Virtual power plant regulation capability test method and device

Abstract

The invention relates to the technical field of virtual power plant testing, and provides a virtual power plant regulation capability testing method, which comprises the steps of generating a deterministic temperature testing scene and a random temperature testing scene based on a temperature prediction curve corresponding to a virtual power plant, and combining the deterministic temperature testing scene and the random temperature testing scene to obtain a virtual power plant regulation capability testing result. Obtaining a total temperature test scene set; clustering the temperature test scenes in the total temperature test scene set, and obtaining clustering centers corresponding to various temperature test scenes; virtual power plant adjustment demand parameter design values corresponding to the various temperature test scenes are determined based on the clustering centers corresponding to the various temperature test scenes; and setting virtual power plant adjustment demand parameters by using the design values of the virtual power plant adjustment demand parameters corresponding to the various temperature test scenes, and then testing the adjustment capability of the virtual power plant. The scheme can be effectively used for simulating the adjustment challenge faced by the virtual power plant in a real environment.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plant testing, and in particular to a method and device for testing the regulation capability of a virtual power plant. Background Art

[0002] A virtual power plant (VPP) is a power coordination and management system that uses advanced information and communication technologies and software systems to aggregate and coordinate DERs such as DG, energy storage systems, controllable loads, and electric vehicles, so that it can participate in the electricity market and grid operations as a special power plant.

[0003] The actual operation of a virtual power plant (VPP) is influenced by numerous factors, temperature being a crucial one. Dynamic temperature fluctuations directly impact the operational characteristics of various resources within the VPP and the electricity demands of users. For example, in high summer temperatures, the electricity demand of temperature-controlled loads such as air conditioners increases significantly, photovoltaic module efficiency decreases, and high temperatures accelerate battery aging. This, in turn, places higher demands on the scheduling and operation of the virtual power plant. Furthermore, temperature fluctuations can lead to dynamic changes in the power ranges of power generation, energy storage, and loads, further increasing the uncertainty of VPP operation.

[0004] For VPP testing, it is usually assumed that the temperature remains unchanged throughout the entire test cycle (static assumption) or a fixed average value is used (average assumption). The temporal coupling relationship between temperature changes and power load and power output is not considered. For example, it is unable to capture load increases, user response rate decreases, and energy storage performance degradation caused by high temperatures. As a result, the test results are seriously deviated from reality. The test scenario is single and ignores temporal correlations, making it impossible to adapt to real-time changes. Summary of the Invention

[0005] In order to overcome the above-mentioned defects, the present invention proposes a method and device for testing the regulation capability of a virtual power plant.

[0006] In a first aspect, a method for testing the regulation capability of a virtual power plant is provided, the method comprising:

[0007] Generating a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, and merging the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set;

[0008] Clustering the temperature test scenarios in the total temperature test scenario set, and obtaining cluster centers corresponding to each type of temperature test scenario;

[0009] Determining the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios based on the cluster centers corresponding to the various temperature test scenarios;

[0010] The virtual power plant regulation demand parameter design values corresponding to the various temperature test scenarios are used to set the virtual power plant regulation demand parameters and then perform a virtual power plant regulation capability test.

[0011] Preferably, generating a deterministic temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant includes:

[0012] Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve;

[0013] Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario;

[0014] The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

[0015] Furthermore, the mathematical model corresponding to the temperature rise rate adjustment rule is as follows:

[0016]

[0017] The mathematical model corresponding to the peak temperature offset adjustment rule is as follows:

[0018] T base (t)′=T base (t)+ΔT peak

[0019] The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows:

[0020] T base (t)′=T base (t)+ΔT event (t)

[0021] The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows:

[0022] T base (t)′=T base (t)+5·(tt start ),t∈[t start ,t end ]

[0023] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows:

[0024]

[0025] In the above formula, T base(t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

[0026] Furthermore, the generating of a random temperature test scenario based on the temperature prediction curve corresponding to the virtual power plant includes:

[0027] Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results;

[0028] Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results;

[0029] Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios;

[0030] The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

[0031] Furthermore, after merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the following steps are performed:

[0032] Randomly add noise to each temperature test scene in the random temperature test scene;

[0033] Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario;

[0034] The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

[0035] Preferably, the design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

[0036] Furthermore, the power requirement of the adjustable load is as follows:

[0037]

[0038] The photovoltaic power generation efficiency is as follows:

[0039] η PV =η STC ·[1+β·(T PV (T)-T STC )]

[0040]

[0041] The energy storage charge and discharge rates are as follows:

[0042] η charge / discharge (T) = η nominal ·f η (T)

[0043]

[0044] The capacity decay is as follows:

[0045] C available (T)=C nominal ·f c (T)

[0046]

[0047] In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, P base is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η (T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, Cnominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

[0048] Preferably, the virtual power plant regulation demand parameter design values corresponding to the various temperature test scenarios are used to set the virtual power plant regulation demand parameters and then perform the virtual power plant regulation capability test, including:

[0049] After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

[0050] Furthermore, the technical indicators are as follows:

[0051] P reg =|P target -P actual |

[0052]

[0053] In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

[0054] Furthermore, the economic indicators are as follows:

[0055]

[0056] R market =P reg ·t·p market

[0057] NetProfit=R market -(C user +C storage )

[0058]

[0059] In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,iThe power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current time period, p market is the market clearing price, NetProfit is the net revenue, and Costper MWh is the unit regulation cost.

[0060] In a second aspect, a virtual power plant regulation capability testing device is provided, the virtual power plant regulation capability testing device comprising:

[0061] A generation module, configured to generate a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, and merge the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set;

[0062] A clustering module, configured to cluster the temperature test scenarios in the total temperature test scenario set and obtain cluster centers corresponding to each type of temperature test scenario;

[0063] A determination module, configured to determine, based on the cluster centers corresponding to the various temperature test scenarios, design values of virtual power plant regulation demand parameters corresponding to the various temperature test scenarios;

[0064] The test module is used to set the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios and then perform a virtual power plant regulation capability test.

[0065] Preferably, the generating module is specifically used for:

[0066] Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve;

[0067] Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario;

[0068] The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

[0069] Furthermore, the mathematical model corresponding to the temperature rise rate adjustment rule is as follows:

[0070]

[0071] The mathematical model corresponding to the peak temperature offset adjustment rule is as follows:

[0072] T base (t)′=T base (t)+ΔT peak

[0073] The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows:

[0074] T base (t)′=T base (t)+ΔT event (t)

[0075] The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows:

[0076] T base (t)′=T base (t)+5·(tt start ),t∈[t start ,t end ]

[0077] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows:

[0078]

[0079] In the above formula, T base (t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

[0080] Furthermore, the generating of a random temperature test scenario based on the temperature prediction curve corresponding to the virtual power plant includes:

[0081] Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results;

[0082] Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results;

[0083] Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios;

[0084] The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

[0085] Furthermore, after merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the following steps are performed:

[0086] Randomly add noise to each temperature test scene in the random temperature test scene;

[0087] Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario;

[0088] The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

[0089] Preferably, the design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

[0090] Furthermore, the power requirement of the adjustable load is as follows:

[0091]

[0092] The photovoltaic power generation efficiency is as follows:

[0093] η PV =η STC ·[1+β·(T PV (T)-T STC )]

[0094]

[0095] The energy storage charge and discharge rates are as follows:

[0096] η charge / discharge (T) = η nominal ·f η (T)

[0097]

[0098] The capacity decay is as follows:

[0099] C available (T)=Cnominal ·f c (T)

[0100]

[0101] In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, P base is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η (T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, C nominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

[0102] Preferably, the test module is specifically used for:

[0103] After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

[0104] Furthermore, the technical indicators are as follows:

[0105] P reg =|P target -P actual |

[0106]

[0107]

[0108] In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

[0109] Furthermore, the economic indicators are as follows:

[0110]

[0111] R market =P reg ·t·p market

[0112] NetProfit=R market -(C user +C storage )

[0113]

[0114] In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,i The power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current time period, p market is the market clearing price, NetProfit is the net revenue, and Costper MWh is the unit regulation cost.

[0115] In a third aspect, a computer device is provided, comprising: one or more processors;

[0116] The processor is configured to execute one or more programs;

[0117] When the one or more programs are executed by the one or more processors, the virtual power plant regulation capability testing method is implemented.

[0118] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the virtual power plant regulation capability testing method is implemented.

