A multi-type energy storage resource configuration method for new power systems

Abstract

The present invention relates to the field of electric power resource configuration, and in particular to a multi-type energy storage resource configuration method for a new type of electric power system. The method divides an electric power network node into a plurality of substations according to system data, obtains electric power data stored in each electric power network node, and a main station reads a plurality of electric power data as training samples, divides the data into a plurality of subsamples according to a preset sampling rate, trains a plurality of resource configuration models respectively, verifies the training results, determines the adaptation rate of each resource configuration model, compares the adaptation rate with the adaptation rate, obtains the corresponding adaptation comparison result, determines the average adaptation rate of a plurality of substations, and compares the adaptation rate with the average adaptation rate threshold. When the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted. By adjusting the sampling rate in real time, the problem that electric power resources and power consumption cannot be correctly matched is effectively solved, the accuracy of power system resource configuration is improved, and dynamic balance of electric power regulation is achieved.

Description

Technical Field

[0001] The present invention relates to the field of power resource configuration, and in particular to a multi-type energy storage resource configuration method for a new power system. Background Art

[0002] As the level of electricity marketization gradually improves, optimizing unit output and resource allocation is an important goal for electricity market participants. On the power generation side of the power system, power generators participate in market competition and achieve maximum resource optimization in the game process by optimizing decisions. Renewable energy generation is greatly affected by weather and has the characteristics of intermittent, volatile, and random, which affects the reliability of the power system. As the proportion of renewable energy increases, the contradiction between the two intensifies. The flexible adjustment characteristics of the energy storage system can effectively alleviate the contradiction between renewable energy output and power system stability, and play an important regulatory role on the power generation side. However, the participation of the energy storage system in the competition on the power generation side also makes the global resource optimization configuration of the power system more complicated.

[0003] Resource allocation on the power generation side of the power system is a research focus of scholars at home and abroad. In the past decade or so, scholars have proposed many optimization methods. However, with the continuous development of the power industry, especially the improvement of the degree of power marketization, the requirements for the optimization accuracy and speed of resource allocation are also increasing. Most of the existing studies are to achieve optimal resource allocation through the transfer of power generation rights and market means. In the power generation rights transaction, power generators are based on the maximization of their own interests, considering their own production capacity, business strategy and market changes, to continuously adjust their own competition strategies, resulting in excessive redundancy in the power system, inefficient resource allocation, and difficulty in adapting to the development of today's power market, affecting the operating efficiency of the power system.

[0004] Chinese Patent Authorization Announcement No.: CN112510683B discloses a method for configuring flexibility resources in an incremental distribution network considering source-load uncertainty, which belongs to the technical field of power systems. It includes the following steps: considering the user interruption load response curve to construct an interruptible load compensation model for the incremental distribution network; considering the energy storage safe operation constraints to construct an energy storage configuration model for the incremental distribution network; using multiple scenarios to characterize the uncertainty of distributed power sources and loads in the incremental distribution network, constructing a joint configuration model for flexibility resources in the incremental distribution network, and solving the model. This invention models the demand-side response and energy storage configuration of the incremental distribution network, and proposes a joint configuration method for interruptible loads and energy storage in the incremental distribution network.

[0005] However, the above method has the following problems: power regulation cannot achieve dynamic balance. Summary of the invention

[0006] To this end, the present invention provides a multi-type energy storage resource configuration method for a new power system, which is used to overcome the problems in the prior art that the types of power grid resources are complex, the statistical methods of various types are not unified, and some small power networks also have power generation capacity, which leads to the inability to achieve dynamic balance in the overall regulation of the power system.

[0007] To achieve the above object, the present invention provides a multi-type energy storage resource configuration method for a new power system, comprising:

[0008] Divide the power network nodes into several substations according to the system data, and obtain the power data stored in each power network node;

[0009] Using the master station to read some of the electric energy data, using the electric energy data as training samples, and dividing the electric energy data into a plurality of sub-samples according to a preset sampling rate;

[0010] Using the sub-samples to train a plurality of resource allocation models respectively, and using the sub-samples to verify the training results;

[0011] Determine the adaptation rate of each resource configuration model based on the verification results, including:

[0012] Setting an adaptation rate threshold, comparing the adaptation rate of each resource configuration model with the adaptation rate threshold, and obtaining a corresponding adaptation comparison result;

[0013] Determine an average adaptation rate of the plurality of substations according to the adaptation comparison result;

[0014] comparing the average adaptation rate with an average adaptation rate threshold;

[0015] When the average adaptation rate is less than the average adaptation rate threshold, adjusting the sampling rate of the resource configuration model;

[0016] The power data includes peak power consumption time, power storage surplus, equipment temperature, and power consumption;

[0017] The adaptation rate is the proportion of the training results that are the same as the training results in the sub-samples after training is performed using the resource configuration model and the training results are obtained;

[0018] The sampling rate is related to the recognition capability of the resource configuration model.

