Clean energy virtual power plant control optimization method and system

Abstract

The invention relates to the technical field of power dispatching, in particular to a clean energy virtual power plant control optimization method and system, and the method comprises the steps: obtaining the power consumption demand of each controllable load, the real-time power data and historical power data generated by each distributed power supply, and the remaining capacity of a battery of an energy storage unit, and calculating an optimization tendency characterization value; dividing an optimization tendency category of each time period, and selecting an optimization strategy, including calculating a demand state characterization value, and judging whether the time period is a strong optimization time period; the strategy selection unit is used for selecting a time period, dividing the time period into a plurality of sub time periods, calculating an optimization tendency characterization value of each sub time period, identifying a feature sub time period, and the display unit is used for displaying a judgment result of the strategy selection unit. Therefore, the time period in which optimization control needs to be carried out can be obtained more accurately, and the operation effectiveness of the virtual power plant is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power dispatching, and in particular to a clean energy virtual power plant control optimization method and system. Background Art

[0002] In today's rapidly developing power system, the instability of electricity demand has become a prominent problem. With economic fluctuations, climate change, and the large-scale grid connection of renewable energy, the load of the power system has become more complex and unpredictable. This demand-side fluctuation has brought great challenges to the stable operation of the power grid, especially during the peak period of power supply and distribution, when the contradiction between supply and demand is particularly prominent. In order to effectively manage this volatility, the concept of virtual power plant (VPP) came into being. A virtual power plant is a system that integrates decentralized power generation resources, energy storage equipment, controllable loads, etc. through advanced information and communication technologies for centralized management and scheduling. It can monitor and optimize electricity demand in real time, and achieve effective management of the balance of power grid supply and demand through flexible control strategies.

[0003] Chinese Patent Publication No.: CN111463834A, discloses a method for controlling the operation of a virtual power plant, including the following steps: obtaining a predicted power generation curve within a preset time interval and a predicted power consumption curve within a preset time interval; generating a predicted power supply curve based on the predicted power generation curve and the predicted power consumption curve; regularly obtaining a first difference between the actual power supply of the virtual power plant in the current time period and the predicted power supply in the current time period; generating first control information based on the first difference and the predicted power supply in the next time period, and sending the first control information to each energy node controller of the virtual power plant, so that the energy node controller can adjust the operating state of the controllable load or energy storage device of the energy node controller in the next time period according to the first control information. The present invention also discloses a virtual power plant, which achieves the effect of reducing the cost of the virtual power plant.

[0004] However, the prior art still has the following problems:

[0005] In the prior art, the problem that the actual amount of electricity generated by the distributed power source may have a large error compared with the prediction is not considered, which leads to the problem of unreliable management and optimization of the operation of distributed energy resources. Summary of the invention

[0006] To this end, the present invention provides a clean energy virtual power plant control optimization method and system to overcome the problem in the prior art that the actual amount of electricity generated by distributed power sources may have a large error compared with the prediction, thereby leading to the problem of being unable to reliably manage and optimize the operation of distributed energy resources.

[0007] To achieve the above objectives, the present invention provides a clean energy virtual power plant control optimization system, comprising:

[0008] A data collection module is used to obtain the power demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit;

[0009] A data classification module, connected to the data collection module, is used to calculate the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and divide the optimization tendency category of each time period;

[0010] A data analysis module, connected to the data collection module and the data classification module, including a strategy selection unit and a display unit;

[0011] The strategy selection unit is used to select an optimization strategy according to the optimization tendency category of each time period, including:

[0012] Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period;

[0013] Dividing the time period into a plurality of sub-time periods, calculating the optimization tendency characterization value of each sub-time period, and identifying characteristic sub-time periods;

[0014] The display unit is used to display the decision result of the strategy selection unit.

[0015] Furthermore, the data classification module also includes a method for obtaining the difference between the real-time power data and the historical power data generated by each distributed power source, wherein:

[0016] Obtain the real-time power generated by each distributed power source in each time period and the corresponding historical power;

[0017] Calculate the difference between the real-time power generated by each distributed power source in each time period and the corresponding historical power;

[0018] The sum of the differences between the real-time power generated by each distributed power source and the corresponding historical power is recorded as the difference between the real-time power data generated by each distributed power source and the historical power data.

[0019] Furthermore, the data classification module calculates the optimization tendency characterization value according to formula (1):

[0020]

[0021] In formula (1), D represents the optimization tendency characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, X represents the difference, and X0 represents the preset difference threshold.

[0022] Furthermore, the data classification module divides each time period into optimization tendency categories.