[0119] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0120] The present invention provides a method and device for testing the regulation capability of a virtual power plant, comprising: generating a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, merging the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set; clustering the temperature test scenarios in the total temperature test scenario set and obtaining cluster centers corresponding to each type of temperature test scenario; determining the design values of the regulation demand parameters of the virtual power plant corresponding to each type of temperature test scenario based on the cluster centers corresponding to the various types of temperature test scenarios; and performing a regulation capability test of the virtual power plant after setting the regulation demand parameters of the virtual power plant using the design values of the regulation demand parameters of the virtual power plant corresponding to the various types of temperature test scenarios. The technical solution provided by the present invention can more comprehensively simulate real data and test the robustness of the VPP under different working conditions. It can establish a good regulation capability test scheme for multiple types of virtual power plants, has universal applicability, and is effectively used to simulate the regulation challenges faced by virtual power plants in real environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] Figure 1 It is a flowchart of the main steps of the virtual power plant regulation capability testing method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0122] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0123] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0124] As disclosed in the background technology, a virtual power plant (VPP) is a power coordination and management system that uses advanced information and communication technologies and software systems to achieve the aggregation and coordinated optimization of DERs such as DG, energy storage systems, controllable loads, and electric vehicles, so that it can participate in the power market and power grid operation as a special power plant.

[0125] The actual operation of a virtual power plant (VPP) is influenced by numerous factors, temperature being a crucial one. Dynamic temperature fluctuations directly impact the operational characteristics of various resources within the VPP and the electricity demands of users. For example, in high summer temperatures, the electricity demand of temperature-controlled loads such as air conditioners increases significantly, photovoltaic module efficiency decreases, and high temperatures accelerate battery aging. This, in turn, places higher demands on the scheduling and operation of the virtual power plant. Furthermore, temperature fluctuations can lead to dynamic changes in the power ranges of power generation, energy storage, and loads, further increasing the uncertainty of VPP operation.

[0126] For VPP testing, it is usually assumed that the temperature remains unchanged throughout the entire test cycle (static assumption) or a fixed average value is used (average assumption). The temporal coupling relationship between temperature changes and power load and power output is not considered. For example, it is unable to capture load increases, user response rate decreases, and energy storage performance degradation caused by high temperatures. As a result, the test results are seriously deviated from reality. The test scenario is single and ignores temporal correlations, making it impossible to adapt to real-time changes.

[0127] In order to improve the above problems, the present invention provides a method and device for testing the regulation capability of a virtual power plant, comprising: generating a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, merging the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set; clustering the temperature test scenarios in the total temperature test scenario set, and obtaining the cluster centers corresponding to each type of temperature test scenario; determining the design values of the regulation demand parameters of the virtual power plant corresponding to each type of temperature test scenario based on the cluster centers corresponding to the various temperature test scenarios; and performing a regulation capability test of the virtual power plant after setting the regulation demand parameters of the virtual power plant using the design values of the regulation demand parameters of the virtual power plant corresponding to the various temperature test scenarios. The technical solution provided by the present invention can simulate real data more perfectly, and at the same time test the robustness of the VPP under different working conditions. It can establish a good regulation capability test scheme for multiple types of virtual power plants, has universal applicability, and is effectively used to simulate the regulation challenges faced by virtual power plants in real environments.

[0128] The above scheme is described in detail below.

[0129] Example 1

[0130] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for testing the regulation capability of a virtual power plant according to an embodiment of the present invention. Figure 1 As shown, the virtual power plant regulation capability testing method in the embodiment of the present invention mainly includes the following steps:

[0131] Step S101: generating a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to a virtual power plant, and merging the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set;

[0132] Step S102: clustering the temperature test scenarios in the total temperature test scenario set, and obtaining cluster centers corresponding to each type of temperature test scenario;

[0133] Step S103: determining the design values of the virtual power plant regulation demand parameters corresponding to each temperature test scenario based on the cluster centers corresponding to the various temperature test scenarios;

[0134] Step S104: performing a virtual power plant regulation capability test after setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios.

[0135] In this embodiment, the generation of a deterministic temperature test scenario based on the temperature prediction curve corresponding to the virtual power plant includes:

[0136] Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve;

[0137] Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario;

[0138] The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

[0139] In a specific embodiment, the added disturbance is a small disturbance simulating the prediction error, which is randomly generated based on a normal distribution probability density function with a variance of 0.3.

