Multi-element novel energy storage aggregation control method based on two-stage collaborative architecture

Abstract

The invention discloses a multi-element novel energy storage aggregation control method based on a two-stage collaborative architecture, and belongs to the technical field of electric energy storage systems, and the method comprises the following steps: 1, building an acquisition system, an energy storage system, a provincial and regional two-stage collaborative novel energy storage coordinated active control system, and a reactive voltage control system considering novel energy storage; 2, performing data acquisition on each provincial power grid energy base in the energy storage system by using an acquisition system; according to the method, the regional adjustment deviation conditions of a plurality of provincial power grid new energy large-base control areas are combined, the regional power grid new energy large-base aggregation control areas are constructed, the complementarity of wide-area new energy fluctuation can be fully utilized to reduce the overall adjustment requirement, adjustment resources such as thermal power and novel energy storage are optimally called, and the overall adjustment requirement of the regional power grid new energy large-base aggregation control areas is met. Therefore, the power grid operation efficiency and the safe and stable operation capability of the power grid are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of electric energy storage systems, and specifically, relates to a novel multi-element energy storage aggregation control method based on a two-level collaborative architecture. Background Art

[0002] At present, large energy bases mainly operate in independent control areas, and each base automatically smoothes out wind and solar power output fluctuations through supporting thermal power to ensure stable DC power transmission. At the same time, in multi-site energy storage systems, coordinated scheduling is needed to achieve optimal utilization and flexible scheduling of energy storage resources, which includes methods and systems for coordinated management of energy transmission and storage status between multiple energy storage sites.

[0003] However, the dispatching and control methods in the prior art still have certain deficiencies. During the control operation process, there is a lack of knowledge on how to obtain the total power supply demand of each power grid served by the multi-site energy storage system in the future time interval. As a result, at the energy storage distribution end, it is impossible to determine the number of energy storage sites that the multi-site energy storage system will use to supply power to each power grid in the future time interval, that is, the number of energy storage sites that provide discharge operations for each power grid. Naturally, it is impossible to determine the number of remaining energy storage sites that can enter the charging state, which makes the multi-site energy storage system in a disordered management mode before the future time interval arrives. The dispatching operation of the dispatching control system needs to be further diversified and efficient. Summary of the invention

[0004] In order to solve the above problems and technical defects, the embodiment of the present application adopts the following technical solution, a multi-element new energy storage aggregation control method based on a two-level collaborative architecture, and the steps are as follows:

[0005] Step 1: Establish an active power control system that coordinates the acquisition system, energy storage system, provincial and local new energy storage, and a reactive voltage control system that takes into account the new energy storage;

[0006] Step 2: Use the data collection system to collect data from each provincial power grid energy base in the energy storage system to obtain power data;

[0007] Step 3: Transmitting the power data to the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive voltage control system taking into account the new energy storage, and the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive voltage control system taking into account the new energy storage perform aggregate analysis on the power data to obtain aggregate analysis values;

[0008] Step 4: Reversely transmit the aggregated analysis values ​​to the active power control system coordinated by the new energy storage at the provincial and local levels. The active power control system coordinated by the new energy storage at the provincial and local levels determines the regulating power of the regional power grid energy according to the aggregated analysis values, and performs active power control with the new energy storage in the control area of ​​each large new energy base.

[0009] Preferably, the provincial and local two-level coordinated new energy storage coordinated active control system includes a coordinated dispatching module, and the coordinated dispatching module includes:

[0010] An energy storage detection module is connected to the acquisition system and is used to obtain the number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid. The obtained number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid are output as multiple configuration data corresponding to the two-level energy storage system;

[0011] A network reconstruction mechanism, used for performing multiple training on the deep neural network to obtain a deep neural network after multiple training, and outputting the deep neural network after multiple training as an intelligent prediction model, wherein the number of training times of the intelligent prediction model is positively correlated with the number of energy storage sites in the two-level energy storage system;

[0012] The prediction execution mechanism is connected to the acquisition system, the energy storage system and the network reconstruction mechanism respectively, and is used to adopt the intelligent prediction model to intelligently predict the total amount of electricity and energy consumed by each power grid in the current time interval based on the set time limit, multiple copies of electricity consumption information corresponding to multiple historical time intervals of each power grid that are the same as the current time interval, and multiple configuration data corresponding to the energy storage system, and output the total amount of electricity and energy consumed by each power grid in the current time interval as the predicted total amount of electricity consumption;

[0013] The content conversion mechanism is connected to the prediction execution mechanism and is used to determine the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the predicted total power consumption and the charging power extreme value of a single energy storage site.