[0019] Furthermore, the step of collecting the electric energy data of the plurality of substations includes:

[0020] The plurality of substations send summary instructions to corresponding electric energy meters;

[0021] The electric energy data stored in the electric energy meter is aggregated to the corresponding collection device through an interface;

[0022] The collection device sends the electric energy data to the master station;

[0023] The electric energy meter obtains the electric energy data from the corresponding collection device according to the summary instruction.

[0024] Further, the master station is used to read a number of the electric energy data, and the electric energy data is divided into a number of the sub-samples according to a preset sampling rate;

[0025] When dividing the sub-samples, the electric energy data are used as the training samples and are sorted according to the indicators.

[0026] The indicators include peak power consumption time, power storage margin, device temperature and / or power consumption of each power data in the training sample. Further, the step of determining the adaptation rate of a single resource configuration model includes:

[0027] Corresponding to each sub-sample received by the single resource configuration model;

[0028] Polling the verification result in the corresponding resource configuration model, and calculating the adaptation rate of the resource configuration model;

[0029] When the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, adjusting the sampling rate of the corresponding resource configuration model;

[0030] Collecting the adaptation rates of the resource configuration models again and using them as new adaptation rates;

[0031] Wherein, a timer is provided in the resource configuration model for polling the verification result of the resource configuration model at fixed intervals.

[0032] Further, the adaptation rate is compared with the adaptation rate threshold to obtain the corresponding adaptation comparison result,

[0033] The adaptation rate threshold is the minimum standard of the adaptation rate of a single resource configuration model.

[0034] Furthermore, when the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, the duration of the corresponding interface is adjusted.

[0035] Further, the adaptation rates of the plurality of resource configuration models are calculated again and used as new adaptation rates, and the average adaptation rates of the plurality of substations are calculated,

[0036] The average adaptation rate is the average of the adaptation rates of several resource configuration models.

[0037] Further, the average adaptation rate is compared with the average adaptation rate threshold,

[0038] The average adaptation rate threshold is the lowest standard of the average values ​​of the adaptation rates of several resource configuration models.

[0039] Further, when the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted.

[0040] Furthermore, the adjusted resource allocation models are sorted from high to low according to the adaptation rate, and the resource allocation models are matched with the sub-samples according to a number of indicators.

[0041] Compared with the prior art, the present invention divides the power network nodes into several substations according to system data, obtains the electric energy data stored in each power network node, and the main station reads several electric energy data as training samples, divides them into several subsamples according to a preset sampling rate, trains several resource configuration models respectively, verifies the training results, determines the adaptation rate of each resource configuration model, compares them with the adaptation rate, obtains the corresponding adaptation comparison results, determines the average adaptation rate of several substations, and compares them with the average adaptation rate threshold. When the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted. By adjusting the sampling rate in real time, the problem of incorrect matching of power resources and power consumption is effectively solved, the accuracy of power system resource configuration is improved, and power regulation achieves dynamic balance.

[0042] Furthermore, by taking a number of electric energy data as training samples and sorting them according to a number of indicators, the sub-samples are matched with the resource allocation model, and the adaptation rate of the resource allocation model to each sub-sample is obtained, after the verification is completed, the resource allocation model with a higher adaptation rate is selected, which can improve the targeting of the sub-samples, thereby effectively saving the training time of the resource allocation model.

[0043] Furthermore, by determining the adaptation rate of the resource configuration model, the configuration capability of the resource configuration model is judged. After the judgment is completed, the configuration capability of the resource configuration model for power resources can be quickly determined, thereby effectively improving the accuracy of the configuration of multiple types of energy storage resources.

[0044] Furthermore, by setting a timer in the resource configuration model and polling the adaptation status of the resource configuration model at fixed intervals, real-time monitoring of the adaptation rate is achieved, thereby improving the efficiency of power resource configuration.

[0045] Furthermore, by setting the adaptation rate threshold and the average adaptation rate threshold, the resource allocation model is adjusted to achieve real-time adjustment of power regulation.

