Source load uncertainty scene modeling method, storage medium and computer equipment

Abstract

The invention discloses a source load uncertainty scene modeling method, a storage medium and computer equipment. The method comprises the steps of determining a high-temperature drought weather influence model and a first output model of a first unit; fitting a first probability density function based on the historical data of the first factor, sampling according to the first probability density function, generating a first scene corresponding to the first factor, and determining a first output scene based on the first scene and a first output model; fitting a second probability density function based on the historical data of the second factor, sampling according to the second probability density function, generating a second scene corresponding to the second factor, and determining a second output scene based on the second scene and the high-temperature drought weather influence model; and scene reduction is performed based on the first output scene and the second output scene to obtain a typical scene, so that extreme high-temperature drought weather can be simulated to accurately model a large number of typical scenes with uncertain source loads.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a source-load uncertainty scenario modeling method, storage medium, and computer equipment. Background Art

[0002] The power system with renewable energy as the core is the key to responding to future climate change and achieving the goal of "carbon neutrality and carbon peak". The operation of renewable energy usually depends on climate conditions. Against the background of global warming, extreme climate events have increased significantly, which has also led to a sharp increase in electricity load, resulting in power restrictions and power outages. But on the other hand, the total number of samples of extreme climate events is still limited, and the samples in each region are even fewer. Therefore, it is difficult to provide the dispatching department with enough historical samples for dispatching reference. For example, for the method of using artificial intelligence models for dispatching, the lack of sample size obviously makes it difficult to train an accurate dispatching model. Summary of the invention

[0003] In order to solve the above technical problems, the embodiments of the present application propose a source-load uncertainty scenario modeling method, storage medium and computer equipment, which can simulate extreme high temperature and drought weather to accurately model a large number of typical source-load uncertainty scenarios.

[0004] In a first aspect, an embodiment of the present application provides a source-load uncertainty scenario modeling method, comprising:

[0005] Determining a high temperature and drought weather impact model and a first output model of the first unit respectively, wherein the high temperature and drought weather impact model is suitable for indicating the impact of high temperature and drought weather on the second unit and the load end;

[0006] Fitting a first probability density function based on historical data of a first factor, sampling according to the first probability density function, generating a first scenario corresponding to the first factor, and determining a first output scenario based on the first scenario and the first output model, wherein the first factor represents a factor affecting the first unit;

[0007] Fitting a second probability density function based on historical data of a second factor, sampling according to the second probability density function, generating a second scenario corresponding to the second factor, and determining a second output scenario based on the second scenario and the high temperature and drought weather impact model, wherein the second factor represents a high temperature and drought weather factor;

[0008] Scenario reduction is performed based on the first output scenario and the second output scenario to obtain a typical scenario.

[0009] Optionally, the second unit includes a photovoltaic unit, and the high temperature and drought weather impact model includes a first impact model;

[0010] in,

[0011] The first impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the photovoltaic group, wherein the photovoltaic group includes a photovoltaic cell group, and the first impact model is determined at least based on the difference between the temperature of the photovoltaic cell group and the operating temperature of the solar cell under standard operating conditions, and the temperature of the photovoltaic cell group is determined by the surface temperature, solar radiation intensity and wind speed at the location of the photovoltaic group.

[0012] Optionally, the second unit includes a first thermal power unit using a direct cooling system, and the high temperature and drought weather impact model includes a second impact model;

[0013] in,

[0014] The second impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the first thermal power unit. The second impact model is expressed by the following formula:

[0015]

[0016] in, is the output efficiency of the first thermal power unit, A i,j Characterizes the available cooling water level of the first thermal power unit and is used to indicate the degree of drought in the environment. represents the water inlet temperature of the cooling system of the first thermal power unit and is determined by the air temperature of the first thermal power unit, β is the efficiency reduction coefficient, T h is the maximum temperature value under normal operating efficiency of the first thermal power unit, T sd is the shutdown water inlet temperature of the first thermal power unit, T r is the temperature when the waste heat actually discharged by the first thermal power unit is equal to the design value of the maximum power unit, δ is the efficiency coefficient, T outmax is the maximum allowable adjustable temperature of the cooling water discharged from the first thermal power unit, ΔT max It is the maximum allowable temperature rise of the cooling water of the first thermal power unit.