[0140] In one embodiment, the mathematical model corresponding to the temperature rise rate adjustment rule is as follows:

[0141]

[0142] The mathematical model corresponding to the peak temperature offset adjustment rule is as follows:

[0143] T base (t)′=T base (t)+ΔT peak

[0144] The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows:

[0145] T base (t)′=T base (t)+ΔTevent (t)

[0146] The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows:

[0147] T base (t)′=T base (t)+5·(tt start ),t∈[t start ,t end ]

[0148] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows:

[0149]

[0150] In the above formula, T base (t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

[0151] In one embodiment, generating a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant includes:

[0152] Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results;

[0153] Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results;

[0154] Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios;

[0155] The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

[0156] In a specific embodiment, the temperature parameters may include: duration, temperature difference range, daily average temperature, temperature rise rate, temperature drop rate, etc.

[0157] In one embodiment, after merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the method includes:

[0158] Randomly add noise to each temperature test scene in the random temperature test scene;

[0159] Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario;

[0160] The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

[0161] In a specific embodiment, the added noise is randomly generated based on a normal distribution probability density function with a variance of 0.5.

[0162] In a specific embodiment, in order to avoid the simplification of test scenarios, the clustering method of the present invention adopts the K-means clustering algorithm, and the specific steps are as follows:

[0163] Step 1. Before clustering, the number of clusters k is manually set. Then, k initial cluster centers C are randomly selected from the dataset (1≤i≤k). In this paper, the k value ranges from 2 to 6 clusters. Cluster evaluation indicators are compared under different numbers of clusters to select the optimal number of clusters.

[0164] Step 2. Calculate the Euclidean distance from the remaining data items to the cluster center C, find the cluster center with the closest distance, and merge it into the cluster.

[0165] Step 3. Update the cluster centers. Calculate the mean of the data items in each cluster as the new cluster center and proceed to the next iteration. Continue to reduce the sum of squared error (SSE) within the cluster until the cluster center stops changing or the objective function converges. Clustering stops.

[0166] In Step 1, the K-means clustering algorithm requires manual selection of the number of clusters. This paper uses the elbow method and silhouette coefficient method to select the optimal number of clusters.

[0167] The core metric of the elbow method is the sum of squared errors (SSE). During the clustering process, as the number of clusters k increases, the degree of cluster cohesion increases, and the SSE value gradually decreases. However, when k is less than the optimal number of clusters, the SSE value decreases significantly. When k is greater than the optimal number of clusters, the SSE value tends to level off. Therefore, the optimal number of clusters is located at the elbow of the SSE vs. k plot.

[0168] The average silhouette coefficient ranges from -1 to 1. Based on the basic clustering algorithm principle of "clustering within a cluster and dispersing outside a cluster," a larger average silhouette coefficient indicates a better clustering effect, with higher similarity between watersheds within a cluster and greater differentiation between watersheds outside a cluster. A value of 0 indicates overlapping clusters.

[0169] However, traditional K-Means may not be sufficient to handle the specific needs of time series data or temperature scenarios. Therefore, we combine dynamic time warping (DTW) with a feature weighting mechanism to design an improved K-Means algorithm for temperature scenario clustering, in order to better capture the temporal characteristics and key patterns of temperature fluctuations.

[0170] In this embodiment, the design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

[0171] In one embodiment, the power requirement of the adjustable load is as follows:

[0172]

[0173] The photovoltaic power generation efficiency is as follows:

[0174] η PV =η STC ·[1+β·(T PV (T)-T STC )]

[0175]

[0176] The energy storage charge and discharge rates are as follows:

[0177] η charge / discharge (T) = η nominal ·f η (T)

[0178]

[0179] The capacity decay is as follows:

[0180] C available (T)=C nominal ·f c (T)

[0181]

[0182] In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, Pbase is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η (T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, C nominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

[0183] In this embodiment, the virtual power plant regulation demand parameter design values corresponding to the various temperature test scenarios are used to set the virtual power plant regulation demand parameters and then perform the virtual power plant regulation capability test, including:

[0184] After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

[0185] During the test, the scene parameters are corrected in real time based on the deviation between the actual temperature and the predicted value: the measured temperature is compared with the predicted value every 15 minutes, and the deviation ΔT is calculated. If ΔT exceeds the threshold, a new scene closest to the current temperature trend is matched from the scene library; if ΔT is within the threshold, the test continues with the original scene, but the prediction parameters for subsequent time periods need to be adjusted.