[0046] Furthermore, by adjusting the sampling rate of the resource allocation model, the resource allocation model is optimized, making power regulation more precise.

[0047] Furthermore, by sorting the resource configuration models after the second adjustment from high to low according to the pass rate and corresponding the resource configuration models to the sub-samples, real-time adjustment of the resource configuration model is achieved, so that the resource configuration model can quickly adapt to the problems of the corresponding labels, thereby reducing errors in power configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of a method for configuring multiple types of energy storage resources for a new power system according to the present invention;

[0049] Figure 2 A flow chart for adjusting the sampling rate of the present invention;

[0050] Figure 3 A flow chart of collecting electric energy data of several substations according to the present invention;

[0051] Figure 4 The present invention is a flow chart for determining the adaptation rate of a single resource configuration model. DETAILED DESCRIPTION

[0052] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0054] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is only for description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0055] In addition, it should be noted that in the description of the present invention, 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 those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] See also Figure 1 As shown, it is a flow chart of a method for configuring multiple types of energy storage resources for a new power system according to the present invention, including:

[0057] Step S1, dividing the power network nodes into a number of substations according to system data, and obtaining the power data stored in each power network node;

[0058] Step S2, the master station reads a number of electric energy data, uses the electric energy data as training samples, and divides them into a number of sub-samples according to a preset sampling rate;

[0059] Step S3, using the sub-samples to train the resource allocation models respectively, and using the sub-samples to verify the training results;

[0060] Step S4, determining the adaptation rate of each resource configuration model according to the verification result;

[0061] See also Figure 2 As shown, it is a flow chart of adjusting the sampling rate of the present invention, including:

[0062] Step S41, setting an adaptation rate threshold, and comparing the adaptation rate of each resource configuration model with the adaptation rate threshold, and obtaining a corresponding adaptation comparison result;

[0063] Step S42, determining the average adaptation rate of several substations according to the adaptation comparison result;

[0064] Step S43, comparing the average adaptation rate with the average adaptation rate threshold;

[0065] Step S44, when the average adaptation rate is less than the average adaptation rate threshold, adjusting the sampling rate of the resource configuration model;

[0066] Among them, power data includes peak power consumption time, power storage surplus, equipment temperature, and power consumption;

[0067] The adaptation rate is the proportion of training results that are the same as the training results in the sub-samples after training with the resource allocation model and obtaining the training results;

[0068] The sampling rate is related to the recognition ability of the resource configuration model.

[0069] In specific implementation, energy storage resource types include hydropower generation, wind power generation, solar power generation, tidal power generation, etc.

[0070] By dividing the power network nodes into several substations according to the system data, the electric energy data stored in each power network node is obtained, the main station reads several electric energy data as training samples, and divides them into several subsamples according to the preset sampling rate. Several resource configuration models are trained respectively, and the training results are verified. The adaptation rate of each resource configuration model is determined, compared with the adaptation rate, and the corresponding adaptation comparison results are obtained. The average adaptation rate of several substations is determined and compared with the average adaptation rate threshold. When the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted. By adjusting the sampling rate in real time, the problem of incorrect matching of power resources and power consumption is effectively solved, the accuracy of power system resource allocation is improved, and power regulation achieves dynamic balance.

[0071] See also Figure 3 As shown, it is a flow chart of collecting electric energy data of several substations according to the present invention, including:

[0072] Step St1, several substations send summary instructions to corresponding electric energy meters;

[0073] Step St2, the electric energy data stored in the electric energy meter is aggregated to the corresponding collection device through the interface;

[0074] Step St3, the collection device sends the power data to the master station;

[0075] Among them, the electric energy meter reads the electric energy data from the corresponding collection device according to the summary instruction.

[0076] Specifically, the master station reads a number of electric energy data and divides the electric energy data into a number of sub-samples according to a preset sampling rate;

[0077] When dividing several sub-samples, several electric energy data are used as training samples and sorted according to several indicators.

[0078] The indicators include peak power consumption time, power storage margin, device temperature and / or power consumption of each power data in the training sample.

[0079] Embodiment 1: When sorting subsamples, if the remaining power of sample A is 1000 kwh, the remaining power of sample B is 2000 kwh, and the remaining power of sample C is 5000 kwh, the samples are sorted as sample A, sample B, and sample C.

[0080] Example 2: When sorting subsamples, if the peak electricity consumption time of sample A is 18:00, the peak electricity consumption time of sample B is 18:10, and the peak electricity consumption time of sample C is 18:30, then the samples are sorted into sample A, sample B, and sample C.