[0017] Optionally, the second unit includes a second thermal power unit using a closed-loop cooling system, and the high temperature and drought weather impact model includes a third impact model;

[0018] in,

[0019] The third impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the second thermal power unit. The third impact model is expressed by the following formula:

[0020]

[0021] in, is the output efficiency of the second thermal power unit, T i,j represents the temperature of the area where thermal power unit i is located at time j, T ha is the maximum allowable temperature of the second thermal power unit at full efficiency output, and ρ is the efficiency reduction coefficient.

[0022] Optionally, the high temperature and drought weather impact model includes a fourth impact model;

[0023] in,

[0024] The fourth impact model is suitable for indicating the impact of high temperature and drought weather on the load end. The fourth impact model is expressed by the following formula:

[0025]

[0026] Where C is the temperature sensitivity coefficient of the load, P l is the load at the load end under the influence of high temperature and dry weather, P ol is the original predicted load value of the load end, Represents the average historical reference temperature of the region, T i,j It represents the temperature in the area where thermal power unit i is located at time j.

[0027] Optionally, the first unit includes a wind turbine unit, the historical data of the first factor includes historical wind speed data, and the first scenario includes a wind speed scenario;

[0028] The fitting of a first probability density function based on the historical data of the first factor, and sampling according to the first probability density function to generate a first scenario corresponding to the first factor, includes:

[0029] Based on the historical wind speed data, Weibull distribution is used for fitting to obtain fitting coefficients, so as to determine a first probability density function suitable for indicating wind speed distribution according to the fitting coefficients;

[0030] The wind speed scenario is generated according to the first probability density function using Latin hypercube sampling.

[0031] Optionally, the historical data of the second factor includes temperature historical data and solar irradiance historical data, the second probability density function includes a third probability density function and a fourth probability density function, and the second scenario corresponding to the second factor includes a temperature scenario and a solar irradiance scenario.

[0032] The fitting of a second probability density function based on the historical data of the second factor, and sampling according to the second probability density function to generate a second scenario corresponding to the second factor, includes:

[0033] Based on the temperature history data, a normal distribution is used for fitting to determine the third probability density function, and according to the third probability density function, Latin hypercube sampling is used to generate the temperature scenario;

[0034] Based on the solar irradiance historical data, chi-square distribution is used for fitting to determine the fourth probability density function, and according to the fourth probability density function, Latin hypercube sampling is used to generate the solar irradiance scene.

[0035] Optionally, performing scenario reduction based on the first output scenario and the second output scenario to obtain a typical scenario includes:

[0036] Based on the first output scenario and the second output scenario, construct a set of scenarios to be reduced;

[0037] Clustering is performed based on the scenes in the set of scenes to be reduced to obtain typical scenes, wherein the clustering is implemented by a BIRCH-AHC double-layer clustering algorithm.

[0038] In a second aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0039] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the steps of any of the methods described above when executing the computer program.

[0040] In summary, the embodiments of the present application have at least the following beneficial effects:

[0041] According to an embodiment of the present application, a high temperature and drought weather impact model and a first output model of the first unit are determined respectively, wherein the high temperature and drought weather impact model is suitable for indicating the impact of high temperature and drought weather on the second unit and the load end; a first probability density function is fitted based on historical data of the first factor, and a first scenario corresponding to the first factor is generated by sampling according to the first probability density function, and a first output scenario is determined based on the first scenario and the first output model, wherein the first factor represents the factor affecting the first unit; a second probability density function is fitted based on historical data of the second factor, and a second scenario corresponding to the second factor is generated by sampling according to the second probability density function, and a second output scenario is determined based on the second scenario and the high temperature and drought weather impact model, wherein the second factor represents the high temperature and drought weather factor; scenario reduction is performed based on the first output scenario and the second output scenario to obtain a typical scenario, so that extreme high temperature and drought weather can be simulated to accurately model a large number of typical scenarios of source-load uncertainty. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a source-load uncertainty scenario modeling method provided in an embodiment of the present application;

