Power distribution network operation optimization control method based on multiple optical storage all-in-one machines

Abstract

The invention discloses a power distribution network operation optimization control method based on multiple optical storage all-in-one machines, relates to the technical field of energy scheduling, and improves the dynamic adaptive capacity in the control process of a power distribution network. According to historical power generation data and historical load fluctuation data, an expected power generation amount curve and a predicted power consumption curve are generated, and various historical environment data and historical power generation data are mapped into a multi-dimensional coordinate system; an electric quantity production causal chain is generated from the historical environment data and the historical power generation data through the environment factor nodes and the electric quantity production nodes, and then an electric quantity production causal network under each energy scheduling time point is obtained; and matching each piece of real-time environment data with the corresponding electric quantity production causal dynamic network, obtaining predicted electricity consumption according to the predicted electricity consumption curve of each electricity consumption area, and generating and executing an energy allocation decision through the predicted electricity consumption and the predicted production electric quantity of each photovoltaic power station.

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching, and in particular to a distribution network operation optimization control method based on a multi-photovoltaic storage integrated machine. Background Art

[0002] With the rapid development and widespread application of renewable energy, the power system is undergoing profound changes. Solar photovoltaic power generation has gradually become an important part of the power system due to its clean, renewable and distributed characteristics. However, the intermittent and unstable nature of photovoltaic power generation has brought new challenges to the operation of the distribution network. The traditional distribution network mainly relies on centralized power generation and fixed load characteristics, while the access of photovoltaic power generation makes the operation of the distribution network more complex and dynamic.

[0003] The existing distribution network operation control technology has the following defects:

[0004] Single control strategy: Most existing control methods for multi-solar-storage devices use a single control strategy, such as local information-based or centralized control, which lacks comprehensive consideration of the global operating status. This results in unstable control effects and difficulty in achieving global optimization in a complex and changeable distribution network environment.

[0005] Lack of dynamic adaptability: Traditional control methods are often based on static models and fixed parameters, which are difficult to adapt to the dynamic changes of photovoltaic power generation and load in the distribution network. The variability of the distribution network operating environment requires the control method to have a high degree of dynamic adaptability, but the existing technology is insufficient in this regard.

[0006] Therefore, how to improve the dynamic adaptability of the distribution network control process while achieving comprehensive consideration of the global operating status is a difficulty in the existing technology. For this purpose, a distribution network operation optimization control method based on a multi-photovoltaic storage integrated machine is provided. Summary of the invention

[0007] In order to solve the above technical problems, the purpose of the present invention is to provide a distribution network operation optimization control method based on multiple photovoltaic storage devices.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] A distribution network operation optimization control method based on a multi-photovoltaic storage integrated device comprises the following steps:

[0010] Step S1, setting a number of energy dispatching periods with a year as the data collection cycle, and then collecting the historical environmental data and historical power generation data of photovoltaic power stations in each region under each energy dispatching period, and at the same time collecting the historical load fluctuation data of each power consumption area;

[0011] Step S2, establishing a two-dimensional coordinate system, mapping the historical power generation data and the historical load fluctuation data in the two-dimensional coordinate system respectively, and dividing the energy dispatch period into a number of energy dispatch time points, splitting the historical power generation data and the historical load fluctuation data into a number of curve segments according to the energy dispatch time points, generating an expected power generation curve and an expected power consumption curve according to the plane area of ​​each curve segment and the x-axis, and then generating an expected power generation reference line according to the expected power generation curve;

[0012] Step S3: set a multidimensional coordinate system, an environmental factor node, and an electric quantity production node, map various historical environmental data and historical power generation data into the multidimensional coordinate system, and then intercept the data points at various energy dispatching time points from the historical environmental data and historical power generation data through the environmental factor node and the electric quantity production node, generate a corresponding electric quantity production causal chain, compare the environmental factor nodes and electric quantity production nodes of the same type of data in the electric quantity production causal chain, locally connect each electric quantity production causal chain according to the comparison result, and then obtain the electric quantity production causal network at various energy dispatching time points;

[0013] Step S4: At the beginning of each energy scheduling period, various real-time environmental data of each photovoltaic power station are collected, and the real-time environmental data are matched with the corresponding power production causal dynamic network. The estimated production power is obtained according to the matching result, and the estimated power consumption is obtained according to the estimated power consumption curve of each power consumption area. Then, energy allocation decisions are generated and executed based on the estimated power consumption and the estimated production power of each photovoltaic power station.