[0081] Example 3: When sorting sub-samples, if the device temperature of sample A is 36° C., the device temperature of sample B is 37° C., and the device temperature of sample C is 38° C., the samples are sorted into sample A, sample B, and sample C.

[0082] By taking several electric energy data as training samples and sorting them according to several indicators, matching the sub-samples with the resource allocation model, and obtaining the adaptation rate of the resource allocation model for each sub-sample, after completing the verification, the resource allocation model with a higher adaptation rate is selected, which can improve the targeting of the sub-samples and effectively save the training time of the resource allocation model.

[0083] See also Figure 4 As shown, it is a flow chart of determining the adaptation rate of a single resource configuration model in the present invention, including:

[0084] Step Sp1, corresponding to each sub-sample received by a single resource configuration model;

[0085] Step Sp2, polling the verification results in the corresponding resource configuration model and calculating the adaptation rate of the resource configuration model;

[0086] Step Sp3, when the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, the sampling rate of the corresponding resource configuration model is adjusted;

[0087] Step Sp4, collecting the adaptation rates of several resource configuration models again and using them as new adaptation rates;

[0088] Wherein, a timer is provided in the resource configuration model for polling the verification result of the resource configuration model at fixed intervals.

[0089] Embodiment 4: The fixed time is 0.1s. The verification results in the resource configuration model are polled at 0.1s, and the adaptation rate of the resource configuration model is monitored to be 80%. The verification results in the resource configuration model are polled at 0.2s, and the adaptation rate of the resource configuration model is monitored to be 75%. The verification results in the resource configuration model are polled at 0.3s, and the adaptation rate of the resource configuration model is monitored to be 85%. The verification results in the resource configuration model are polled at 0.4s, and the adaptation rate of the resource configuration model is monitored to be 80%.

[0090] Example 5: The fixed time is 0.5s. The verification results in the resource configuration model are polled at 0.5s, and the adaptation rate of the resource configuration model is monitored to be 82%. The verification results in the resource configuration model are polled at 1.0s, and the adaptation rate of the resource configuration model is monitored to be 75%. The verification results in the resource configuration model are polled at 1.5s, and the adaptation rate of the resource configuration model is monitored to be 84%. The verification results in the resource configuration model are polled at 2.0s, and the adaptation rate of the resource configuration model is monitored to be 86%.

[0091] By determining the adaptation rate of the resource configuration model, the configuration capability of the resource configuration model is judged. After the judgment is completed, the configuration capability of the resource configuration model for power resources can be quickly determined, thereby effectively improving the accuracy of the configuration of multiple types of energy storage resources.

[0092] By setting a timer in the resource configuration model and polling the adaptation status of the resource configuration model at fixed intervals, real-time monitoring of the adaptation rate is achieved, thereby improving the efficiency of power resource configuration.

[0093] By adjusting the sampling rate of the resource allocation model, the resource allocation model is optimized, making power regulation more precise.

[0094] Specifically, the adaptation rate is compared with the adaptation rate threshold to obtain the corresponding adaptation comparison result.

[0095] Among them, the adaptation rate threshold is the minimum standard of the adaptation rate of a single resource configuration model.

[0096] Specifically, when the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, the duration of the corresponding interface is adjusted.

[0097] Example 6: If the adaptation rate threshold is 80%, the interface duration is 1 second, and the adaptation rate is monitored to be 75%, which is less than the adaptation rate threshold, the duration of the corresponding interface is adjusted to 1.5 seconds.

[0098] Specifically, the adaptation rates of several resource configuration models are calculated again and used as new adaptation rates. The average adaptation rates of several substations are calculated.

[0099] The average adaptation rate is the average of the adaptation rates of several resource configuration models.

[0100] Example 7: If there are four resource configuration models A, B, C, and D, the adaptation rate of model A is 80%, the adaptation rate of model B is 70%, the adaptation rate of model C is 90%, and the adaptation rate of model D is 80%, then the average adaptation rate is 80%.

[0101] Specifically, the average adaptation rate is compared with the average adaptation rate threshold.

[0102] The average adaptation rate threshold is the minimum standard of the average values ​​of the adaptation rates of several resource configuration models.

[0103] Specifically, when the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted.

[0104] Embodiment 8: If the average adaptation rate threshold is 80%, the sampling rate of the resource configuration model is 1.5, and the average adaptation rate is monitored to be 75%, the sampling rate of the resource configuration model is adjusted to 2.

