A virtual power plant optimization scheduling method and system

Abstract

The present application discloses a virtual power plant optimization scheduling method and system, which relates to the field of power regulation technology. The method includes comparing the historical power demand value and the actual power demand value in the obtained preset sub-region set to screen out the target sub-region, screening out the pre-processing associated sub-region set from the preset sub-region set, statistically analyzing the resource allocation condition information of the first target associated sub-region and the target sub-region extracted from the pre-processing associated sub-region set in the preset first historical period, screening out the second target associated sub-region set in the preset second historical period from the preset sub-region set, combining the obtained first resource allocation condition and the second resource allocation condition set into a resource allocation condition set, obtaining the current feature information set affecting power distribution, matching the pre-processing resource allocation condition from the resource allocation condition set, and rescheduling and allocating resources. The present invention provides a virtual power plant optimization scheduling method and system, which improves resource utilization.

Description

Technical Field

[0001] The present application relates to the technical field of power regulation, and in particular to a virtual power plant optimization scheduling method and system. Background Art

[0002] A virtual power plant is a power coordination management system that uses advanced information and communication technologies and software systems to achieve the aggregation and coordinated optimization of distributed energy resources DER (Distributed Energy Resources), such as distributed generation DG (Distributed Generation), energy storage system (ESS), controllable load, and electric vehicle (EV), so as to participate in the electricity market and power grid operation as a special power plant.

[0003] Virtual power plants integrate a variety of distributed energy, energy storage equipment and load resources. Because they have different characteristics, it is more difficult to reasonably dispatch virtual power plants and affects the resource integration efficiency of virtual power plants. In view of the above problems, how to integrate and dispatch dispersed resources and improve energy utilization efficiency is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a virtual power plant optimization scheduling method and system.

[0005] In a first aspect, the present application provides a virtual power plant optimization scheduling method, the method comprising:

[0006] Acquire a detection area, divide the detection area into several sub-areas to obtain a preset sub-area set, compare historical power consumption demand values ​​of multiple buildings with different power consumption levels in the preset sub-area set with actual power consumption demand values ​​of charging piles in corresponding location areas to obtain a comparison result set, and screen out a target sub-area according to a first comparison result in the comparison result set;

[0007] According to the target sub-region, a pre-processing associated sub-region set is screened out from a preset sub-region set, where the pre-processing associated sub-region set refers to a sub-region that is adjacent to the target sub-region;

[0008] Performing difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data, and extracting a first target associated sub-region from the pre-processed associated sub-region set according to the first associated difference data;

[0009] The resource allocation condition information of the first target-associated sub-region and the target sub-region in a preset first historical period is counted to obtain a first resource allocation condition, a second target-associated sub-region set in a preset second historical period is selected from the preset sub-region set, and a second resource allocation condition set is counted based on the second target-associated sub-region set, and the first resource allocation condition and the second resource allocation condition set are combined into a resource allocation condition set;

[0010] Obtain a current feature information set that affects power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period; match a preprocessing resource allocation condition from a resource allocation condition set based on the current feature information set that affects power distribution; and reschedule and allocate resources for the total allocatable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period based on the preprocessing resource allocation condition.

[0011] Preferably, a detection area is obtained, and distribution statistics of buildings with multiple different power consumption levels are performed on the detection area to obtain building distribution statistics results;

[0012] According to the building distribution statistics, the detection area is divided into a plurality of sub-areas to obtain a preset sub-area set;

[0013] The distribution of charging piles in each sub-area of ​​the preset sub-area set is counted to obtain a charging pile distribution statistical result set;

[0014] Preset a first historical period, where the first historical period is a recent historical period, and obtain a data set of historical power consumption demand values ​​of buildings in each sub-area in the preset sub-area set in the first historical period;

[0015] Obtain a data set of historical actual power demand values ​​of charging piles in each distribution result in the first historical period in the charging pile distribution statistical result set;

[0016] Compare the historical power demand value data set with the historical actual power demand value data set in a one-to-one correspondence, and output a comparison result set;

[0017] A first comparison result is selected from the comparison result set, wherein the first comparison result refers to a value in a historical power demand value data set that is greater than or less than a historical actual power demand value data set, and a corresponding target sub-area that meets the first comparison result is extracted from the preset sub-area set.

[0018] Preferably, according to the target sub-region, multiple sub-regions adjacent to the target sub-region are screened out from a preset sub-region set, and an associated sub-region set is output;

[0019] A second comparison result is screened out from the comparison result set. If the first comparison result is that a historical power consumption demand value set is smaller than a value in a historical actual power consumption demand value set, then the second comparison result refers to a value in a historical power consumption demand value set that is larger than a value in a historical actual power consumption demand value set. If the first comparison result is that a historical power consumption demand value set is larger than a value in a historical actual power consumption demand value set, then the second comparison result refers to a value in a historical power consumption demand value set that is smaller than a value in a historical actual power consumption demand value set. A corresponding preprocessed associated sub-region set with an opposite condition to the second comparison result is extracted from the associated sub-region set.