[0014] Furthermore, the collection process includes:

[0015] Several energy scheduling periods are set with one year as the data collection cycle. Voltage sensors and i types of environmental perception sensors are installed in each photovoltaic power station, and power sensors are installed in each power consumption area. When an energy scheduling period begins, all sensors in the photovoltaic power station and the power consumption area are reset, and then various historical environmental data, historical power generation data and historical load fluctuation data in the corresponding energy scheduling period are collected.

[0016] Furthermore, the process of obtaining the plane area of ​​each curve segment and the x-axis includes:

[0017] A two-dimensional coordinate system is established, and historical power generation data and historical load fluctuation data of the same data type in different data collection cycles but in the same energy dispatch period are respectively mapped into the same two-dimensional coordinate system, and a number of energy dispatch time points with equal time intervals are divided in each energy dispatch period, and the curves on each two-dimensional coordinate system are split into a number of curve segments according to each energy dispatch time point;

[0018] The plane area values ​​between each curve segment and the x-axis within the same pair of energy scheduling time points are obtained, and then the plane area averages of each pair of energy scheduling time points under different numbers of data collection cycles are obtained in sequence according to the time sequence.

[0019] Furthermore, the process of establishing the expected power generation curve and the estimated power consumption curve includes:

[0020] The plane area averages between each curve segment and the x-axis between each pair of energy scheduling time points under different numbers of data collection cycles are mapped onto the same two-dimensional coordinate system, and a smooth curve is set so that the interval corresponding to the smooth curve between each energy scheduling time point passes through as many plane area averages as possible;

[0021] The smooth curves of different data types are mapped to the two-dimensional coordinate system where the corresponding historical power generation data or historical load fluctuation data are located, and then all the curve segments below the smooth curve are eliminated. Then, according to the generation process of the smooth curve, the smooth curves corresponding to the retained curve segments are obtained, and they are recorded as the expected power generation curve and the expected power consumption curve respectively.

[0022] Furthermore, the process of generating an expected power generation reference line according to the expected power generation curve includes:

[0023] According to the curve segments corresponding to the historical power generation data, the associated historical environmental data are retrieved to establish a multidimensional coordinate system, and the curve segments corresponding to the historical power generation data and the corresponding retrieved historical environmental data are mapped in the same multidimensional coordinate system, and then the power generation is used as the dependent variable and the various types of environmental data are used as independent variables to establish the corresponding multidimensional linear regression equation;

[0024] The process of collecting and establishing the expected power generation curve is to obtain the ideal state environmental curve corresponding to each environmental data, substitute the ideal state environmental curve corresponding to each environmental data and the expected power generation curve into the multidimensional linear regression equation, and correct the various relationship parameters in the multidimensional linear regression equation according to the substitution results. The straight line corresponding to the corrected multidimensional linear regression equation is mapped into the same multidimensional coordinate system, so as to obtain the expected power generation reference line of each photovoltaic power station in different energy scheduling periods under the ideal environmental state.

[0025] Furthermore, the generation process of the electricity production causal chain includes:

[0026] Set i environmental factor nodes and power production nodes, and set corresponding data names for each environmental factor node according to the data names of various types of environmental data;

[0027] Then, all data are extracted from the historical power station data set and the historical electricity consumption data set in each data collection cycle, and various historical environmental data and historical power generation data corresponding to the same substation but in the same energy collection period in different data collection cycles are mapped into the same multidimensional coordinate system, and several energy dispatch time points are marked on the multidimensional coordinate system, and the expected power generation reference line is mapped into the multidimensional coordinate system;

[0028] Through the environmental factor node and the electricity production node, various historical environmental data and historical power generation data are selected, and at the data points at each energy scheduling point, the environmental factor node and the electricity production node on each energy scheduling node are connected in sequence to obtain several electricity production cause-and-effect chains.