[0014] Furthermore, the data collected by the collection system in step 2 includes: the actual power and planned value of thermal power, hydropower and DC lines, and the actual power and actual charge state of the new energy storage.

[0015] Preferably, multiple sets of electricity consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each power grid served by the two-level energy storage system composed of multiple energy storage sites are obtained, including: multiple historical time intervals are the same as any time interval in the current time interval in the single day in which they are located and have the same duration, and are all within the set time limit; the electricity consumption information corresponding to a single historical time interval that is the same as the current time interval on a certain day in the past includes the peak value of electricity consumption, the valley value of electricity consumption, and the total amount of electricity consumption of each power grid in the single historical time interval.

[0016] Furthermore, the obtaining of the number of energy storage sites in the two-level energy storage system, the charging energy extreme value of a single energy storage site, the number of each power grid and the total number of accumulated load devices in each power grid includes: the multiple energy storage sites in the two-level energy storage system have the same structure.

[0017] Furthermore, the deep neural network is trained multiple times to obtain a deep neural network after multiple trainings, and outputs it as an intelligent prediction model, including: in each training of the deep neural network, using the known peak power consumption of each of the power grids in a past time interval as a single output parameter of the deep neural network, setting a time limit, multiple power consumption information corresponding to multiple historical time intervals that are the same as a past time interval in the past multiple days before the date of a past time interval, and multiple configuration data corresponding to the two-level energy storage system as multiple input parameters of the deep neural network to perform this training.

[0018] Furthermore, the intelligent prediction model is used to intelligently predict the total amount of electric energy consumed by each electric power grid in the current time interval based on a set time limit, multiple copies of electric power consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system, and outputs the predicted total amount of electric energy, including: inputting the set time limit, multiple copies of electric power consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system into the intelligent prediction model in parallel.

[0019] Still further, the determining the number of energy storage sites that need to be configured for each power grid for discharge within the current time interval based on the predicted total power consumption and the charging energy extreme value of a single energy storage site includes: determining the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the integer division result of the predicted total power consumption divided by the charging energy extreme value of a single energy storage site.

[0020] Compared with the prior art, the beneficial effects of the embodiments of the present application are:

[0021] (1) This application is based on the electricity consumption information of each power grid served by a multi-site energy storage system composed of multiple energy storage sites during the same time period of each past day and multiple configuration data corresponding to the multi-site energy storage system to intelligently predict the total electricity consumption of each power grid during the same time period of the day, thereby providing key data for determining the charging and discharging strategy of each energy storage site in the multi-site energy storage system; at the same time, this application combines the regional regulation deviation of multiple provincial power grid new energy base control areas, and by constructing a regional power grid new energy base aggregation control area, it can fully utilize the complementarity of wide-area new energy fluctuations to reduce the overall regulation demand, and optimize the use of regulation resources such as thermal power and new energy storage, thereby improving the power grid operation efficiency and enhancing the safe and stable operation capability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In the attached picture:

[0023] Figure 1 This is a system flow chart of an embodiment of the present application;

[0024] Figure 2 It is a structural diagram of the active control system of the new energy storage coordination between the provincial and local levels in the embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Example

[0027] like Figure 1 , Figure 2 As shown in the figure, the multi-element new energy storage aggregation control method based on the two-level collaborative architecture has the following steps:

[0028] Step 1: Establish an active power control system that coordinates the acquisition system, energy storage system, provincial and local new energy storage, and a reactive voltage control system that takes into account the new energy storage;

[0029] Step 2: Use the data collection system to collect data from each provincial power grid energy base in the energy storage system to obtain power data;

[0030] Step 3: Transmitting the power data to the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive power voltage control system taking into account the new energy storage, and the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive power voltage control system taking into account the new energy storage perform aggregate analysis on the power data to obtain aggregate analysis values;

[0031] Step 4: The aggregated analysis values ​​are transmitted back to the active power control system coordinated by the new energy storage at the provincial and local levels. The active power control system coordinated by the new energy storage at the provincial and local levels determines the regulating power of the regional power grid energy according to the aggregated analysis values, and performs active power control with the new energy storage in the control area of ​​each large new energy base.