[0186] In one embodiment, the technical indicators are as follows:

[0187] P reg =|P target -P actual |

[0188]

[0189] In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

[0190] In one embodiment, the economic indicators are as follows:

[0191]

[0192] R market =P reg ·t·p market

[0193] NetProfit=R market -(C user +C storage )

[0194]

[0195] In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,i The power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current time period, p market is the market clearing price, NetProfit is the net revenue, and Costper MWh is the unit regulation cost.

[0196] Example 2

[0197] Based on the same inventive concept, the present invention further provides a virtual power plant regulation capability testing device, the virtual power plant regulation capability testing device comprising:

[0198] A generation module, configured to generate a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, and merge the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set;

[0199] A clustering module, configured to cluster the temperature test scenarios in the total temperature test scenario set and obtain cluster centers corresponding to each type of temperature test scenario;

[0200] A determination module, configured to determine, based on the cluster centers corresponding to the various temperature test scenarios, design values of virtual power plant regulation demand parameters corresponding to the various temperature test scenarios;

[0201] The test module is used to set the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios and then perform a virtual power plant regulation capability test.

[0202] Preferably, the generating module is specifically used for:

[0203] Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve;

[0204] Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario;

[0205] The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

[0206] Furthermore, the mathematical model corresponding to the temperature rise rate adjustment rule is as follows:

[0207]

[0208] The mathematical model corresponding to the peak temperature offset adjustment rule is as follows:

[0209] T base (t)′=T base (t)+ΔT peak

[0210] The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows:

[0211] T base (t)′=T base (t)+ΔT event (t)

[0212] The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows:

[0213] T base (t)′=T base (t)+5·(tt start ),t∈[t start ,t end ]

[0214] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows:

[0215]

[0216] In the above formula, T base (t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

[0217] Furthermore, the generating of a random temperature test scenario based on the temperature prediction curve corresponding to the virtual power plant includes:

[0218] Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results;

[0219] Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results;

[0220] Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios;

[0221] The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

[0222] Furthermore, after merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the following steps are performed:

[0223] Randomly add noise to each temperature test scene in the random temperature test scene;

[0224] Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario;

[0225] The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

[0226] Preferably, the design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

[0227] Furthermore, the power requirement of the adjustable load is as follows:

[0228]

[0229] The photovoltaic power generation efficiency is as follows:

[0230] η PV =η STC ·[1+β·(T PV (T)-T STC )]

[0231]

[0232] The energy storage charge and discharge rates are as follows:

[0233] η charge / discharge (T) = η nominal ·f η (T)

[0234]

[0235] The capacity decay is as follows:

[0236] C available (T)=C nominal ·f c (T)

[0237]

[0238] In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, P base is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η(T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, C nominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

[0239] Preferably, the test module is specifically used for:

[0240] After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

[0241] Furthermore, the technical indicators are as follows:

[0242] P reg =|P target -P actual |

[0243]

[0244] In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

[0245] Furthermore, the economic indicators are as follows:

[0246]

[0247] R market =P reg ·t·p market

[0248] NetProfit=R market -(C user +C storage )

[0249]

[0250] In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,i The power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current period, p market is the market clearing price, NetProfit is the net revenue, and Costper MWh is the unit regulation cost.

[0251] Example 3

[0252] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a virtual power plant regulation capability testing method in the above embodiment.

[0253] Example 4

[0254] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of a virtual power plant regulation capability testing method in the above embodiment.

[0255] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0256] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0257] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0258] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0259] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for testing the regulation capability of a virtual power plant, characterized in that: The method comprises: Generating a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, and merging the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set; Clustering the temperature test scenarios in the total temperature test scenario set, and obtaining cluster centers corresponding to each type of temperature test scenario; Determining the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios based on the cluster centers corresponding to the various temperature test scenarios; The virtual power plant regulation demand parameter design values corresponding to the various temperature test scenarios are used to set the virtual power plant regulation demand parameters and then perform a virtual power plant regulation capability test.

