit, the load distribution process is carried out on the jointly controlled unit.

4. The method according to claim 1, characterized in that, The load constraint parameters include the unit operating range of the jointly controlled unit; The step of determining the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters includes: Extract the upper limit and lower limit of the unit's operation from the unit's operating range; Based on the current load value and the upper limit of unit operation, the increaseable capacity of the jointly controlled unit is determined, and based on the current load value and the lower limit of unit operation, the decreaseable capacity of the jointly controlled unit is determined. Based on the increaseable capacity and the decreaseable capacity, the load regulation margin of the jointly controlled unit is obtained.

5. The method according to claim 1, characterized in that, Before determining the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters when the load fluctuation is less than the load threshold value corresponding to the power plant, the method further includes: Based on the current active power setpoint and the current load value, the current operating status data of the power plant is obtained; The unit regulation performance parameters and external environment data of the power plant are obtained, and the current operating status data, the unit regulation performance parameters and the external environment data are input into multiple trained load threshold prediction models to obtain multiple predicted load threshold values ​​corresponding to the power plant. The multiple predicted load thresholds are fused together according to the model weights of each trained load threshold prediction model to obtain the load threshold value.

6. The method according to any one of claims 1 to 5, characterized in that, The step of inputting the load regulation margin into the trained load priority prediction model to obtain the predicted load priority of the coordinated units includes: The regulation energy consumption and response speed of the jointly controlled unit are obtained; Extract the first feature vector corresponding to the load regulation margin, the second feature vector corresponding to the regulation energy consumption, and the third feature vector corresponding to the response speed; The first feature vector, the second feature vector, and the third feature vector are subjected to feature alignment processing to obtain the first aligned feature vector corresponding to the load regulation margin, the second aligned feature vector corresponding to the regulation energy consumption, and the third aligned feature vector corresponding to the response speed. The first aligned feature vector, the second aligned feature vector, and the third aligned feature vector are fused to obtain a fused feature vector. The fused feature vector is input into the trained load priority prediction model to obtain the predicted load priority of the joint control unit.

7. A dynamic active power distribution device based on load variation, characterized in that, The device includes: The data acquisition module is used to acquire the current active power setpoint and historical active power setpoint of the power plant, as well as the current load value and load constraint parameters of the interconnected units in the power plant; The load variation determination module is used to determine the load variation of the power plant based on the current active power setpoint and the historical active power setpoint. The margin determination module is used to determine the load regulation margin of the jointly controlled unit based on the current load value and the load constraint parameters when the load change is less than the load threshold value corresponding to the power plant. The information generation module is used to input the load adjustment margin into the trained load priority prediction model to obtain the predicted load priority of the joint control unit, and generate the load allocation information of the joint control unit based on the predicted load priority. The information verification module is used to verify the load allocation information according to the load constraint parameters and obtain the verification result corresponding to the load allocation information. The load allocation module is used to generate a load allocation instruction corresponding to the load allocation information when the verification result meets the preset verification result, and to perform corresponding load allocation processing on the joint control unit according to the load allocation instruction.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images