[0043] Figure 2 is a schematic diagram of a wind power scenario set provided in an embodiment of the present application;

[0044] Figure 3 is a schematic diagram of a photovoltaic output scenario set provided in an embodiment of the present application;

[0045] Figure 4 is a schematic diagram of a temperature uncertainty scenario set provided by an embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of five typical scene sets obtained based on the BIRCH-AHC two-layer clustering algorithm provided in the embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of the original load not affected by temperature and the load conditions affected by temperature of five typical scenario sets provided in the embodiment of the present application;

[0048] Figure 7 It is a schematic diagram of the output efficiency changes of different types of thermal power units provided in the embodiment of the present application under five typical scene sets;

[0049] Figure 8 is a schematic diagram of the before and after changes of a typical set of photovoltaic output scenarios under the influence of temperature provided in an embodiment of the present application;

[0050] Fig. 9It is a schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] In the description of the present application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more. In the description of the present application, the term "including" and its variations are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".

[0053] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0054] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0055] First, see Figure 1 , shows a flow chart of a source-load uncertainty scenario modeling method provided in an embodiment of the present application, the method comprising steps S101-S104, which are specifically as follows:

[0056] S101, respectively determining a high temperature and drought weather impact model and a first output model of the first unit, wherein the high temperature and drought weather impact model is suitable for indicating the impact of high temperature and drought weather on the second unit and the load end;

[0057] S102, fitting a first probability density function based on historical data of a first factor, performing sampling according to the first probability density function, generating a first scenario corresponding to the first factor, and determining a first output scenario based on the first scenario and the first output model, wherein the first factor represents a factor affecting the first unit;

[0058] S103, fitting a second probability density function based on historical data of a second factor, sampling according to the second probability density function, generating a second scenario corresponding to the second factor, and determining a second output scenario based on the second scenario and the high temperature and drought weather impact model, wherein the second factor represents a high temperature and drought weather factor;

[0059] S104: Perform scenario reduction based on the first output scenario and the second output scenario to obtain a typical scenario.

[0060] Among them, this typical scenario can be used to provide reference for power supply planning, overall operation, etc. of the power system, and can also be used to train artificial intelligence models to obtain scheduling models.

[0061] In an optional implementation, the second unit includes a photovoltaic unit, and the high temperature and drought weather impact model includes a first impact model;

[0062] in,

[0063] The first impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the photovoltaic group, wherein the photovoltaic group includes a photovoltaic cell group, and the first impact model is determined at least based on the difference between the temperature of the photovoltaic cell group and the operating temperature of the solar cell under standard operating conditions, and the temperature of the photovoltaic cell group is determined by the surface temperature, solar radiation intensity and wind speed at the location of the photovoltaic group.

[0064] It should be noted that photovoltaic power generation is a multifunctional solar technology that converts solar energy into electrical energy through solar panels. It does not require fuel and has good environmental benefits. The control system monitors and adjusts the energy conversion and output of photovoltaic power generation to ensure its stable operation. Power conversion equipment such as distribution cabinets and inverters convert direct current into alternating current, and then connects to the grid after boosting the voltage through a step-up transformer.

[0065] In one example, the efficiency of solar photovoltaic power generation depends on the solar irradiance and other atmospheric variables that affect the efficiency of the panel, such as the surface air temperature and the wind speed on the sand surface, and the high temperature and drought weather indicated by the first impact model has an effect on the output efficiency η of the photovoltaic unit. PV The influence of is expressed as:

[0066]

[0067] Where, L r is the solar shortwave irradiance, L0 is the solar irradiance under standard conditions, γ is the efficiency loss coefficient, T0 is the solar cell operating temperature under standard conditions, T cell is the temperature of the photovoltaic cell array.

[0068] T cell It can be calculated by the following formula:

[0069] T cell =c1+c2·T sur +c3·rsds+c4·v 10m

[0070] In the formula, c1, c2, c3, c4 are the coefficients corresponding to the influencing parameters, T sur is the surface temperature, which is related to the air temperature.