[0023] The data classification module compares the optimization tendency characterization value with a preset optimization tendency characterization value comparison threshold,

[0024] If the optimization tendency characterization value within the time period is less than a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period into a weak optimization tendency category;

[0025] If the optimization tendency characterization value within the time period is greater than or equal to a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period as a strong optimization tendency category.

[0026] Furthermore, the strategy selection unit selects the optimization strategy according to the optimization tendency category of each time period, wherein:

[0027] If the optimization tendency category within the time period is a weak optimization tendency category, the time period is divided into a plurality of sub-time periods, the optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified;

[0028] If the optimization tendency category within the time period is a strong optimization tendency category, obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period.

[0029] Furthermore, the strategy selection unit calculates the demand state characterization value according to formula (2):

[0030]

[0031] In formula (2), E represents the demand state characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, C represents the remaining capacity of the energy storage unit battery, and C0 represents the preset remaining capacity threshold of the energy storage unit battery.

[0032] Furthermore, the strategy selection unit determines whether the time period is a strong optimization time period.

[0033] The demand state characterization value of the time period is compared with a preset demand state characterization value comparison threshold,

[0034] If the demand state characterization value of the time period is greater than a preset demand state characterization value comparison threshold, it is determined whether the time period is a strong optimization time period.

[0035] Furthermore, the strategy selection unit divides the time period into a plurality of sub-time periods, wherein each sub-time period has an equal length.

[0036] Furthermore, the strategy selection unit identifies characteristic sub-time periods,

[0037] The optimization tendency characterization value of each sub-time period is compared with the optimization tendency characterization value comparison threshold of the preset sub-time period.

[0038] If the optimization tendency characterization value of the sub-time period is greater than a preset optimization tendency characterization value comparison threshold of the sub-time period, the sub-time period is identified as a characteristic sub-time period.

[0039] Furthermore, a virtual power plant control optimization method is provided.

[0040] Step S1, obtaining the power demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit;

[0041] Step S2, calculating the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and dividing the optimization tendency category of each time period;

[0042] Step S3, selecting an optimization strategy according to the optimization tendency category of each time period, including:

[0043] Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period;

[0044] The time period is divided into a number of sub-time periods, an optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified.

[0045] Compared with the prior art, the present invention obtains the electricity demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit, calculates the optimization tendency characterization value, divides the optimization tendency category of each time period, and selects the optimization strategy, including calculating the demand state characterization value, determining whether the time period is a strong optimization time period; dividing the time period into several sub-time periods, calculating the optimization tendency characterization value of each sub-time period, identifying characteristic sub-time periods, and a display unit for displaying the determination result of the strategy selection unit. The present invention obtains time periods with high electricity demand and low prediction accuracy of the electricity generated by distributed power sources, and further screens the time periods, so as to more accurately obtain the time periods that need to be optimized and controlled, thereby improving the effectiveness of the operation of the virtual power plant.

[0046] In particular, the present invention calculates the optimization tendency characterization value through the data classification module. The electricity demand of each controllable load in each time period can characterize the electricity demand situation in the time period. The difference between the real-time electricity data and the historical electricity data generated by each distributed power source can characterize the accuracy of the electricity prediction generated by the distributed power source in the time period. By calculating the optimization tendency characterization value, the time period with high electricity demand and low accuracy of distributed power source prediction can be obtained, which provides data support for the follow-up and improves the control optimization of the virtual power plant.

[0047] In particular, the present invention divides the optimization tendency categories of each time period through a data classification module. Since the user's electricity demand varies greatly in different time periods, there are large differences in the accuracy of the prediction of the amount of electricity generated by each distributed power source in different time periods. By obtaining the time periods with high electricity demand and low accuracy of the prediction of the amount of electricity generated by the distributed power source, the time periods that need to be optimized and controlled can be obtained more accurately, thereby improving the effectiveness of the operation of the virtual power plant.

[0048] In particular, the present invention calculates the demand state characterization value through the strategy selection unit. The remaining capacity of the energy storage unit battery and the electricity demand of each controllable load are important influencing parameters for whether the virtual power plant operates effectively. When the optimization tendency category of the time period is a strong optimization tendency category, the virtual power plant is prone to fail to operate effectively. When the energy reserves of the energy storage units in the virtual power plant are relatively sufficient, even if the electricity demand is high and the prediction accuracy of the electricity generated by the distributed power source is low, it is not easy to affect the effective operation of the virtual power plant. When the energy reserves of the energy storage units in the virtual power plant are relatively insufficient, it is more likely that the virtual power plant cannot operate effectively. By calculating the demand state characterization value, the time periods of the strong optimization tendency category can be further screened, thereby improving the monitoring of the virtual power plant, thereby improving the effective operation of the virtual power plant.