[0020] Preferably, a difference calculation is performed on the first comparison result to obtain a first demand difference, and a first demand difference set is output according to the first demand difference;

[0021] performing difference calculation on the second comparison result to obtain a second demand difference, and outputting a second demand difference set according to the second demand difference;

[0022] Perform one-to-one correspondence statistics on the first demand difference set and the second demand difference set to obtain a difference data set;

[0023] Preset a demand difference associated interval value, and filter out first associated difference data within the demand difference associated interval value from the difference data set;

[0024] According to the first associated difference data, a first target associated sub-region that meets the first associated difference data is extracted from the pre-processed associated sub-region set.

[0025] Preferably, the characteristic information affecting power distribution of the target sub-area and the first target associated sub-area in the first historical period is collected respectively, and a first characteristic information set affecting power distribution is output;

[0026] The first power distribution influencing characteristic information set and the first associated difference data are combined into a first resource allocation condition;

[0027] Preset a second historical period, the second historical period is located in all historical periods before the first historical period, obtain second associated difference data according to the second historical period, and output a second associated difference data set according to the second associated difference data;

[0028] Extracting a second target associated subregion from the preset subregion set, and outputting a second target associated subregion set according to the second target associated subregion, wherein the second target associated subregion set refers to the remaining adjacent associated subregions excluding the first target associated subregion;

[0029] Collect the power distribution-influencing feature information of the target sub-area and the second target associated sub-area respectively in the second historical period, and output a second power distribution-influencing feature information set;

[0030] The second power distribution influencing characteristic information set and the second associated difference data set are combined into a second resource allocation condition set;

[0031] The first power distribution-affecting feature information set and the second power distribution-affecting feature information set are combined into a power distribution-affecting feature reference information set, and the first resource allocation condition set and the second resource allocation condition set are combined into a resource allocation condition set.

[0032] Preferably, the power distribution-influencing characteristic information of the target sub-region in the current time period and the power distribution-influencing characteristic information of all sub-regions adjacent to the target sub-region in the preset sub-region set are obtained, and the current power distribution-influencing characteristic information set is output;

[0033] Filter out a preprocessed power distribution influencing feature information set that best matches the current power distribution influencing feature information set from the power distribution influencing feature reference information set;

[0034] According to the preprocessing power distribution-affecting feature information set, a corresponding preprocessing resource allocation condition is screened out from a resource allocation condition set;

[0035] According to the current information set of characteristics affecting power distribution, the power demand forecast value of buildings in the target sub-area in the current period and the power demand forecast value of buildings in all sub-areas adjacent to the target sub-area in the preset sub-area set are respectively predicted, and the current power demand forecast value data set is output;

[0036] Collect the distributable load of charging piles in the target sub-area in the current period and the distributable load of charging piles in all sub-areas adjacent to the target sub-area in the preset sub-area set, and output the total distributable load of charging piles;

[0037] The total allocatable load of the charging pile, the current power demand forecast value data set and the pre-processed resource allocation conditions are all input into the virtual power plant adjustable resource model for resource rescheduling and allocation.

[0038] In a second aspect, a virtual power plant optimization dispatching system includes:

[0039] The target area analysis unit is used to obtain the detection area, divide the detection area into several sub-areas to obtain a preset sub-area set, compare the historical power consumption demand values ​​of multiple buildings with different power consumption levels in the preset sub-area set with the actual power consumption demand values ​​of the charging piles in the corresponding location area to obtain a comparison result set, and screen out the target sub-area according to the first comparison result in the comparison result set;

[0040] An adjacent region analysis unit is used to select a pre-processed associated sub-region set from a preset sub-region set according to a target sub-region, where the pre-processed associated sub-region set refers to a sub-region that is adjacent to the target sub-region;

[0041] an associated region determining unit, configured to perform difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data, and extract a first target associated subregion from the preprocessed associated subregion set according to the first associated difference data;

[0042] an allocation condition statistics unit, configured to obtain a first resource allocation condition by collecting statistics on the resource allocation condition information of the first target associated sub-region and the target sub-region in a preset first historical period, filter out a second target associated sub-region set in a preset second historical period from the preset sub-region set, obtain a second resource allocation condition set based on the second target associated sub-region set, and collect the first resource allocation condition and the second resource allocation condition set into a resource allocation condition set;

[0043] The resource allocation processing unit is used to obtain the current feature information set that affects power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period, match the pre-processing resource allocation conditions from the resource allocation condition set according to the current feature information set that affects power distribution, and re-schedule and allocate resources for the total allocatable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period according to the pre-processing resource allocation conditions.