[0071] It should be noted that different thermal power units may use different cooling technologies. Extreme high temperature and drought weather have different effects on thermal power units using different cooling technologies. This application mainly considers two main cooling technologies:

[0072] 1. Direct cooling, that is, the heated cooling water returns to the water source. This technology requires a large amount of water from the water source;

[0073] 2. Closed-loop cooling, where cooling water circulates in a cooling loop including a cooling tower, with a small portion of the cooling water evaporating and released into the atmosphere. This technology only requires a small amount of water to be drawn from the water source.

[0074] Among them, the volume of cooling water required when the thermal power plant is running at maximum load can be expressed as:

[0075]

[0076] ΔT=max(min(T outmax -T inw ,ΔT max ),0)

[0077] Where V req is the cooling water capacity, P maxis the installed capacity of the thermal power plant, α is the proportion of waste heat dissipated into the air, which is smaller for the direct cooling system and larger for the closed-loop cooling system. ΔT max is the maximum allowable temperature rise of cooling water, T outmax is the highest allowable adjustable temperature of discharged cooling water, T inw is the plant inlet water temperature.

[0078] When T inw When increasing, V req This has a significant impact on the once-through cooling system, but not on the closed-loop cooling system. Power plants using closed-loop cooling systems are highly robust to water shortages and have negligible dependence on source water temperature, because any increase in water temperature can be compensated by increasing the volume of cooling water. In contrast, the output efficiency of power plants using closed-loop cooling systems is mainly affected by the cooling water temperature T that is circulated back to the condenser. inc This temperature can be assumed to be close to the air temperature.

[0079] Using parameter T i,j and A i,j To characterize the intensity of simulated high temperature and drought events, T i,j is the temperature at the location of power plant i at time j, A i,j It represents the cooling water availability of the power plant and is used to measure the drought degree of the environment. The value is around 1. The smaller the value, the higher the drought degree. The expression is:

[0080]

[0081] In the formula, t min is the minimum flow water temperature, t max is the maximum flow water temperature, γ is the slope of the regression curve, t ip It is the turning point temperature.

[0082] On this basis, embodiments of the above two cooling technologies are given below.

[0083] In an optional embodiment, the second unit includes a first thermal power unit using a direct cooling system, and the high temperature and drought weather impact model includes a second impact model;

[0084] in,

[0085] The second impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the first thermal power unit. The second impact model is expressed by the following formula:

[0086]

[0087] in, is the output efficiency of the first thermal power unit, A i,j Characterizes the available cooling water level of the first thermal power unit and is used to indicate the degree of drought in the environment. represents the water inlet temperature of the cooling system of the first thermal power unit and is determined by the air temperature of the first thermal power unit, β is the efficiency reduction coefficient, T h is the maximum temperature value under normal operating efficiency of the first thermal power unit, T sd is the shutdown water inlet temperature of the first thermal power unit, T r is the temperature when the waste heat actually discharged by the first thermal power unit is equal to the design value of the maximum power unit, δ is the efficiency coefficient, T outmax is the maximum allowable adjustable temperature of the cooling water discharged from the first thermal power unit, ΔT max It is the maximum allowable temperature rise of the cooling water of the first thermal power unit.

[0088] In one example, the efficiency coefficient δ can be obtained according to the continuity of the thermal power output efficiency expression, for example, expressed as the following formula:

[0089]

[0090] δ=A i,j +βΔT max -βA i,j (T outmax -T h )

[0091] In an optional embodiment, the second unit includes a second thermal power unit using a closed-loop cooling system, and the high temperature and drought weather impact model includes a third impact model;

[0092] in,

[0093] The third impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the second thermal power unit. The third impact model is expressed by the following formula:

[0094]

[0095] in, is the output efficiency of the second thermal power unit, T i,j represents the temperature of the area where thermal power unit i is located at time j, T ha is the maximum allowable temperature of the second thermal power unit at full efficiency output, and ρ is the efficiency reduction coefficient.

[0096] In an optional implementation, the high temperature and drought weather impact model includes a fourth impact model;

[0097] in,

[0098] The fourth impact model is suitable for indicating the impact of high temperature and drought weather on the load end. The fourth impact model is expressed by the following formula:

[0099]

[0100] Where C is the temperature sensitivity coefficient of the load, P l is the load at the load end under the influence of high temperature and dry weather, P ol is the original predicted load value of the load end, Represents the average historical reference temperature of the region, T i,j It represents the temperature in the area where thermal power unit i is located at time j.