[0032] The active control system for the coordinated new energy storage system at the provincial and local levels includes a coordinated dispatching module, which includes:

[0033] The energy storage detection module is connected to the acquisition system and is used to obtain the number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid. The obtained number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid are output as multiple configuration data corresponding to the two-level energy storage system;

[0034] A network reconstruction mechanism is used to perform multiple training on the deep neural network to obtain a deep neural network after multiple training, and output the deep neural network after multiple training as an intelligent prediction model, and the number of training times of the intelligent prediction model is positively correlated with the number of energy storage sites in the two-level energy storage system;

[0035] The prediction execution mechanism is connected to the collection system, the energy storage system and the network reconstruction mechanism respectively, and is used to adopt an intelligent prediction model to intelligently predict the total amount of electricity and energy consumed by each power grid in the current time interval based on the set time limit, multiple copies of electricity consumption information corresponding to multiple historical time intervals of each power grid that are the same as the current time interval, and multiple configuration data corresponding to the energy storage system, and output the total amount of electricity and energy consumed by each power grid in the current time interval as the predicted total amount of electricity consumption;

[0036] The content conversion mechanism is connected to the prediction execution mechanism and is used to determine the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the predicted total power consumption and the charging power extreme value of a single energy storage site.

[0037] The data collected by the collection system in step 2 include: the actual power and planned values ​​of thermal power, hydropower and DC lines, as well as the actual power and actual charge state of new energy storage.

[0038] The multiple sets of electricity consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each power grid served by the two-level energy storage system composed of multiple energy storage sites are obtained, including: the multiple historical time intervals are the same as any time interval in the current time interval in the single day in which they are located and the duration is equal, and all are within the set time limit; the electricity consumption information corresponding to a single historical time interval that is the same as the current time interval on a certain day in the past for each power grid includes the peak value of electricity consumption, the valley value of electricity consumption, and the total amount of electricity consumption of each power grid in the single historical time interval.

[0039] Obtaining the number of energy storage sites in the two-level energy storage system, the charging energy extreme value of a single energy storage site, the number of each power grid and the total number of accumulated load devices in each power grid includes: multiple energy storage sites in the two-level energy storage system have the same structure.

[0040] The deep neural network is trained multiple times to obtain a deep neural network after multiple trainings, and the output as an intelligent prediction model includes: in each training of the deep neural network, the known peak power consumption of each power grid in a past time interval is used as a single output parameter of the deep neural network, and a set time limit, multiple power consumption information corresponding to multiple historical time intervals that are the same as a past time interval in the past multiple days before a date of a past time interval, and multiple configuration data corresponding to the two-level energy storage system are used as multiple input parameters of the deep neural network to perform this training.

[0041] An intelligent prediction model is adopted to intelligently predict the total amount of electric energy consumed by each electric power grid in the current time interval based on a set time limit, multiple copies of electric power consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system. The output as the predicted total amount of electric energy consumption includes: inputting the set time limit, multiple copies of electric power consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system into the intelligent prediction model in parallel.

[0042] Determining the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the predicted total electricity consumption and the charging energy extreme value of a single energy storage site includes: determining the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the integer division result of the predicted total electricity consumption divided by the charging energy extreme value of a single energy storage site.

[0043] This application is based on the electricity consumption information of each power grid in the same time period of the past days served by a multi-site energy storage system composed of multiple energy storage sites and multiple configuration data corresponding to the multi-site energy storage system to intelligently predict the total electricity consumption of each power grid in the same time period of the day, thereby providing key data for determining the charging and discharging strategies of each energy storage site in the multi-site energy storage system; at the same time, this application combines the regional regulation deviations of multiple provincial power grid new energy base control areas, and by constructing a regional power grid new energy base aggregation control area, it can make full use of the complementarity of wide-area new energy fluctuations to reduce the overall regulation demand, and optimize the call of regulation resources such as thermal power and new energy storage, thereby improving the power grid operation efficiency and enhancing the safe and stable operation capabilities of the power grid.

[0044] The above-mentioned embodiments only express the preferred implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for ordinary technicians in this field, several modifications, improvements and substitutions can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A new multi-element energy storage aggregation control method based on a two-level collaborative architecture, characterized in that: Here are the steps: Step 1: Establish an active power control system that coordinates the acquisition system, energy storage system, provincial and local new energy storage, and a reactive voltage control system that takes into account the new energy storage; Step 2: Use the data collection system to collect data from each provincial power grid energy base in the energy storage system to obtain power data; Step 3: Transmitting the power data to the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive voltage control system taking into account the new energy storage, and the active power control system coordinated by the provincial and local levels with the new energy storage and the reactive voltage control system taking into account the new energy storage perform aggregate analysis on the power data to obtain aggregate analysis values; Step 4: Reversely transmit the aggregated analysis values ​​to the active power control system coordinated by the new energy storage at the provincial and local levels. The active power control system coordinated by the new energy storage at the provincial and local levels determines the regulating power of the regional power grid energy according to the aggregated analysis values, and performs active power control with the new energy storage in the control area of ​​each large new energy base.

2. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 1 is characterized in that: The provincial and local coordinated new energy storage coordinated active control system includes a coordinated dispatching module, and the coordinated dispatching module includes: An energy storage detection module is connected to the acquisition system and is used to obtain the number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid. The obtained number of energy bases in the two-level energy storage system, the charging energy extreme value of a single energy base, the number of each power grid, and the total number of accumulated load devices in each power grid are output as multiple configuration data corresponding to the two-level energy storage system; A network reconstruction mechanism, used for performing multiple training on the deep neural network to obtain a deep neural network after multiple training, and outputting the deep neural network after multiple training as an intelligent prediction model, wherein the number of training times of the intelligent prediction model is positively correlated with the number of energy storage sites in the two-level energy storage system; The prediction execution mechanism is connected to the acquisition system, the energy storage system and the network reconstruction mechanism respectively, and is used to adopt the intelligent prediction model to intelligently predict the total amount of electricity and energy consumed by each power grid in the current time interval based on the set time limit, multiple copies of electricity consumption information corresponding to multiple historical time intervals of each power grid that are the same as the current time interval, and multiple configuration data corresponding to the energy storage system, and output the total amount of electricity and energy consumed by each power grid in the current time interval as the predicted total amount of electricity consumption; The content conversion mechanism is connected to the prediction execution mechanism and is used to determine the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the predicted total power consumption and the charging power extreme value of a single energy storage site.

3. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 1 is characterized in that: The data collected by the collection system in step 2 include: the actual power and planned value of thermal power, hydropower and DC lines, and the actual power and actual charge state of the new energy storage.

4. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 2 is characterized in that: Acquire multiple sets of electricity consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each power grid served by the two-level energy storage system composed of multiple energy storage sites, including: multiple historical time intervals have the same time position and equal duration as any time interval in the current time interval within the single day in which they are located, and are all within the set time limit; the electricity consumption information corresponding to a single historical time interval that is the same as the current time interval on a certain day in the past for each power grid includes the peak value of electricity consumption, the valley value of electricity consumption, and the total amount of electricity consumption of each power grid in the single historical time interval.

5. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 4 is characterized in that: The method of obtaining the number of energy storage sites in the two-level energy storage system, the charging energy extreme value of a single energy storage site, the number of each power grid and the total number of accumulated load devices in each power grid includes: multiple energy storage sites in the two-level energy storage system have the same structure.

6. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 5 is characterized in that: The method of performing multiple trainings on the deep neural network to obtain the deep neural network after multiple trainings and outputting it as an intelligent prediction model includes: in each training of the deep neural network, using the known peak power consumption of each power grid in a past time interval as a single output parameter of the deep neural network, setting a time limit, multiple power consumption information corresponding to multiple historical time intervals that are the same as a past time interval in the past multiple days before the date of a past time interval, and multiple configuration data corresponding to the two-level energy storage system as multiple input parameters of the deep neural network to perform this training.

7. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 6 is characterized in that: The intelligent prediction model is used to intelligently predict the total amount of electric energy consumed by each electric power grid in the current time interval based on a set time limit, multiple copies of electricity consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system, and outputs the predicted total amount of electric energy, including: inputting the set time limit, multiple copies of electricity consumption information corresponding to multiple historical time intervals that are the same as the current time interval in the past multiple days for each electric power grid, and multiple configuration data corresponding to the two-level energy storage system into the intelligent prediction model in parallel.

8. The multi-element new energy storage aggregation control method based on a two-level collaborative architecture according to claim 7 is characterized in that: The method of determining the number of energy storage sites that need to be configured for each power grid and used for discharge within the current time interval based on the predicted total power consumption and the charging energy extreme value of a single energy storage site includes: determining the number of energy storage sites that need to be configured for each power grid and the number of energy storage sites for discharge within the current time interval based on the integer division result of the predicted total power consumption divided by the charging energy extreme value of a single energy storage site.

Images