[0044] Compared with the prior art, the present invention has the following characteristics and beneficial effects:

[0045] By classifying and counting the power consumption levels of buildings in the monitoring area, it is convenient to divide the monitoring area into multiple preset sub-areas, reducing the interference between data caused by the traditional technology of not conducting detailed analysis on the distribution of buildings with different power consumption levels in different locations, resulting in large errors in resource allocation results and increased resource waste. When the detection and analysis shows that the power consumption demand value of the building in the target sub-area is different from the actual power demand value of the charging pile in the corresponding area, it means that the first target associated sub-area located in the target sub-area has a certain correlation effect, that is, the charging piles in the buildings in the first target associated sub-area also use part of the resources, resulting in the target sub-area. The actual electricity demand value of the charging pile is less than the building electricity demand value, and the building electricity demand value and the actual electricity demand value of the charging pile in the target sub-area of ​​each historical period will change, so different historical periods are analyzed, that is, the adjacent sub-areas with correlation will also change, so the adjacent sub-areas that have changed in different historical periods are statistically analyzed, so as to statistically obtain the regular characteristics of the changes in the building electricity demand value and the actual electricity demand value of the charging pile in the target sub-area, and collect and count the conditional information of resource allocation, so as to match the target sub-area of ​​the current period to analyze the required resource allocation conditions, so as to make more accurate resource rescheduling and allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flowchart of the steps of a virtual power plant optimization scheduling method mainly embodied in this embodiment.

[0047] Figure 2 It is a structural block diagram of a virtual power plant optimization scheduling system mainly embodied in this embodiment. DETAILED DESCRIPTION

[0048] The present invention is further described in detail below with reference to the following examples.

[0049] Reference Figure 1 , a virtual power plant optimization scheduling method and system, the method comprising the following steps:

[0050] S1. Obtain a detection area, divide the detection area into several sub-areas to obtain a preset sub-area set, compare the historical power consumption demand values ​​of various buildings with different power consumption levels in the preset sub-area set with the actual power consumption demand values ​​of charging piles in the corresponding location area to obtain a comparison result set, and screen out the target sub-area based on the first comparison result in the comparison result set.

[0051] S2. According to the target sub-region, a pre-processing associated sub-region set is screened out from the preset sub-region set, where the pre-processing associated sub-region set refers to a sub-region that is adjacent to the target sub-region.

[0052] S3. Perform difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data, and extract a first target associated sub-region from the pre-processed associated sub-region set based on the first associated difference data.

[0053] S4. Count the resource allocation condition information of the first target associated sub-area and the target sub-area within the preset first historical period to obtain a first resource allocation condition, select a second target associated sub-area set within the preset second historical period from the preset sub-area set, count a second resource allocation condition set based on the second target associated sub-area set, and the first resource allocation condition and the second resource allocation condition set are combined into a resource allocation condition set.

[0054] S5. Obtain the current feature information set that affects power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period, match the pre-processing resource allocation conditions from the resource allocation condition set based on the current feature information set that affects power distribution, and re-dispatch and allocate resources for the total allocatable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period based on the pre-processing resource allocation conditions.

[0055] Specifically, the detection area is first determined. The levels of building power consumption demand values ​​contained in the large-scale detection area are different, and the distribution areas of buildings with different power consumption levels are also different. Therefore, the monitoring area is divided into several sub-areas according to the distribution locations of buildings with different power consumption levels to obtain a preset sub-area set. For sub-areas in the preset sub-area set where resource utilization does not meet the standards, that is, the building power consumption demand value is different from the actual power demand value of the charging pile, the sub-area in this case is screened out as the target sub-area, and the sub-area adjacent to the target sub-area position is screened out from the remaining preset sub-area sets, and the building power consumption demand value is compared with the actual power demand value of the charging pile in the same way, and the result of the comparison is opposite to the result of the above-mentioned target sub-area analysis and comparison, then the adjacent sub-area corresponding to this result is used as the first target associated sub-area, so as to combine the target sub-area with the first target associated sub-area. The resource allocation condition information of the correlation between the two is analyzed to count the resource allocation condition information as one of the reference matching conditions for the subsequent resource reallocation of the charging piles in the current target sub-area. In addition, the associated adjacent sub-areas of the target sub-area will also change in different historical periods. It is necessary to count the adjacent sub-areas that have changed in different historical periods, that is, to select the second target associated sub-area set from the preset sub-area set, and use the same analysis steps as above to count the resource allocation condition information between the target sub-area and the second target associated sub-area set. Finally, all the resource allocation condition information obtained by counting are combined to obtain a resource allocation condition set. Finally, the current distribution feature information set affecting the target sub-area and the adjacent sub-area in the current period is obtained to match the most matching pre-processing resource allocation condition from the resource allocation condition set, so as to realize the rescheduling and allocation of the total load that can be allocated to the charging piles and improve the utilization rate of resources.

[0056] The specific step S1 includes the following sub-steps:

[0057] The detection area is obtained, and the distribution of buildings with various power consumption levels in the detection area is statistically analyzed to obtain the building distribution statistical results.