[0101] In an optional implementation, the first unit includes a wind turbine unit, the historical data of the first factor includes historical wind speed data, and the first scenario includes a wind speed scenario;

[0102] The fitting of a first probability density function based on the historical data of the first factor, and sampling according to the first probability density function to generate a first scenario corresponding to the first factor, includes:

[0103] Based on the wind speed historical data, Weibull distribution is used for fitting to obtain a fitting coefficient, so as to determine a first probability density function suitable for indicating the wind speed distribution according to the fitting coefficient; wherein the fitting coefficient may be a plurality of fitting coefficients corresponding to a plurality of set time periods respectively, and each fitting coefficient may determine a corresponding first probability density function for indicating the wind speed in the corresponding set time period;

[0104] The wind speed scenario is generated according to the first probability density function using Latin hypercube sampling.

[0105] In one example, the first probability density function can be expressed by the following formula:

[0106]

[0107] Wherein, k and c are the fitting coefficients of Weibull distribution, and x is the wind speed, which is the independent variable of the first probability density function. In this embodiment, the wind speed affects the output of the wind turbine, and the distribution of the wind speed obeys the Weibull distribution.

[0108] It should be noted that wind turbines are one of the clean and renewable energy sources and occupy an important position in the energy structure. Wind drives the turbine and converts mechanical energy into electrical energy through the generator. In this process, the speed increaser is responsible for increasing the turbine speed so that the generator reaches the operating conditions. The electrical energy is connected to the grid through the transformer and power electronics. The control system monitors and controls the operation of the entire wind turbine to ensure safe and stable power generation.

[0109] In one example, the operation model of a wind turbine is expressed by the following formula:

[0110]

[0111] In the formula, v H is the wind speed at the height H of the wind turbine hub, S represents the swept area, ρ is the air density; η max is the maximum wind energy utilization factor, P max is the maximum output power; η w is the wind energy utilization rate; P r and P WTG (v H ) are the rated power and actual power of the fan, v 10m and v r are the wind speed at a height of 10m and the rated operating wind speed of the wind turbine, v ci and v co They are the cut-in wind speed and cut-out wind speed of the fan respectively.

[0112] In an optional implementation, the historical data of the second factor includes temperature historical data and solar irradiance historical data, the second probability density function includes a third probability density function and a fourth probability density function, and the second scenario corresponding to the second factor includes a temperature scenario and a solar irradiance scenario.

[0113] The fitting of a second probability density function based on the historical data of the second factor, and sampling according to the second probability density function to generate a second scenario corresponding to the second factor, includes:

[0114] Based on the temperature history data, a normal distribution is used for fitting to determine the third probability density function, and according to the third probability density function, Latin hypercube sampling is used to generate the temperature scenario;

[0115] Based on the solar irradiance historical data, chi-square distribution is used for fitting to determine the fourth probability density function, and according to the fourth probability density function, Latin hypercube sampling is used to generate the solar irradiance scene.

[0116] In one example, the average temperature under high temperature weather conditions may also be generated based on the temperature history data to determine the third probability density, thereby generating the temperature scenario.

[0117] In one example, the fourth probability density function can be expressed by the following formula:

[0118]

[0119] Where y is a random variable, n is the degree of freedom, and Γ is the gamma function.

[0120] In this embodiment, solar irradiance affects photovoltaic output, and the distribution of irradiance obeys chi-square distribution.

[0121] In one example, the first output scenario and / or the second output scenario may be generated in the manner of generating any of the above scenarios (the first scenario and / or the second scenario), which will not be described in detail herein.

[0122] In one example, the method of generating any of the above scenarios (the first scenario and / or the second scenario) can be used to generate a thermal power unit output efficiency scenario and a typical photovoltaic output scenario based on the obtained temperature scenario and a given decreasing cooling water availability level sequence.