[0029] Furthermore, the process of establishing the electricity production causal network includes:

[0030] Set a deviation threshold, and set a corresponding deviation detection interval with the values ​​of various environmental data on the expected power generation reference line at each energy scheduling point as the interval center;

[0031] Determine the relationship between the difference between the value contained in the power production node in each power production causal chain and the value of the expected power generation reference line at the corresponding energy scheduling time and the deviation threshold;

[0032] According to the judgment result, it is further judged whether the difference between the value contained in each environmental factor node in the corresponding power production causal chain and the value of the expected power generation reference line at the corresponding energy scheduling time point is within the relevant deviation detection interval, and the corresponding environmental factor node is marked as an environmental impact node according to the judgment result;

[0033] Set numerical approximate thresholds for various types of environmental data respectively, and judge whether the absolute value of the difference between the data values ​​recorded by the environmental impact nodes of the same data type in each electricity production causal chain of the same photovoltaic power station at the same energy dispatch time is less than or equal to the corresponding numerical approximate threshold, and according to the judgment result, locally connect the consistent environmental impact nodes in each electricity production causal chain of the same photovoltaic power station at the same energy dispatch time, wherein the environmental impact nodes at the connection directly overlap, thereby obtaining the electricity production causal network of each photovoltaic power station at each energy dispatch time;

[0034] The causal networks of electricity production in the same energy dispatch period are overlapped and spliced ​​in time sequence to obtain the causal dynamic network of electricity production in the corresponding energy dispatch period.

[0035] Furthermore, the generation process of the energy allocation decision includes:

[0036] Obtain the energy transmission efficiency between each photovoltaic power station and each power consumption area, and then obtain the estimated power consumption of each power consumption area between each energy scheduling time point according to the estimated power consumption curve of each power consumption area at the beginning of each energy scheduling period;

[0037] At the same time, every time an energy dispatch time point begins, various real-time environmental data of each photovoltaic power generation area are collected, and according to the current energy dispatch period and energy dispatch time point, the corresponding power production causal network is extracted from the power production causal dynamic network;

[0038] First, it is determined whether each item of real-time environmental data is within the deviation detection interval of the corresponding type of environmental data, and according to the determination result, each item of real-time environmental data is matched with the environmental factor node to obtain the numerical fit between the real-time environmental data and the data contained in the environmental factor node;

[0039] According to the matching results of various real-time environmental data and environmental factor nodes, the actual power production chain is selected from the power production causal network, and the values ​​recorded by the power production nodes in the actual power production chain are recorded as the estimated production power of the corresponding photovoltaic power station before the next energy scheduling time point;

[0040] Based on the estimated power generation and the energy transmission efficiency between each photovoltaic power station and each power consumption area, the optimization algorithm is collected to generate and execute energy allocation decisions.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention generates an expected power generation curve and an estimated power consumption curve based on historical power generation data and historical load fluctuation data, and maps various historical environmental data and historical power generation data in a multidimensional coordinate system, and then generates a power production causal chain from the historical environmental data and historical power generation data through environmental factor nodes and power production nodes, and then obtains a power production causal network at each energy scheduling time point. At the beginning of each energy scheduling period, various real-time environmental data are matched with the corresponding power production causal dynamic network, and the estimated power consumption is obtained according to the estimated power consumption curve of each power consumption area, and then the energy allocation decision is generated and executed according to the estimated power consumption and the estimated production power of each photovoltaic power station, thereby achieving the comprehensive consideration of the global operating status while improving the dynamic adaptability in the distribution network control process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention.