[0058] According to the statistical results of building distribution, the detection area is divided into several sub-areas to obtain a preset sub-area set.

[0059] The distribution of charging piles in each sub-area of ​​the preset sub-area set is statistically analyzed to obtain a charging pile distribution statistical result set.

[0060] A first historical period is preset, where the first historical period is a recent historical period, and a data set of historical power consumption demand values ​​of buildings in each sub-area in the preset sub-area set during the first historical period is obtained.

[0061] Obtain a data set of historical actual power demand values ​​of charging piles in each distribution result in the first historical period in the charging pile distribution statistical result set.

[0062] A one-to-one numerical comparison is performed between a historical power demand value data set and a historical actual power demand value data set, and a comparison result set is output.

[0063] A first comparison result is selected from the comparison result set, wherein the first comparison result refers to a value in a historical power demand value data set that is greater than or less than a historical actual power demand value data set, and a corresponding target sub-area that meets the first comparison result is extracted from the preset sub-area set.

[0064] Specifically, if the detection area is area A, the building distribution statistics (area A contains buildings of various power consumption levels, here take three levels as an example: level one power consumption buildings, level two power consumption buildings and level three power consumption buildings, level one buildings consume the most power), a preset sub-area set (if the distribution areas of the above three levels of buildings are not uniform, the location area of ​​the level one power consumption building set is recorded as area a, the location area of ​​the level two power consumption building set is recorded as area b, and the location area of ​​the level three power consumption building set is recorded as area c, and these areas are divided into sub-areas accordingly, that is, preset sub-areas a, b, and c are obtained. Area A also includes preset sub-areas d, e, f, and g. Here only the three preset sub-areas a, b, and c are used for explanation, and the three types of preset sub-areas a, b, and c are not limited to one, that is, there can be two or more preset sub-areas a), a preset first historical period (such as within the previous week or month), a data set of historical power consumption demand values ​​(for example, if the building power consumption demand value in the preset sub-area a is 70%, the building power consumption demand value in the preset sub-area b is 70%, and the building power consumption demand value in the preset sub-area b is 70%. The power demand value is 60%, and the power demand value of buildings in the preset sub-area c is 50%), a data set of historical actual power demand values ​​(for example, the actual power demand value of charging piles in the preset sub-area a is 50%, the actual power demand value of charging piles in the preset sub-area b is 70%, and the actual power demand value of charging piles in the preset sub-area c is 40%, where the total allocatable resources are 100%), a comparison result set (the comparison result set obtained is the preset sub-area a: the power demand value is 20% greater than the actual power demand value, the preset sub-area b: the power demand value is 10% less than the actual power demand value, and the preset sub-area c is greater than the actual power demand value by 10%), and the first comparison result is screened out from the comparison result set (for example, the comparison result set of the preset sub-areas a and c is recorded as the first comparison result, and the comparison result set of the preset sub-area b is recorded as the second comparison result. Conversely, if the preset sub-area b is recorded as the first comparison result, the preset sub-areas a and c are recorded as the second comparison result), and a target sub-area (the preset sub-areas a and c are taken as the target sub-areas).

[0065] The specific step S2 includes the following sub-steps:

[0066] According to the target sub-region, multiple sub-regions adjacent to the target sub-region are screened out from the preset sub-region set, and an associated sub-region set is output.

[0067] A second comparison result is screened out from the comparison result set. If the first comparison result is that a value in a historical power consumption demand value dataset is smaller than a value in a historical actual power consumption demand value dataset, then the second comparison result refers to a value in a historical power consumption demand value dataset that is larger than a value in a historical actual power consumption demand value dataset. If the first comparison result is that a value in a historical power consumption demand value dataset is larger than a value in a historical actual power consumption demand value dataset, then the second comparison result refers to a value in a historical power consumption demand value dataset that is smaller than a value in a historical actual power consumption demand value dataset. A corresponding preprocessed associated sub-region set with an opposite condition to the second comparison result is extracted from the associated sub-region set.

[0068] Specifically, such as the associated sub-region set (taking the preset sub-region a in the target sub-region as an example, the preset sub-region a is also called the target sub-region. If the above-mentioned b, d, e, f preset sub-regions are adjacent sub-regions of the target sub-region a, the b, d, e, f preset sub-regions are called the associated sub-region set), the second comparison result (based on the above-mentioned first comparison result, the second comparison result here is the b preset sub-region: the power consumption demand value is less than 10% of the actual power demand value. Similarly, if the d, e, and f preset sub-regions are respectively: the power consumption demand value is less than 20% of the actual power demand value, the power consumption demand value is greater than 15% of the actual power demand value, and the power consumption demand value is equal to the actual power demand value, the second comparison result here is the b preset sub-region: the power consumption demand value is less than 10% of the actual power demand value, the d preset sub-region: the power consumption demand value is less than 20% of the actual power demand value, the power consumption demand value is greater than 15% of the actual power demand value, and the power consumption demand value is equal to the actual power demand value, then the b and d preset sub-regions here are called the pre-processed associated sub-region set).