[0123] In an optional implementation manner, the performing scenario reduction based on the first output scenario and the second output scenario to obtain a typical scenario includes:

[0124] Based on the first output scenario and the second output scenario, construct a set of scenarios to be reduced;

[0125] Clustering is performed based on the scenes in the set of scenes to be reduced to obtain typical scenes, wherein the clustering is implemented by a BIRCH-AHC double-layer clustering algorithm.

[0126] In one example, the generated first output scenario, second output scenario and temperature scenario set can be constructed as a set of scenarios to be reduced; the maximum-minimum normalization method is used to unify the scenes in the set of scenarios to be reduced into benchmark values, and then they are spliced ​​into high-dimensional vectors for clustering, and the original values ​​are restored after obtaining the typical scene set.

[0127] In one example, for the BIRCH-AHC two-layer clustering algorithm, the specific description is as follows:

[0128] The BIRCH clustering algorithm can form a clustering tree structure for a large amount of data, which is suitable for processing large-scale photovoltaic output data sets; it automatically determines the number of clusters, and can quickly adapt to the distribution characteristics of scene sets under different circumstances. The BIRCH clustering algorithm is used to first establish a clustering feature tree. The process is as follows: (a) First, initialize the parameters of the clustering tree and read in the clustering data samples in turn. (b) For each sample, start from the root node and search for the leaf node and cluster subcluster with the closest Euclidean distance downward. (c) If the distribution radius of the cluster subcluster is still less than the threshold after the sample is added, it is successfully inserted; if the number of subclusters of the current leaf node is less than the leaf balance factor, a new cluster subcluster is created to store the sample, and the new subcluster is added to the leaf node. (d) If the number of current leaf nodes reaches the branch balance factor, the leaf node is split into two new leaf nodes. (e) Check whether the upper node also needs to be split. If so, split it in the same way. When all the samples are inserted, a clustering feature tree is formed.

[0129] Since the BIRCH algorithm is an unsupervised learning algorithm, the number of clusters obtained is difficult to be within the expected range when considering the BIRCH clustering effect. Therefore, the Agglomerative Hierarchical Clustering (AHC) algorithm is used to perform secondary clustering on the subclusters obtained after BIRCH clustering to obtain a typical scenario.

[0130] In order to verify the effectiveness of the proposed scenario modeling method, the actual data of a certain area over a week is taken as an example. With an interval of 1 hour, the heat wave begins on the second day of the week, the high temperature lasts from the second to the fourth day, and the high temperature ends on the fifth to seventh day, but the drought continues. The parameters shown in Table 1 are used for testing.

[0131] Table 1

[0132]

[0133]

[0134] In addition, see Figure 2 , shows 1000 sets of wind power scene sets obtained based on the embodiments of the present application, see Figure 3 , shows 1000 sets of photovoltaic output scene sets obtained based on the embodiments of the present application, see Figure 4 , showing the original temperature not affected by the heat wave and 1000 sets of temperature uncertainty scenarios obtained based on the embodiments of the present application, see Figure 5 , shows five typical scene sets obtained by using the BIRCH-AHC two-layer clustering algorithm in the embodiment of the present application, see Figure 6 , showing the original load without temperature influence and the load under the influence of temperature for five typical scenario sets, see Figure 7 , which shows the changes in output efficiency of different types of thermal power units under five typical scenarios, see Figure 8 , showing the before and after changes in a typical set of photovoltaic output scenarios under the influence of temperature.