[0044] Figure 1The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0045] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0046] like Figure 1 As shown, a distribution network operation optimization control method based on a multi-photovoltaic storage integrated device includes the following steps:

[0047] Step S1, setting a number of energy dispatching periods with a year as the data collection cycle, and then collecting the historical environmental data and historical power generation data of photovoltaic power stations in each region under each energy dispatching period, and at the same time collecting the historical load fluctuation data of each power consumption area;

[0048] The specific implementation process of step S1 includes:

[0049] With one year as the data collection cycle, m energy dispatch periods are set. It should be noted that the time spans of various energy dispatch periods are not exactly the same, that is, there are energy dispatch periods with a time length of one month, and there are also energy dispatch periods with a time length of two months, where m is a natural number greater than 0;

[0050] The photovoltaic power station is composed of a power generation unit and an energy storage unit. A voltage sensor, a GPS positioning device and i types of environmental perception sensors are set in each photovoltaic power station, and a power sensor is installed in each power consumption area. The types of environmental sensors include temperature sensors, light sensors, humidity sensors, etc., and i is a natural number greater than 0;

[0051] At the beginning of each energy dispatch period, all sensors in the photovoltaic power station and the power consumption area are reset, and then the historical environmental data, historical power generation data and historical load fluctuation data in the corresponding energy dispatch period are collected. The historical environmental data includes historical humidity change data, historical light change data, etc. It should be noted that the above data are collected under the condition that there is no hardware damage in the photovoltaic power station and the power consumption area;

[0052] When the energy dispatch period ends, all data generated by each photovoltaic power station and power consumption area are summarized to obtain the historical power station data set and historical power consumption data set under the corresponding energy dispatch period.

[0053] Step S2, establishing a two-dimensional coordinate system, mapping the historical power generation data and the historical load fluctuation data in the two-dimensional coordinate system respectively, and dividing the energy dispatch period into a number of energy dispatch time points, splitting the historical power generation data and the historical load fluctuation data into a number of curve segments according to the energy dispatch time points, generating an expected power generation curve and an expected power consumption curve according to the plane area of ​​each curve segment and the x-axis, and then generating an expected power generation reference line according to the expected power generation curve;

[0054] The specific implementation process of step S2 includes:

[0055] Establish a two-dimensional coordinate system, collect historical power station data sets and historical electricity consumption data in different data collection cycles but the same energy dispatch period, and map the historical power generation data and historical load fluctuation data of the same data type into the same two-dimensional coordinate system, where the x-axis of the two-dimensional coordinate system is associated with time, and the y-axis is associated with the numerical unit of the corresponding type of data;

[0056] In each energy dispatching period, a number of energy dispatching time points with equal time intervals are divided, and the curves on each two-dimensional coordinate system are split into a number of curve segments according to each energy dispatching time point;

[0057] The plane area values ​​between each curve segment and the x-axis between the same pair of energy scheduling time points are obtained, and then the plane area average values ​​of each pair of energy scheduling time points under different numbers of data collection cycles are obtained in sequence according to the time sequence. The specific process includes: firstly, the plane area average values ​​between each curve segment and the x-axis between each pair of energy scheduling time points under the first data collection cycle and the second data collection cycle are obtained, and then the plane area average values ​​between each curve segment and the x-axis between each pair of energy scheduling time points under the first data collection cycle, the second data collection cycle and the third data collection cycle are obtained, and so on, until the plane area average values ​​between each curve segment and the x-axis between each pair of energy scheduling time points under all existing data collection cycles are obtained.