[0069] The specific step S3 includes the following sub-steps:

[0070] A difference calculation is performed on the first comparison result to obtain a first demand difference, and a first demand difference set is output based on the first demand difference.

[0071] A second demand difference value is obtained by performing a difference calculation on the second comparison result, and a second demand difference value set is output according to the second demand difference value.

[0072] The first demand difference set and the second demand difference set are statistically analyzed in one-to-one correspondence to obtain a difference data set.

[0073] A demand difference associated interval value is preset, and first associated difference data within the demand difference associated interval value is screened out from the difference data set.

[0074] According to the first associated difference data, a first target associated sub-region that meets the first associated difference data is extracted from the pre-processed associated sub-region set.

[0075] Specifically, such as the first demand difference set (that is, a: 20%, c: 10% mentioned above, taking a as the target sub-area as an example as mentioned above, the subsequent data analysis is performed on a: 20%), the second demand difference set (that is, b: 10%, d: 20%), the difference data set (that is, the difference data between a and b is 10%, and the difference data between a and d is 0), the preset demand difference associated interval value (if it is 0-10%), the first target associated sub-area (that is, the b and d preset sub-areas, one of the preset sub-areas is selected here as an example for explanation, if it is the B preset sub-area, it is also called the first target associated sub-area).

[0076] The specific step S4 includes the following sub-steps:

[0077] The characteristic information affecting power distribution of the target sub-area and the first target associated sub-area in the first historical period is collected respectively, and a first characteristic information set affecting power distribution is output.

[0078] The first power distribution influencing characteristic information set and the first associated difference data are combined into a first resource allocation condition.

[0079] A second historical period is preset, and the second historical period is located in all historical periods before the first historical period. According to the second historical period, second associated difference data is obtained, and according to the second associated difference data, a second associated difference data set is output.

[0080] A second target associated subregion is extracted from the preset subregion set, and a second target associated subregion set is outputted based on the second target associated subregion, wherein the second target associated subregion set refers to the remaining adjacent associated subregions excluding the first target associated subregion.

[0081] The power distribution-affecting feature information of the target sub-area and the second target associated sub-area in the second historical period is collected respectively, and a second power distribution-affecting feature information set is output.

[0082] The second power distribution influencing characteristic information set and the second associated difference data set are combined into a second resource allocation condition set.

[0083] The first power distribution influencing feature information set and the second power distribution influencing feature information set are combined into a power distribution influencing feature reference information set, and the first resource allocation condition set and the second resource allocation condition set are combined into a resource allocation condition set.

[0084] Specifically, the first set of characteristic information affecting power distribution (i.e., the environmental conditions in the previous week in history in a preset sub-area: a fluctuation chart of weather condition change trend, a fluctuation chart of electricity market price trend, and the frequency of equipment failure and maintenance as well as a variety of characteristic information affecting power distribution during the maintenance period), the first resource allocation condition (refers to the preset optimization scheduling information table that is statistically calculated, which serves as the reference condition information for subsequent resource scheduling and allocation: if the conditions are x and y, when the condition x is matched and satisfied, the available resources can be scheduled and allocated according to the remaining y conditions), a preset second historical period (if it is within the previous two weeks, the previous three weeks, or the previous four weeks, if the best detection historical period here is the previous month), a second associated difference data set (the analysis steps are the same as those of the first associated difference data, and no further explanation is given here), and a second set of characteristic information affecting power distribution (the explanation is the same as that of the first characteristic information affecting power distribution, No further explanation is given here), resource allocation condition set (i.e., the set of all resource allocation conditions for changes in association characteristics between different target-associated sub-regions in the target sub-region within the previous two weeks, the previous three weeks, and the previous four weeks. For example, when the first target-associated sub-region of the target sub-region a is matched and it is not the preset sub-region b, then other preset sub-regions that meet the conditions can be matched from the resource allocation condition set, and the subsequent resource allocation condition information analysis can be continued, such as in the first historical period: target sub-region a, the first target-associated sub-region is b, in the second historical period: target sub-region a, the second target-associated sub-region is c, in the third historical period: target sub-region a, the second target-associated sub-region is d, in the fourth historical period: target sub-region a, the second target-associated sub-region is e, and the resource allocation condition information analyzed and statistically obtained in each historical period is combined to obtain the resource allocation condition set).

[0085] The specific step S5 includes the following sub-steps:

[0086] The power distribution feature information affecting the target sub-area in the current period and the power distribution feature information affecting all sub-areas adjacent to the target sub-area in the preset sub-area set are obtained, and the current power distribution feature information set affecting the power distribution is output.

[0087] A preprocessing feature information set affecting power distribution that best matches the current feature information set affecting power distribution is selected from the reference feature information set affecting power distribution.