2. The method according to claim 1, wherein The generating of a deterministic temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant includes: Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve; Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario; The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

3. The method according to claim 2, wherein The mathematical model corresponding to the temperature rise rate adjustment rule is as follows: The mathematical model corresponding to the peak temperature offset adjustment rule is as follows: T base (t)′=T base (t)+ΔT peak The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows: T base (t)′=T base (t)+ΔT event (t) The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows: T base (t)′=T base (t)+5·(t-t start ),t∈[t start ,t end ] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows: In the above formula, T base (t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

4. The method according to claim 2, wherein The generating of a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant includes: Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results; Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results; Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios; The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

5. The method according to claim 4, wherein After merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the method includes: Randomly add noise to each temperature test scene in the random temperature test scene; Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario; The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

6. The method according to claim 1, wherein The design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

7. The method according to claim 6, wherein The power requirements of the adjustable load are as follows: The photovoltaic power generation efficiency is as follows: or PV =the STC ·[1+β·(T PV (T)-T STC )] The energy storage charge and discharge rates are as follows: or charge / discharge (T)=η nominal ·f η (T) The capacity decay is as follows: C available (T)=C nominal ·f c (T) In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, P base is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η (T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, C nominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

8. The method according to claim 1, wherein The virtual power plant regulation demand parameter design values corresponding to the various temperature test scenarios are used to set the virtual power plant regulation demand parameters and then perform the virtual power plant regulation capability test, including: After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

9. The method according to claim 8, wherein The technical indicators are as follows: P reg =|P target -P actual | In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

10. The method according to claim 8, wherein The economic indicators are as follows: R market =P reg ·t·p market NetProfit=R market -(C user +C storage ) In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,i The power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current period, p market is the market clearing price, NetProfit is the net revenue, and Cost per MWh is the unit adjustment cost.

11. A virtual power plant regulation capability testing device, characterized in that: The device comprises: A generation module, configured to generate a deterministic temperature test scenario and a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant, and merge the deterministic temperature test scenario and the random temperature test scenario to obtain a total temperature test scenario set; A clustering module, configured to cluster the temperature test scenarios in the total temperature test scenario set and obtain cluster centers corresponding to each type of temperature test scenario; A determination module, configured to determine, based on the cluster centers corresponding to the various temperature test scenarios, design values of virtual power plant regulation demand parameters corresponding to the various temperature test scenarios; The test module is used to set the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios and then perform a virtual power plant regulation capability test.

12. The device according to claim 11, wherein The generation module is specifically used for: Add disturbance to the temperature prediction curve corresponding to the virtual power plant to obtain the benchmark temperature curve; Adjusting the reference temperature curve using predefined rules to obtain a deterministic temperature test scenario; The predefined rules include: a temperature rise rate adjustment rule, a peak temperature offset adjustment rule, a history mode superposition adjustment rule, a maximum temperature rise rate adjustment rule or a continuous high temperature adjustment rule.

13. The device according to claim 12, wherein The mathematical model corresponding to the temperature rise rate adjustment rule is as follows: The mathematical model corresponding to the peak temperature offset adjustment rule is as follows: T base (t)′=T base (t)+ΔT peak The mathematical model corresponding to the historical pattern superposition adjustment rule is as follows: T base (t)′=T base (t)+ΔT event (t) The mathematical model corresponding to the maximum temperature rise rate adjustment rule is as follows: T base (t)′=T base (t)+5·(t-t start ),t∈[t start ,t end ] The mathematical model corresponding to the continuous high temperature adjustment rule is as follows: In the above formula, T base (t)′ is the data value corresponding to the time t of the adjusted deterministic temperature test scenario, T base (t) is the data value corresponding to the reference temperature curve at time t, ΔT rate is the target amplitude temperature, t is the adjustment time, t start is the starting time of the disturbance window, t end is the end time of the disturbance window, ΔT peak is the peak temperature offset, ΔT event (t) is the temperature deviation corresponding to time t in the historical event record, ΔT sustain is the maximum temperature deviation.

14. The device according to claim 12, wherein The generating of a random temperature test scenario based on a temperature prediction curve corresponding to the virtual power plant includes: Cluster the historical temperature curve data corresponding to the virtual power plant to obtain clustering results; Taking the temperature prediction curve as a benchmark, setting scenario generation constraints according to the temperature parameters of each cluster center in the clustering results, and using a Monte Carlo simulation algorithm to generate directional disturbance temperature scenarios corresponding to each cluster center in the clustering results; Based on the temperature prediction curve, a Monte Carlo simulation algorithm is used to generate random temperature scenarios; The directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers are merged to obtain a random temperature test scenario.