[0058] Furthermore, the mean values ​​of the plane areas between each curve segment and the x-axis between each pair of energy scheduling time points under different numbers of data collection cycles are mapped onto the same two-dimensional coordinate system, and a smooth curve is set so that the interval corresponding to the smooth curve between each energy scheduling time point passes through as many mean values ​​of the plane areas as possible;

[0059] The smooth curves of different data types are respectively mapped onto the two-dimensional coordinate system where the corresponding historical power generation data or historical load fluctuation data are located, and then all the curve segments below the smooth curve are eliminated. Then, according to the generation process of the smooth curve, the smooth curves corresponding to the retained curve segments are obtained, and they are recorded as the expected power generation curve and the expected power consumption curve respectively;

[0060] At the same time, the relevant historical environmental data are retrieved according to the curve segments corresponding to the historical power generation data, and a multidimensional coordinate system is established. The curve segments corresponding to the historical power generation data and the corresponding retrieved historical environmental data are mapped in the same multidimensional coordinate system, and then the power generation is used as the dependent variable and the various types of environmental data are used as independent variables to establish the corresponding multidimensional linear regression equation, where the multidimensional linear regression equation can be expressed as: U = a1x1 + ... + a n x n , where U represents the power generation, x n and a n They represent the nth environmental data and the corresponding relationship parameters respectively, and n is a natural number greater than 0;

[0061] Collect and establish the expected power generation curve process, obtain the ideal state environment curve corresponding to each environmental data, substitute the ideal state environment curve corresponding to each environmental data and the expected power generation curve into the multidimensional linear regression equation, and modify each relationship parameter in the multidimensional linear regression equation according to the substitution result;

[0062] The straight line corresponding to the modified multidimensional linear regression equation is mapped into the same multidimensional coordinate system, and then the expected power generation reference line of each photovoltaic power station in different energy scheduling periods under ideal environmental conditions is obtained.

[0063] Step S3: set a multidimensional coordinate system, an environmental factor node, and an electric quantity production node, map various historical environmental data and historical power generation data into the multidimensional coordinate system, and then intercept the data points at various energy dispatching time points from the historical environmental data and historical power generation data through the environmental factor node and the electric quantity production node, generate a corresponding electric quantity production causal chain, compare the environmental factor nodes and electric quantity production nodes of the same type of data in the electric quantity production causal chain, locally connect each electric quantity production causal chain according to the comparison result, and then obtain the electric quantity production causal network at various energy dispatching time points;

[0064] The specific implementation process of step S3 includes:

[0065] Set i environmental factor nodes and power production nodes, and set corresponding data names for each environmental factor node according to the data names of various types of environmental data;

[0066] Then, all data are extracted from the historical power station data set and the historical electricity consumption data set in each data collection cycle, and various historical environmental data and historical power generation data corresponding to the same substation but in the same energy collection period in different data collection cycles are mapped into the same multidimensional coordinate system, and several energy dispatch time points are marked on the multidimensional coordinate system, and the expected power generation reference line is mapped into the multidimensional coordinate system;

[0067] Select various historical environmental data and historical power generation data through the environmental factor node and the power production node, and connect the environmental factor node and the power production node on each energy scheduling node in sequence at the data point at each energy scheduling time point, so as to obtain several power production cause-and-effect chains;

[0068] Set a deviation threshold, and set a corresponding deviation detection interval with the values ​​of various environmental data on the expected power generation reference line at each energy scheduling point as the interval center;

[0069] Then, the relationship between the difference between the value contained in the power production node in each power production causal chain and the value of the expected power generation reference line at the corresponding energy scheduling time point and the deviation threshold is determined;

[0070] If the difference is greater than or equal to the deviation threshold, the corresponding electricity production causal chain is deleted;

[0071] If the difference is less than the deviation threshold, it is further determined whether the difference between the values ​​contained in each environmental factor node in the corresponding power production causal chain and the values ​​of the expected power generation reference line at the corresponding energy scheduling time point is within the relevant deviation detection interval;

[0072] It should be noted that when the power generation of a photovoltaic power station in a period of time is greater than or equal to the power generation given by the expected power generation reference line at the corresponding time, then the various environmental data at the corresponding time must be within the corresponding deviation detection interval;

[0073] Furthermore, if the difference is within the relevant deviation detection interval, no operation is performed on the corresponding environmental factor node;