[0088] According to the preprocessing information set of the characteristics influencing power distribution, the corresponding preprocessing resource allocation conditions are screened out from the resource allocation condition set.

[0089] According to the current information set of characteristics affecting power distribution, the power consumption demand forecast value of buildings in the target sub-area during the current period and the power consumption demand forecast value of buildings in all sub-areas adjacent to the target sub-area in the preset sub-area set are predicted respectively, and the current power consumption demand forecast value data set is output.

[0090] The allocatable load of charging piles in the target sub-area in the current period and the allocatable load of charging piles in all sub-areas adjacent to the target sub-area in the preset sub-area set are collected, and the total allocatable load of charging piles is output.

[0091] The total allocatable load of charging piles, the current power demand forecast data set and the pre-processed resource allocation conditions are input into the virtual power plant adjustable resource model for resource rescheduling and allocation.

[0092] Specifically, for example, the current feature information set affecting power distribution (which is the same as the explanation of the first feature information set affecting power distribution mentioned above, and will not be further explained here), the pre-processing feature information set affecting power distribution (i.e., the current feature information set affecting power distribution: the fluctuation chart of weather condition change trend, the fluctuation chart of power market price trend, and the frequency of equipment failure and maintenance, as well as the maintenance period, are matched with the reference information set affecting power distribution characteristics. When the information change characteristic matching degree is as high as 90%, the pre-processing feature information set affecting power distribution is selected: if it is the respective feature information affecting power distribution of the target sub-area a and the first target associated sub-area b in the first historical period), the corresponding pre-processing resource allocation condition is selected from the resource allocation condition set (i.e., the first associated difference data corresponding to the target sub-area a and the first target associated sub-area b in the first historical period is selected, i.e., the first resource allocation condition is selected), if the current period is one week, the current power consumption demand forecast value data set (i.e., the building power consumption forecast model of the prior art: such as the multivariate linear regression model is used to predict the current feature information affecting power distribution in the current period, if the target a The power demand forecast value of the target sub-area is 60%, and the power demand forecast value of the first target associated sub-area b is 40%: the preset sub-areas are concentrated in the sub-areas adjacent to the target sub-area), the total load that can be allocated to the charging piles (the original load that can be allocated to the charging piles in the target sub-area a is 60%, and the original load that can be allocated to the first target associated sub-area b is 80%, then the total load that can be allocated to the charging piles is 140%), and the virtual power plant can adjust the resource model (such as the optimization scheduling model in the prior art: the optimization scheduling model optimizes the scheduling of multiple energy resources to improve the efficiency and Reliability, according to the above charging pile can allocate total load: 140%, current power demand forecast value data set: the power demand forecast value of target sub-area a is 60%, the power demand forecast value of the first target associated sub-area b is 40% and the pre-processing resource allocation condition: the first associated difference data 10%, then the remaining 140% of M numerical resources can be allocated to the target sub-area a, and the remaining 140%-M=N numerical resources can be allocated to the first target associated sub-area b, and M is 10% more than N), to achieve resource rescheduling and allocation, and improve resource utilization.

[0093] A virtual power plant optimization scheduling system, by applying a virtual power plant optimization scheduling method as described above, includes a target area analysis unit, an adjacent area analysis unit, an associated area determination unit, an allocation condition statistics unit and a resource allocation processing unit, with reference to Figure 2, the detection area is obtained by the target area analysis unit, and the detection area is divided into several sub-areas to obtain a preset sub-area set. The historical power consumption demand values ​​of various buildings with different power consumption levels in the preset sub-area set are compared with the actual power consumption demand values ​​of the charging piles in the corresponding location area to obtain a comparison result set, and the target sub-area is screened out according to the first comparison result in the comparison result set; the pre-processing associated sub-area set is screened out from the preset sub-area set according to the target sub-area by the adjacent area analysis unit, and the pre-processing associated sub-area set refers to the sub-area adjacent to the target sub-area; the first comparison result and the second comparison result in the comparison result set are respectively analyzed by the associated area determination unit to obtain the first associated difference data, and the first target associated sub-area is extracted from the pre-processed associated sub-area set according to the first associated difference data; the first target associated sub-area is analyzed by the allocation condition statistics unit The resource allocation condition information of the sub-area and the target sub-area in the preset first historical time period is statistically obtained to obtain the first resource allocation condition, the second target associated sub-area set in the preset second historical time period is screened out from the preset sub-area set, and the second resource allocation condition set is statistically obtained based on the second target associated sub-area set, and the first resource allocation condition and the second resource allocation condition set are combined into a resource allocation condition set; the current feature information set affecting power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set in the current time period is obtained through the resource allocation processing unit, and the pre-processed resource allocation condition is matched from the resource allocation condition set according to the current feature information set affecting power distribution, and according to the pre-processed resource allocation condition, the total allocatable load of the charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set in the current time period is rescheduled and allocated.