[0049] In particular, the present invention identifies characteristic sub-time periods through a strategy selection unit. When the optimization tendency category of the time period is a weak optimization tendency category, the virtual power plant is basically in an effective operation stage. However, the power demand and the prediction accuracy of the power generated by the distributed power source may fluctuate to a certain extent. Thus, sub-time periods with larger fluctuations are identified, thereby improving the monitoring of the virtual power plant and improving the effective operation of the virtual power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A structural diagram of a clean energy virtual power plant control optimization system according to an embodiment of the invention;

[0051] Figure 2 It is a structural diagram of a data analysis module of an embodiment of the invention;

[0052] Figure 3 A logical decision diagram for classifying optimization tendency categories for each time period by a data classification module of an embodiment of the invention;

[0053] Figure 4 This is a logical decision diagram for a strategy selection unit in an embodiment of the present invention to determine whether a time period is a strong optimization time period. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0056] See also Figure 1-Figure 4 As shown, Figure 1 This is a structural diagram of the clean energy virtual power plant control optimization system of the embodiment of the invention. Figure 2 This is a structural diagram of a data analysis module according to an embodiment of the invention. Figure 3 The data classification module of the embodiment of the invention divides the optimization tendency category logic decision diagram of each time period, Figure 4 This is a logic determination diagram of whether a time period is a strong optimization time period determined by a strategy selection unit of an embodiment of the invention. The clean energy virtual power plant control optimization system of the present invention includes:

[0057] A data collection module is used to obtain the power demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit;

[0058] A data classification module, connected to the data collection module, is used to calculate the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and divide the optimization tendency category of each time period;

[0059] A data analysis module, connected to the data collection module and the data classification module, including a strategy selection unit and a display unit;

[0060] The strategy selection unit is used to select an optimization strategy according to the optimization tendency category of each time period, including:

[0061] Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period;

[0062] Dividing the time period into a plurality of sub-time periods, calculating the optimization tendency characterization value of each sub-time period, and identifying characteristic sub-time periods;

[0063] The display unit is used to display the decision result of the strategy selection unit.

[0064] In this embodiment, the data collection module, the data classification module, and the data analysis module can all be composed of logic components or a combination of logic components, and the logic components include a field programmable processor, a computer, or a microprocessor in a computer.

[0065] In this embodiment, the duration of each time period is selected within the range of [1h, 2h].

[0066] Specifically, the data classification module also includes a method for obtaining the difference between the real-time power data and the historical power data generated by each distributed power source, wherein:

[0067] Obtain the real-time power generated by each distributed power source in each time period and the corresponding historical power;

[0068] Calculate the difference between the real-time power generated by each distributed power source in each time period and the corresponding historical power;

[0069] The sum of the differences between the real-time power generated by each distributed power source and the corresponding historical power is recorded as the difference between the real-time power data generated by each distributed power source and the historical power data.

[0070] Specifically, the data classification module calculates the optimization tendency representation value according to formula (1):

[0071]

[0072] In formula (1), D represents the optimization tendency characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, X represents the difference, and X0 represents the preset difference threshold.

[0073] In this embodiment, Q0 and X0 are pre-measured in experiments, and the electricity demand in each time period, the real-time electricity data and the historical electricity data generated by each distributed power source are obtained. The average electricity demand Qe is calculated according to the electricity demand in each time period. It is assumed that Q0 = a×Qe, 1.3<a<1.5, a is the electricity demand coefficient, and the average difference Xe is calculated according to the real-time electricity data and the historical electricity data generated by each distributed power source in each time period. It is assumed that X0 = b×Xe, 1.1<b<1.3, b is the difference coefficient.

[0074] Specifically, the present invention calculates the optimization tendency characterization value through the data classification module. The electricity demand of each controllable load in each time period can characterize the electricity demand situation in the time period. The difference between the real-time electricity data and the historical electricity data generated by each distributed power source can characterize the accuracy of the electricity prediction generated by the distributed power source in the time period. By calculating the optimization tendency characterization value, the time period with high electricity demand and low accuracy of distributed power source prediction can be obtained, which provides data support for the follow-up and improves the control optimization of the virtual power plant.

[0075] Specifically, the data classification module divides each time period into optimization tendency categories.

[0076] The data classification module compares the optimization tendency characterization value with a preset optimization tendency characterization value comparison threshold,

[0077] If the optimization tendency characterization value within the time period is less than a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period into a weak optimization tendency category;

[0078] If the optimization tendency characterization value within the time period is greater than or equal to a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period as a strong optimization tendency category.