[0074] If the difference is not within the relevant deviation detection interval, the environmental factor node corresponding to the causal chain of electricity production is marked as an environmental impact node;

[0075] Set numerical approximate thresholds for various types of environmental data respectively, and judge whether the absolute value of the difference between the data values ​​recorded by the environmental impact nodes of the same data type in each electricity production causal chain at the same energy dispatch time point of the same photovoltaic power station is less than or equal to the corresponding numerical approximate threshold;

[0076] If the absolute value of the difference is greater than the corresponding numerical approximation threshold, no action is taken;

[0077] If the absolute value of the difference is less than or equal to the corresponding numerical approximation threshold, the corresponding environmental impact nodes are judged to be consistent;

[0078] Then, according to the judgment results, the consistent environmental impact nodes in each electricity production causal chain of the same photovoltaic power station at the same energy dispatch time point are partially connected, and the environmental impact nodes at the connection point are directly overlapped, so as to obtain the electricity production causal network of each photovoltaic power station at each energy dispatch time point;

[0079] The causal networks of electricity production in the same energy dispatch period are overlapped and spliced ​​in time sequence to obtain the causal dynamic network of electricity production in the corresponding energy dispatch period.

[0080] Step S4: At the beginning of each energy dispatch period, various real-time environmental data of each photovoltaic power station are collected, and the various real-time environmental data are matched with the corresponding power production causal dynamic network, and the estimated production power is obtained according to the matching result, and the estimated power consumption is obtained according to the estimated power consumption curve of each power consumption area, and then the energy dispatch decision is generated and executed according to the estimated power consumption and the estimated production power of each photovoltaic power station;

[0081] The specific implementation process of step S4 includes:

[0082] Obtain the energy transmission efficiency between each photovoltaic power station and each power consumption area, and then obtain the estimated power consumption of each power consumption area between each energy scheduling time point according to the estimated power consumption curve of each power consumption area at the beginning of each energy scheduling period;

[0083] At the same time, every time an energy dispatch time point begins, various real-time environmental data of each photovoltaic power generation area are collected, and according to the current energy dispatch period and energy dispatch time point, the corresponding power production causal network is extracted from the power production causal dynamic network;

[0084] First, it is determined whether each real-time environmental data is within the deviation detection interval of the corresponding type of environmental data. If so, the corresponding real-time environmental data is matched with the environmental factor nodes in the power production causal network that do not have environmental impact node tags and have the same type of data;

[0085] If not, the corresponding real-time environmental data is matched with the environmental factor nodes with the environmental impact node label and the same type of data in the electricity production causal network;

[0086] In the process of matching various real-time environmental data with environmental factor nodes, the numerical fit between the real-time environmental data and the data contained in the environmental factor node is obtained, wherein the numerical fit is a value obtained by dividing the numerical value of the real-time environmental data by the numerical value of the data contained in the environmental factor node;

[0087] According to the matching results of various real-time environmental data and environmental factor nodes, several reserve power production chains are traversed from the power production causal network, and the reserve power production chain with the largest sum of numerical fit is counted and selected as the actual power production chain;

[0088] Then, the value recorded by the power production node in the actual power production chain is recorded as the estimated power production of the corresponding photovoltaic power station before the next energy scheduling time point;

[0089] Then, based on the estimated power generation of the photovoltaic power station before the next energy scheduling point and the energy transmission efficiency between each photovoltaic power station and each power consumption area, the optimization algorithm is collected to generate energy allocation decisions, so that the energy allocation decision satisfies that the power allocated to each power consumption area is greater than or equal to the estimated power consumption of each power consumption area before the next energy scheduling point;

[0090] Each photovoltaic power station executes the energy allocation decision until the next energy allocation time point begins, and then repeatedly generates and executes the energy allocation decision.