[0094] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A virtual power plant optimization scheduling method, characterized in that: The following steps are involved: Acquire a detection area, divide the detection area into several sub-areas to obtain a preset sub-area set, compare historical power consumption demand values ​​of multiple buildings with different power consumption levels in the preset sub-area set with actual power consumption demand values ​​of charging piles in corresponding location areas to obtain a comparison result set, and screen out a target sub-area according to a first comparison result in the comparison result set; Acquire a detection area, and perform statistics on the distribution of buildings with multiple different power consumption levels in the detection area to obtain a building distribution statistical result; According to the building distribution statistics, the detection area is divided into a plurality of sub-areas to obtain a preset sub-area set; The distribution of charging piles in each sub-area of ​​the preset sub-area set is counted to obtain a charging pile distribution statistical result set; Preset a first historical period, where the first historical period is a recent historical period, and obtain a data set of historical power consumption demand values ​​of buildings in each sub-area in the preset sub-area set in the first historical period; Obtain a data set of historical actual power demand values ​​of charging piles in each distribution result in the first historical period in the charging pile distribution statistical result set; Compare the historical power demand value data set with the historical actual power demand value data set in a one-to-one correspondence, and output a comparison result set; Filter out a first comparison result from the comparison result set, the first comparison result refers to a value in a historical power demand value data set that is greater than or less than a historical actual power demand value data set, and extract a corresponding target sub-region that meets the first comparison result from the preset sub-region set; According to the target sub-region, a pre-processing associated sub-region set is screened out from a preset sub-region set, where the pre-processing associated sub-region set refers to a sub-region that is adjacent to the target sub-region; Performing difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data, if the first comparison result is that the historical power consumption demand value one data set is less than the value of the historical actual power consumption demand value one data set, then the second comparison result refers to the value of the historical power consumption demand value one data set that is greater than the value of the historical actual power consumption demand value one data set, if the first comparison result is that the historical power consumption demand value one data set is greater than the value of the historical actual power consumption demand value one data set, then the second comparison result refers to the value of the historical power consumption demand value one data set that is less than the value of the historical actual power consumption demand value one data set, and extracting a first target associated sub-region from the pre-processed associated sub-region set according to the first associated difference data; The resource allocation condition information of the first target-associated sub-region and the target sub-region in a preset first historical period is counted to obtain a first resource allocation condition, a second target-associated sub-region set in a preset second historical period is selected from the preset sub-region set, and a second resource allocation condition set is counted based on the second target-associated sub-region set, and the first resource allocation condition and the second resource allocation condition set are combined into a resource allocation condition set; Collecting the power distribution-influencing feature information of the target sub-area and the first target associated sub-area respectively in the first historical period, and outputting a first power distribution-influencing feature information set; The first power distribution influencing characteristic information set and the first associated difference data are combined into a first resource allocation condition; Preset a second historical period, the second historical period is located in all historical periods before the first historical period, obtain second associated difference data according to the second historical period, and output a second associated difference data set according to the second associated difference data; Extracting a second target associated subregion from the preset subregion set, and outputting a second target associated subregion set according to the second target associated subregion, wherein the second target associated subregion set refers to the remaining adjacent associated subregions excluding the first target associated subregion; Collect the power distribution-influencing feature information of the target sub-area and the second target associated sub-area respectively in the second historical period, and output a second power distribution-influencing feature information set; The second power distribution influencing characteristic information set and the second associated difference data set are combined into a second resource allocation condition set; The first set of characteristic information affecting power distribution and the second set of characteristic information affecting power distribution are combined into a reference information set of characteristic information affecting power distribution, and the first set of resource allocation conditions and the second set of resource allocation conditions are combined into a resource allocation condition set; Obtain a current feature information set that affects power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period; match a preprocessing resource allocation condition from a resource allocation condition set based on the current feature information set that affects power distribution; and reschedule and allocate resources for the total allocatable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period based on the preprocessing resource allocation condition.

2. A virtual power plant optimization scheduling method according to claim 1, characterized in that: According to the target sub-region, a pre-processing associated sub-region set is screened out from a preset sub-region set, where the pre-processing associated sub-region set refers to a sub-region that is adjacent to the target sub-region, specifically: According to the target sub-region, a plurality of sub-regions adjacent to the target sub-region are screened out from a preset sub-region set, and an associated sub-region set is output; A second comparison result is screened out from the comparison result set. If the first comparison result is that a historical power consumption demand value set is smaller than a value in a historical actual power consumption demand value set, then the second comparison result refers to a value in a historical power consumption demand value set that is larger than a value in a historical actual power consumption demand value set. If the first comparison result is that a historical power consumption demand value set is larger than a value in a historical actual power consumption demand value set, then the second comparison result refers to a value in a historical power consumption demand value set that is smaller than a value in a historical actual power consumption demand value set. A corresponding preprocessed associated sub-region set with an opposite condition to the second comparison result is extracted from the associated sub-region set.