[0105] By setting the adaptation rate threshold and the average adaptation rate threshold, the resource allocation model is adjusted to achieve real-time adjustment of power regulation.

[0106] Specifically, the adjusted resource allocation models are sorted from high to low according to the adaptation rate, and the resource allocation models are matched with sub-samples according to several indicators.

[0107] By sorting the resource configuration models after the second adjustment from high to low according to the pass rate and corresponding the resource configuration models to the sub-samples, real-time adjustment of the resource configuration model is achieved, so that the resource configuration model can quickly adapt to the corresponding label problems, thereby reducing errors in power configuration.

[0108] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multi-type energy storage resource configuration method for a new power system, characterized in that: include: Divide the power network nodes into several substations according to the system data, and obtain the power data stored in each power network node; Using the master station to read some of the electric energy data, using the electric energy data as training samples, and dividing the electric energy data into a plurality of sub-samples according to a preset sampling rate; Using the sub-samples to train a plurality of resource allocation models respectively, and using the sub-samples to verify the training results; Determine the adaptation rate of each resource configuration model based on the verification results. include, Setting an adaptation rate threshold, comparing the adaptation rate of each resource configuration model with the adaptation rate threshold, and obtaining a corresponding adaptation comparison result; comparing the average fitness rate with an average fitness rate threshold; When the average adaptation rate is less than the average adaptation rate threshold, adjusting the sampling rate of the resource configuration model; The step of determining the adaptation rate of a single resource configuration model includes: Corresponding to each sub-sample received by the single resource configuration model; Polling the verification result in the corresponding resource configuration model, and calculating the adaptation rate of the resource configuration model; When the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, adjusting the sampling rate of the corresponding resource configuration model; Collecting the adaptation rates of the resource configuration models again and using them as new adaptation rates; A timer is provided in the resource configuration model for polling the verification result of the resource configuration model at fixed intervals; recalculating the adaptation rates of the plurality of resource configuration models and using them as new adaptation rates, and calculating the average adaptation rates of the plurality of substations, The average adaptation rate is the average of the adaptation rates of several resource configuration models; The power data includes peak power consumption time, power storage surplus, equipment temperature, and power consumption; The adaptation rate is the proportion of the training results that are the same as the training results in the sub-samples after training is performed using the resource configuration model and the training results are obtained; The sampling rate is related to the recognition capability of the resource configuration model.

2. The multi-type energy storage resource configuration method for a new power system according to claim 1 is characterized in that: The step of collecting the electric energy data of the plurality of substations comprises: The plurality of substations send summary instructions to corresponding electric energy meters; The electric energy data stored in the electric energy meter is aggregated to the corresponding collection device through an interface; The collection device sends the electric energy data to the master station; The electric energy meter obtains the electric energy data from the corresponding collection device according to the summary instruction.

3. The multi-type energy storage resource configuration method for a new power system according to claim 2 is characterized in that: Using a master station to read a number of the electric energy data, and dividing the electric energy data into a number of the sub-samples according to a preset sampling rate; When dividing the sub-samples, the electric energy data are sorted as the training samples according to the indicators. The indicators include the remaining amount of the electric energy data, peak power consumption time, equipment temperature and / or power consumption.

4. The multi-type energy storage resource configuration method for a new power system according to claim 3 is characterized in that: Compare the adaptation rate with the adaptation rate threshold to obtain the corresponding adaptation comparison result, The adaptation rate threshold is the minimum standard of the adaptation rate of a single resource configuration model.

5. The multi-type energy storage resource configuration method for a new power system according to claim 4 is characterized in that: When the adaptation rate of a single resource configuration model is lower than the adaptation rate threshold, the duration of the corresponding interface is adjusted.

6. The multi-type energy storage resource configuration method for a new power system according to claim 5 is characterized in that: comparing the average adaptation rate with the average adaptation rate threshold, The average adaptation rate threshold is the lowest standard of the average values ​​of the adaptation rates of several resource configuration models.

7. The multi-type energy storage resource configuration method for a new power system according to claim 6 is characterized in that: When the average adaptation rate is less than the average adaptation rate threshold, the sampling rate of the resource configuration model is adjusted.

8. The multi-type energy storage resource configuration method for a new power system according to claim 7 is characterized in that: The adjusted resource allocation models are sorted from high to low according to the adaptation rate, and the resource allocation models are matched with the sub-samples according to a number of indicators.

Images