[0135] Among them, Figure 2 and Figure 3 It can be seen that the output of photovoltaic and wind power does not differ much from day to day. The output of photovoltaic is relatively large from 10:00 to 16:00 during the day, and is zero at night. The output of wind power is relatively large at night because the wind speed is generally higher at night. Figure 4 It can be seen that under the influence of the heat wave, the temperature rose rapidly from the second to the fourth day and the scene uncertainty became more obvious, which is consistent with the set scenario. Figure 5 It can be seen that after normalizing, splicing and restoring all scenes, five typical scene sets are obtained. The peaks of photovoltaic output fluctuate greatly, corresponding to the different degrees of sunlight being blocked by clouds during the noon period when photovoltaic output is generally high. After clustering, the temperature scenes are basically around the set historical average temperature. Figure 6 It can be seen that the rise in temperature under the influence of heat waves will lead to an increase in load, which may be due to the increase in the power of some electrical equipment under high temperature and the increase in residents' dependence on air conditioning. Figure 7 It can be seen that high temperature and drought greatly reduce the efficiency of the through-cooling unit, especially in the case of drought after high temperature, the available level of cooling water decreases, and the efficiency of the through-cooling unit will remain at a relatively low level, about 30%-40%. The closed-loop cooling unit is more robust to water shortages, so its efficiency is only slightly reduced by the high temperature, but it is maintained at about 90% overall, which is still at a relatively high level. Figure 8 It can be seen that due to the influence of high temperature, the temperature of the photovoltaic battery group is generally higher than the temperature under standard working conditions. Therefore, the photovoltaic output will decrease due to the influence of temperature, and the efficiency will be reduced by about 20%.

[0136] In a second aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0137] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the steps of any of the methods described above when executing the computer program.

[0138] See also Fig. 9The computer device of this embodiment includes: a processor 901, a memory 902, and a computer program stored in the memory 902 and executable on the processor 901, such as a source-load uncertainty scenario modeling program. When the processor 901 executes the computer program, the steps in the above-mentioned source-load uncertainty scenario modeling method embodiments are implemented, such as Figure 1 Steps S101-S104 are shown.

[0139] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 902 and executed by the processor 901 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the computer device.

[0140] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may include, but not limited to, a processor 901 and a memory 902. Those skilled in the art may understand that the schematic diagram is only an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0141] The processor 901 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor 901 may also be any conventional processor, etc. The processor 901 is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0142] The memory 902 can be used to store the computer program and / or module, and the processor 901 implements various functions of the computer device by running or executing the computer program and / or module stored in the memory 902, and calling the data stored in the memory 902. The memory 902 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 902 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0143] Wherein, if the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor 901. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0144] In summary, the embodiments of the present application have at least the following beneficial effects:

[0145] According to an embodiment of the present application, a high temperature and drought weather impact model and a first output model of the first unit are determined respectively, wherein the high temperature and drought weather impact model is suitable for indicating the impact of high temperature and drought weather on the second unit and the load end; a first probability density function is fitted based on historical data of the first factor, and a first scenario corresponding to the first factor is generated by sampling according to the first probability density function, and a first output scenario is determined based on the first scenario and the first output model, wherein the first factor represents the factor affecting the first unit; a second probability density function is fitted based on historical data of the second factor, and a second scenario corresponding to the second factor is generated by sampling according to the second probability density function, and a second output scenario is determined based on the second scenario and the high temperature and drought weather impact model, wherein the second factor represents the high temperature and drought weather factor; scenario reduction is performed based on the first output scenario and the second output scenario to obtain a typical scenario, so that extreme high temperature and drought weather can be simulated to accurately model a large number of typical scenarios of source-load uncertainty.

[0146] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary hardware platform, and of course it can also be implemented entirely by hardware. Based on such an understanding, all or part of the contribution of the technical solution of the present application to the background technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0147] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A source-load uncertainty scenario modeling method, characterized in that: include: Determining a high temperature and drought weather impact model and a first output model of the first unit respectively, wherein the high temperature and drought weather impact model is suitable for indicating the impact of high temperature and drought weather on the second unit and the load end; Fitting a first probability density function based on historical data of a first factor, sampling according to the first probability density function, generating a first scenario corresponding to the first factor, and determining a first output scenario based on the first scenario and the first output model, wherein the first factor represents a factor affecting the first unit; Fitting a second probability density function based on historical data of a second factor, sampling according to the second probability density function, generating a second scenario corresponding to the second factor, and determining a second output scenario based on the second scenario and the high temperature and drought weather impact model, wherein the second factor represents a high temperature and drought weather factor; Scenario reduction is performed based on the first output scenario and the second output scenario to obtain a typical scenario.