3. A virtual power plant optimization scheduling method according to claim 2, characterized in that: Performing difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data, if the first comparison result is that the historical power consumption demand value one data set is less than the value of the historical actual power consumption demand value one data set, then the second comparison result refers to the value of the historical power consumption demand value one data set that is greater than the value of the historical actual power consumption demand value one data set, if the first comparison result is that the historical power consumption demand value one data set is greater than the value of the historical actual power consumption demand value one data set, then the second comparison result refers to the value of the historical power consumption demand value one data set that is less than the value of the historical actual power consumption demand value one data set, according to the first associated difference data, the step of extracting the first target associated sub-region from the pre-processed associated sub-region set is specifically: Performing difference calculation on the first comparison result to obtain a first demand difference, and outputting a first demand difference set according to the first demand difference; performing difference calculation on the second comparison result to obtain a second demand difference, and outputting a second demand difference set according to the second demand difference; Perform one-to-one correspondence statistics on the first demand difference set and the second demand difference set to obtain a difference data set; Preset a demand difference associated interval value, and filter out first associated difference data within the demand difference associated interval value from the difference data set; According to the first associated difference data, a first target associated sub-region that meets the first associated difference data is extracted from the pre-processed associated sub-region set.

4. A virtual power plant optimization scheduling method according to claim 1, characterized in that: The steps of obtaining a current power distribution-affecting feature information set of all sub-areas adjacent to the target sub-area in the preset sub-area set in the current time period, matching a pre-processing resource allocation condition from a resource allocation condition set according to the current power distribution-affecting feature information set, and rescheduling and allocating resources for the total allocable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set in the current time period according to the pre-processing resource allocation condition, are specifically as follows: Obtaining the power distribution feature information affecting the target sub-area in the current period and the power distribution feature information affecting all sub-areas adjacent to the target sub-area in the preset sub-area set, and outputting the current power distribution feature information set; Filter out a preprocessed power distribution influencing feature information set that best matches the current power distribution influencing feature information set from the power distribution influencing feature reference information set; According to the preprocessing power distribution-affecting feature information set, a corresponding preprocessing resource allocation condition is screened out from a resource allocation condition set; According to the current information set of characteristics affecting power distribution, the power demand forecast value of buildings in the target sub-area in the current period and the power demand forecast value of buildings in all sub-areas adjacent to the target sub-area in the preset sub-area set are respectively predicted, and the current power demand forecast value data set is output; Collect the distributable load of charging piles in the target sub-area in the current period and the distributable load of charging piles in all sub-areas adjacent to the target sub-area in the preset sub-area set, and output the total distributable load of charging piles; The total allocatable load of the charging pile, the current power demand forecast value data set and the pre-processed resource allocation conditions are all input into the virtual power plant adjustable resource model for resource rescheduling and allocation.

5. A virtual power plant optimization dispatching system, characterized in that: The system is used to implement a virtual power plant optimization scheduling method according to any one of claims 1 to 4, comprising: The target area analysis unit is used to obtain the detection area, divide the detection area into several sub-areas to obtain a preset sub-area set, compare the historical power consumption demand values ​​of multiple buildings with different power consumption levels in the preset sub-area set with the actual power consumption demand values ​​of the charging piles in the corresponding location area to obtain a comparison result set, and screen out the target sub-area according to the first comparison result in the comparison result set; An adjacent region analysis unit is used to select a pre-processed associated sub-region set from a preset sub-region set according to a target sub-region, where the pre-processed associated sub-region set refers to a sub-region that is adjacent to the target sub-region; an associated region determination unit, configured to perform difference analysis on the first comparison result and the second comparison result in the comparison result set to obtain first associated difference data; if the first comparison result is that a value in a historical power demand value data set is less than a value in a historical actual power demand value data set, then the second comparison result refers to a value in a historical power demand value data set that is greater than a value in a historical actual power demand value data set; if the first comparison result is that a value in a historical power demand value data set is greater than a value in a historical actual power demand value data set, then the second comparison result refers to a value in a historical power demand value data set that is less than a value in a historical actual power demand value data set; and extract a first target associated sub-region from the preprocessed associated sub-region set based on the first associated difference data; an allocation condition statistics unit, configured to obtain a first resource allocation condition by collecting statistics on the resource allocation condition information of the first target associated sub-region and the target sub-region in a preset first historical period, filter out a second target associated sub-region set in a preset second historical period from the preset sub-region set, obtain a second resource allocation condition set based on the second target associated sub-region set, and collect the first resource allocation condition and the second resource allocation condition set into a resource allocation condition set; The resource allocation processing unit is used to obtain the current feature information set that affects power distribution in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period, match the pre-processing resource allocation conditions from the resource allocation condition set according to the current feature information set that affects power distribution, and re-schedule and allocate resources for the total allocatable load of charging piles in the target sub-area and all sub-areas adjacent to the target sub-area in the preset sub-area set within the current time period according to the pre-processing resource allocation conditions.

Images