[0091] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A distribution network operation optimization control method based on multiple photovoltaic storage integrated devices, characterized in that: The following steps are involved: Step S1, setting a number of energy dispatching periods with a year as the data collection cycle, and then collecting the historical environmental data and historical power generation data of photovoltaic power stations in each region under each energy dispatching period, and at the same time collecting the historical load fluctuation data of each power consumption area; Step S2, establishing a two-dimensional coordinate system, mapping the historical power generation data and the historical load fluctuation data in the two-dimensional coordinate system respectively, and dividing the energy dispatch period into a number of energy dispatch time points, splitting the historical power generation data and the historical load fluctuation data into a number of curve segments according to the energy dispatch time points, generating an expected power generation curve and an expected power consumption curve according to the plane area of ​​each curve segment and the x-axis, and then generating an expected power generation reference line according to the expected power generation curve; Step S3: set a multidimensional coordinate system, an environmental factor node, and an electric quantity production node, map various historical environmental data and historical power generation data into the multidimensional coordinate system, and then intercept the data points at various energy dispatching time points from the historical environmental data and historical power generation data through the environmental factor node and the electric quantity production node, generate a corresponding electric quantity production causal chain, compare the environmental factor nodes and electric quantity production nodes of the same type of data in the electric quantity production causal chain, locally connect each electric quantity production causal chain according to the comparison result, and then obtain the electric quantity production causal network at various energy dispatching time points; Step S4: At the beginning of each energy scheduling period, various real-time environmental data of each photovoltaic power station are collected, and the real-time environmental data are matched with the corresponding power production causal dynamic network. The estimated production power is obtained according to the matching result, and the estimated power consumption is obtained according to the estimated power consumption curve of each power consumption area. Then, energy allocation decisions are generated and executed based on the estimated power consumption and the estimated production power of each photovoltaic power station.

2. The method for optimizing the operation of a distribution network based on a multi-solar-storage integrated device according to claim 1, characterized in that: The collection process includes: Several energy scheduling periods are set with one year as the data collection cycle. Voltage sensors and i types of environmental perception sensors are set in each photovoltaic power station, and power sensors are installed in each power consumption area. When an energy scheduling period begins, all sensors in the photovoltaic power station and the power consumption area are reset, and then various historical environmental data, historical power generation data and historical load fluctuation data in the corresponding energy scheduling period are collected, and i is a natural number greater than 0.

3. The method for optimizing the operation of a distribution network based on a multi-solar-storage integrated device according to claim 2, characterized in that: The process of obtaining the plane area of ​​each curve segment and the x-axis includes: A two-dimensional coordinate system is established, and historical power generation data and historical load fluctuation data of the same data type in different data collection cycles but in the same energy dispatch period are respectively mapped into the same two-dimensional coordinate system, and several energy dispatch time points are divided in each energy dispatch period, and the curves on each two-dimensional coordinate system are split into several curve segments according to each energy dispatch time point; The plane area values ​​between each curve segment and the x-axis within the same pair of energy scheduling time points are obtained, and then the plane area averages of each pair of energy scheduling time points under different numbers of data collection cycles are obtained in sequence according to the time sequence.

4. The method for optimizing the operation of a distribution network based on a multi-solar-storage integrated device according to claim 3, characterized in that: The process of establishing the expected power generation curve and the estimated power consumption curve includes: The average of the plane areas between each curve segment and the x-axis between each pair of energy dispatch time points under different numbers of data collection cycles is mapped onto the same two-dimensional coordinate system, and a smooth curve is set. The smooth curves of different data types are respectively mapped onto the two-dimensional coordinate system where the corresponding historical power generation data or historical load fluctuation data are located, and then all the curve segments below the smooth curve are eliminated. According to the generation process of the smooth curve, the smooth curves corresponding to the retained curve segments are obtained, and they are recorded as the expected power generation curve and the expected power consumption curve, respectively.