[0079] In this embodiment, the preset optimization tendency characterization value comparison threshold is selected within the range of [1.55, 1.60].

[0080] Specifically, the present invention divides the optimization tendency categories of each time period through a data classification module. Since the user's electricity demand varies greatly in different time periods, there are large differences in the accuracy of the prediction of the amount of electricity generated by each distributed power source in different time periods. By obtaining the time periods with high electricity demand and low accuracy of the prediction of the amount of electricity generated by the distributed power source, the time periods that need to be optimized and controlled can be obtained more accurately, thereby improving the effectiveness of the operation of the virtual power plant.

[0081] Specifically, the strategy selection unit selects an optimization strategy according to the optimization tendency category of each time period, wherein:

[0082] If the optimization tendency category within the time period is a weak optimization tendency category, the time period is divided into a plurality of sub-time periods, the optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified;

[0083] If the optimization tendency category within the time period is a strong optimization tendency category, obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period.

[0084] Specifically, the strategy selection unit calculates the demand state representation value according to formula (2):

[0085]

[0086] In formula (2), E represents the demand state characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, C represents the remaining capacity of the energy storage unit battery, and C0 represents the preset remaining capacity threshold of the energy storage unit battery.

[0087] In this embodiment, C0 is selected within the range of [0.6Cq, 0.8Cq], where Cq is the total capacity of the energy storage unit battery.

[0088] Specifically, the present invention calculates the demand state characterization value through the strategy selection unit. The remaining capacity of the energy storage unit battery and the electricity demand of each controllable load are important influencing parameters for whether the virtual power plant operates effectively. When the optimization tendency category of the time period is a strong optimization tendency category, the virtual power plant is prone to fail to operate effectively. When the energy storage unit energy reserves in the virtual power plant are relatively sufficient, even if the electricity demand is high and the prediction accuracy of the electricity generated by the distributed power source is low, it is not easy to affect the effective operation of the virtual power plant. When the energy storage unit energy reserves in the virtual power plant are relatively insufficient, it is more likely that the virtual power plant cannot operate effectively. By calculating the demand state characterization value, the time period of the strong optimization tendency category can be further screened, thereby improving the monitoring of the virtual power plant, thereby improving the effective operation of the virtual power plant.

[0089] Specifically, the strategy selection unit determines whether the time period is a strong optimization time period.

[0090] The demand state characterization value of the time period is compared with a preset demand state characterization value comparison threshold,

[0091] If the demand state characterization value of the time period is greater than a preset demand state characterization value comparison threshold, it is determined whether the time period is a strong optimization time period.

[0092] In this embodiment, the preset demand state characterization value comparison threshold is selected within the range of [1.55, 1.60].

[0093] Specifically, the strategy selection unit divides the time period into a plurality of sub-time periods, wherein each sub-time period has an equal length.

[0094] In this embodiment, the sub-time period is selected within the range of [20 min, 30 min].

[0095] Specifically, the strategy selection unit identifies a characteristic sub-time period,

[0096] The optimization tendency characterization value of each sub-time period is compared with the optimization tendency characterization value comparison threshold of the preset sub-time period.

[0097] If the optimization tendency characterization value of the sub-time period is greater than a preset optimization tendency characterization value comparison threshold of the sub-time period, the sub-time period is identified as a characteristic sub-time period.

[0098] In this embodiment, the optimization tendency characterization value Dz of each sub-time period is obtained, and the average optimization tendency characterization value Dze of each sub-time period is calculated. The optimization tendency characterization value comparison threshold Dz0 of the preset sub-time period is set to be c×Dze, 1.1<c<1.2, and c is the optimization tendency characterization value coefficient of the sub-time period.

[0099] Specifically, the present invention identifies characteristic sub-time periods through a strategy selection unit. When the optimization tendency category of the time period is a weak optimization tendency category, the virtual power plant is basically in an effective operation stage. However, the power demand and the prediction accuracy of the power generated by the distributed power source may fluctuate to a certain extent. Thus, sub-time periods with larger fluctuations are identified, thereby improving the monitoring of the virtual power plant and improving the effective operation of the virtual power plant.

[0100] In this embodiment, the display unit displays the determination result and the characteristic sub-time period.

[0101] Specifically, a virtual power plant control optimization method is proposed.

[0102] Step S1, obtaining the power demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit;

[0103] Step S2, calculating the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and dividing the optimization tendency category of each time period;

[0104] Step S3, selecting an optimization strategy according to the optimization tendency category of each time period, including:

[0105] Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period;

[0106] The time period is divided into a number of sub-time periods, an optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified.