15. The device according to claim 14, wherein After merging the directional disturbance temperature scenarios and random temperature scenarios corresponding to the various cluster centers to obtain a random temperature test scenario, the method includes: Randomly add noise to each temperature test scene in the random temperature test scene; Randomly add temperature deviations corresponding to extreme events to each temperature test scenario in the random temperature test scenario; The data exceeding the preset maximum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset maximum temperature value, and the data less than the preset minimum temperature value in each temperature test scenario in the random temperature test scenario is replaced with the preset minimum temperature value.

16. The device according to claim 11, wherein The design value of the virtual power plant regulation demand parameter corresponding to the temperature test scenario includes at least one of the following: power demand of the adjustable load, photovoltaic power generation efficiency, energy storage charge and discharge rate, and capacity attenuation.

17. The device according to claim 16, characterized in that The power requirements of the adjustable load are as follows: The photovoltaic power generation efficiency is as follows: or PV =the STC ·[1+β·(T PV (T)-T STC )] The energy storage charge and discharge rates are as follows: or charge / discharge (T)=η nominal ·f η (T) The capacity decay is as follows: C available (T)=C nominal ·f c (T) In the above formula, P load is the power demand of the adjustable load, k is the proportional coefficient, T is the temperature test scenario, T set The temperature is set by the user, n is the power index, P base is the base load power, η PV is the photovoltaic power generation efficiency, η STC is the module efficiency under standard test conditions, β is the temperature coefficient, T PV (T) is the actual operating temperature of the photovoltaic module, T STC is the standard test temperature, G is the actual irradiance, G NOCT is the irradiance at nominal operating temperature, T NOCT is the nominal operating temperature of the component, η charge / discharge (T) is the energy storage charge and discharge rate, η nominal is the nominal charge and discharge efficiency, f η (T) is the scenario coefficient of temperature on energy storage charge and discharge rate, α low is the low temperature efficiency attenuation curve, α high is the high temperature efficiency attenuation curve, T ref is the reference temperature, C available (T) is the capacity attenuation, C nominal is the nominal capacity, f c (T) is the scenario coefficient of temperature on capacity attenuation, k low is the low temperature capacity attenuation coefficient, k high is the high temperature capacity attenuation coefficient.

18. The device according to claim 11, wherein The test module is specifically used for: After setting the virtual power plant regulation demand parameters using the design values of the virtual power plant regulation demand parameters corresponding to the various temperature test scenarios, it is determined whether the corresponding technical indicators and economic indicators of the virtual power plant meet the standards. If so, the virtual power plant passes the regulation capacity test; otherwise, the virtual power plant fails the regulation capacity test.

19. The device according to claim 18, wherein The technical indicators are as follows: P reg =|P target -P actual | In the above formula, P reg To adjust the capacity, P target Adjust the power to the target, P actual To actually adjust the power, T 90 is the response speed, P actual (t) is the actual regulated power at time t, Ω is the regulation accuracy, N is the calculation cycle, P target (t) is the target adjustment power at time t, and p is the success rate.

20. The device according to claim 18, wherein The economic indicators are as follows: R market =P reg ·t·p market NetProfit=R market -(C user +C storage ) In the above formula, C user is the user compensation cost, n is the total number of users, P curtail,i The power cut for the i-th user, t i To reduce the duration, r compensation is the unit compensation price, C storage is the energy storage loss cost, T is the statistical period, E cycle,t is the charge and discharge amount during period t, c degradation is the unit cycle cost, f(T t ) is the temperature correction coefficient, R market is the market return, P reg is the adjustment capacity, t is the current time period, p market is the market clearing price, NetProfit is the net revenue, and Cost per MWh is the unit adjustment cost.

21. A computer device, characterized in that: include: one or more processors; The processor is configured to execute one or more programs; When the one or more programs are executed by the one or more processors, the virtual power plant regulation capability testing method according to any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed, it implements the virtual power plant regulation capability testing method as described in any one of claims 1 to 10.

Images