5. The method for optimizing the operation of a distribution network based on a multi-solar-storage integrated device according to claim 4, characterized in that: The process of generating an expected power generation reference line according to the expected power generation curve includes: Establish a multidimensional coordinate system, and map the retained curve segments corresponding to the historical power generation data and the corresponding retrieved historical environmental data into the same multidimensional coordinate system, and then establish a multidimensional linear regression equation with power generation as the dependent variable and various types of environmental data as independent variables; The ideal environmental curve corresponding to each environmental data is obtained, and the various relationship parameters in the multidimensional linear regression equation are corrected according to the ideal environmental curve corresponding to each environmental data and the expected power generation curve. The straight line corresponding to the corrected multidimensional linear regression equation is mapped to the same multidimensional coordinate system, and then the expected power generation reference line of each photovoltaic power station in different energy scheduling periods under the ideal environmental state is obtained.

6. A distribution network operation optimization control method based on multiple photovoltaic and storage integrated devices according to claim 5, characterized in that: The generation process of the electricity production causal chain includes: Set i environmental factor nodes and power production nodes, map various historical environmental data and historical power generation data corresponding to the same substation but in the same energy collection period in different data collection cycles into the same multidimensional coordinate system, mark several energy scheduling time points on the multidimensional coordinate system, and map the expected power generation reference line into the multidimensional coordinate system; Through the environmental factor node and the electricity production node, the data points of various historical environmental data and historical power generation data at each energy scheduling point are selected, and the environmental factor node and the electricity production node on each energy scheduling node are connected in sequence to obtain several electricity production causal chains.

7. A distribution network operation optimization control method based on multiple photovoltaic and storage integrated devices according to claim 6, characterized in that: The process of establishing the electricity production causal network includes: Set the deviation threshold, taking the values ​​of various environmental data on the expected power generation reference line at each energy scheduling point as the center of the interval, and set the corresponding deviation detection interval; Determine the relationship between the difference between the value contained in the power production node in each power production causal chain and the value of the expected power generation reference line at the corresponding energy scheduling time and the deviation threshold; According to the judgment result, it is further judged whether the difference between the numerical value contained in each environmental factor node in the corresponding electricity production causal chain and the numerical value of the expected power generation reference line at the corresponding energy scheduling time point is within the relevant deviation detection interval; according to the judgment result, the corresponding environmental factor node is marked as an environmental impact node, and numerical approximate thresholds are set for various types of environmental data respectively, and it is judged whether the absolute value of the difference between the data values ​​recorded by the environmental impact nodes of the same data type in each electricity production causal chain at the same energy scheduling time point for the same photovoltaic power station is less than or equal to the corresponding numerical approximate threshold; according to the judgment result, each electricity production causal chain is locally connected, and the environmental impact nodes at the connection point are directly overlapped, so as to obtain the electricity production causal network of each photovoltaic power station at each energy scheduling time point.

8. The method for optimizing the operation of a distribution network based on a multi-solar-storage integrated device according to claim 7, characterized in that: The generation process of the energy allocation decision includes: Obtain the energy transmission efficiency between each photovoltaic power station and each power consumption area, and then obtain the estimated power consumption of each power consumption area between each energy scheduling time point according to the estimated power consumption curve of each power consumption area at the beginning of each energy scheduling period; At the same time, every time an energy dispatch time point begins, various real-time environmental data of each photovoltaic power generation area are collected, and according to the current energy dispatch period and energy dispatch time point, the corresponding power production causal network is extracted from the power production causal dynamic network; Determine whether each item of real-time environmental data is within the deviation detection interval of the corresponding type of environmental data, match each item of real-time environmental data with the environmental factor node according to the determination result, and obtain the numerical fit between the real-time environmental data and the data contained in the environmental factor node; According to the matching results of various real-time environmental data and environmental factor nodes, the actual power production chain is selected from the power production causal network, and the values ​​recorded by the power production nodes in the actual power production chain are recorded as the estimated production power of the corresponding photovoltaic power station before the next energy scheduling time point; Based on the estimated power generation and the energy transmission efficiency between each photovoltaic power station and each power consumption area, the collection optimization algorithm generates and executes energy allocation decisions.

Images