2. The method according to claim 1, characterized in that The second unit includes a photovoltaic unit, and the high temperature and drought weather impact model includes a first impact model; in, The first impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the photovoltaic group, wherein the photovoltaic group includes a photovoltaic cell group, and the first impact model is determined at least based on the difference between the temperature of the photovoltaic cell group and the operating temperature of the solar cell under standard operating conditions, and the temperature of the photovoltaic cell group is determined by the surface temperature, solar radiation intensity and wind speed at the location of the photovoltaic group.

3. The method according to claim 1, characterized in that The second unit includes a first thermal power unit using a direct cooling system, and the high temperature and drought weather impact model includes a second impact model; in, The second impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the first thermal power unit. The second impact model is expressed by the following formula: in, is the output efficiency of the first thermal power unit, A i,j Characterizes the available cooling water level of the first thermal power unit and is used to indicate the degree of drought in the environment. represents the water inlet temperature of the cooling system of the first thermal power unit and is determined by the air temperature of the first thermal power unit, β is the efficiency reduction coefficient, T h is the maximum temperature value under normal operating efficiency of the first thermal power unit, T sd is the shutdown water inlet temperature of the first thermal power unit, T r is the temperature when the waste heat actually discharged by the first thermal power unit is equal to the design value of the maximum power unit, δ is the efficiency coefficient, T outmax is the maximum allowable adjustable temperature of the cooling water discharged from the first thermal power unit, ΔT max It is the maximum allowable temperature rise of the cooling water of the first thermal power unit.

4. The method according to claim 1, characterized in that: The second unit includes a second thermal power unit using a closed-loop cooling system, and the high temperature and drought weather impact model includes a third impact model; in, The third impact model is suitable for indicating the impact of high temperature and drought weather on the output efficiency of the second thermal power unit. The third impact model is expressed by the following formula: in, is the output efficiency of the second thermal power unit, T i,j represents the temperature of the area where thermal power unit i is located at time j, T ha is the maximum allowable temperature of the second thermal power unit at full efficiency output, and ρ is the efficiency reduction coefficient.

5. The method according to claim 1, characterized in that The high temperature and drought weather impact model includes a fourth impact model; in, The fourth impact model is suitable for indicating the impact of high temperature and drought weather on the load end. The fourth impact model is expressed by the following formula: Where C is the temperature sensitivity coefficient of the load, P l is the load at the load end under the influence of high temperature and dry weather, P ol is the original predicted load value of the load end, Represents the average historical reference temperature of the region, T i,j It represents the temperature in the area where thermal power unit i is located at time j.

6. The method according to claim 1, characterized in that The first unit includes a wind turbine unit, the historical data of the first factor includes historical wind speed data, and the first scenario includes a wind speed scenario; The fitting of a first probability density function based on the historical data of the first factor, and sampling according to the first probability density function to generate a first scenario corresponding to the first factor, includes: Based on the historical wind speed data, Weibull distribution is used for fitting to obtain fitting coefficients, so as to determine a first probability density function suitable for indicating wind speed distribution according to the fitting coefficients; The wind speed scenario is generated according to the first probability density function using Latin hypercube sampling.

7. The method according to claim 1, characterized in that The historical data of the second factor includes temperature historical data and solar irradiance historical data, the second probability density function includes a third probability density function and a fourth probability density function, and the second scene corresponding to the second factor includes a temperature scene and a solar irradiance scene. The fitting of a second probability density function based on the historical data of the second factor, and sampling according to the second probability density function to generate a second scenario corresponding to the second factor, includes: Based on the temperature history data, a normal distribution is used for fitting to determine the third probability density function, and according to the third probability density function, Latin hypercube sampling is used to generate the temperature scenario; Based on the solar irradiance historical data, chi-square distribution is used for fitting to determine the fourth probability density function, and according to the fourth probability density function, Latin hypercube sampling is used to generate the solar irradiance scene.

8. The method according to claim 1, characterized in that The scene reduction based on the first output scene and the second output scene to obtain a typical scene includes: Based on the first output scenario and the second output scenario, construct a set of scenarios to be reduced; Clustering is performed based on the scenes in the set of scenes to be reduced to obtain typical scenes, wherein the clustering is implemented by a BIRCH-AHC double-layer clustering algorithm.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

10. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method according to any one of claims 1 to 8 when executing the computer program.

Images