[0107] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A clean energy virtual power plant control optimization system, characterized in that: include: A data collection module is used to obtain the power demand of each controllable load, the real-time and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit; A data classification module, connected to the data collection module, is used to calculate the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and divide the optimization tendency category of each time period; A data analysis module, connected to the data collection module and the data classification module, including a strategy selection unit and a display unit; The strategy selection unit is used to select an optimization strategy according to the optimization tendency category of each time period, including: Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period; Dividing the time period into a plurality of sub-time periods, calculating the optimization tendency characterization value of each sub-time period, and identifying characteristic sub-time periods; The display unit is used to display the decision result of the strategy selection unit.

2. The clean energy virtual power plant control optimization system according to claim 1 is characterized in that: The data classification module also includes a method for obtaining the difference between the real-time power data and the historical power data generated by each distributed power source, wherein: Obtain the real-time power generated by each distributed power source in each time period and the corresponding historical power; Calculate the difference between the real-time power generated by each distributed power source in each time period and the corresponding historical power; The sum of the differences between the real-time power generated by each distributed power source and the corresponding historical power is recorded as the difference between the real-time power data generated by each distributed power source and the historical power data.

3. The clean energy virtual power plant control optimization system according to claim 2 is characterized in that: The data classification module calculates the optimization tendency characterization value according to formula (1), In formula (1), D represents the optimization tendency characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, X represents the difference, and X0 represents the preset difference threshold.

4. The clean energy virtual power plant control optimization system according to claim 3 is characterized in that: The data classification module divides each time period into optimization tendency categories, The data classification module compares the optimization tendency characterization value with a preset optimization tendency characterization value comparison threshold, If the optimization tendency characterization value within the time period is less than a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period into a weak optimization tendency category; If the optimization tendency characterization value within the time period is greater than or equal to a preset optimization tendency characterization value comparison threshold, the data classification module classifies the optimization tendency category within the time period as a strong optimization tendency category.

5. The clean energy virtual power plant control optimization system according to claim 4 is characterized in that: The strategy selection unit selects an optimization strategy according to the optimization tendency category of each time period, wherein: If the optimization tendency category within the time period is a weak optimization tendency category, the time period is divided into a plurality of sub-time periods, the optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified; If the optimization tendency category within the time period is a strong optimization tendency category, obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value based on the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period.

6. The clean energy virtual power plant control optimization system according to claim 1 is characterized in that: The strategy selection unit calculates the demand state representation value according to formula (2): In formula (2), E represents the demand state characterization value, Q represents the power demand of each controllable load, Q0 represents the preset power demand threshold, C represents the remaining capacity of the energy storage unit battery, and C0 represents the preset remaining capacity threshold of the energy storage unit battery.

7. The clean energy virtual power plant control optimization system according to claim 6 is characterized in that: The strategy selection unit determines whether the time period is a strong optimization time period, The demand state characterization value of the time period is compared with a preset demand state characterization value comparison threshold, If the demand state characterization value of the time period is greater than a preset demand state characterization value comparison threshold, it is determined whether the time period is a strong optimization time period.

8. The clean energy virtual power plant control optimization system according to claim 1, characterized in that: The strategy selection unit divides the time period into a plurality of sub-time periods, wherein each sub-time period has an equal length.

9. The clean energy virtual power plant control optimization system according to claim 1, characterized in that: The strategy selection unit identifies characteristic sub-time periods, The optimization tendency characterization value of each sub-time period is compared with the optimization tendency characterization value comparison threshold of the preset sub-time period. If the optimization tendency characterization value of the sub-time period is greater than a preset optimization tendency characterization value comparison threshold of the sub-time period, the sub-time period is identified as a characteristic sub-time period.

10. A virtual power plant control optimization method applied to the clean energy virtual power plant control optimization system according to any one of claims 1 to 9, characterized in that: Step S1, obtaining the power demand of each controllable load, the real-time power data and historical power data generated by each distributed power source, and the remaining battery capacity of the energy storage unit; Step S2, calculating the optimization tendency characterization value according to the power demand of each controllable load in each time period combined with the difference between the real-time power data and the historical power data generated by each distributed power source, and dividing the optimization tendency category of each time period; Step S3, selecting an optimization strategy according to the optimization tendency category of each time period, including: Obtain the remaining capacity of the energy storage unit battery in the time period, calculate the demand state characterization value according to the remaining capacity of the energy storage unit battery and the power demand of each controllable load, and determine whether the time period is a strong optimization time period; The time period is divided into a number of sub-time periods, an optimization tendency characterization value of each sub-time period is calculated, and a characteristic sub-time period is identified.

Images