Microgrid secondary system networking based on elastic matching and regulation and control method thereof

Through the microgrid secondary system networking method based on elastic matching, the oscillation problem of the microgrid when facing constant power load and networking mode changes is solved, the system is flexible networking and stable control is realized, and the energy consumption is improved. Optimization of elasticity and power costs.

CN118920566AActive Publication Date: 2024-11-08NARI NANJING CONTROL SYSTEM CO LTD +4
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202410931593.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-08
Estimated Expiration
2044-07-12

AI Technical Summary

Technical Problem

When the microgrid faces a large number of constant power load access and the working state switching under different networking modes, the system oscillation and voltage fluctuations are prone to occur, affecting stable operation.

Method used

Using the microgrid secondary system networking method based on elastic matching, including information acquisition layer, optimization scheduling layer, module control layer and information feedback layer, the elastic metric is corrected through the neural network prediction model, and the charging and discharging strategy of the energy storage system is optimized to realize Flexible networking and stable control of the system.

Benefits of technology

It improves the operating control reliability of the microgrid, realizes elasticity of energy consumption and minimizes power costs, and stabilizes the system's power demand and voltage balance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118920566A_ABST
    Figure CN118920566A_ABST
Patent Text Reader

Abstract

The invention discloses a micro-grid secondary system networking based on elastic matching and a regulation and control method thereof. The method comprises the following steps: collecting system data in real time; according to the collected system data, taking the minimum total cost and elasticity measurement as targets, obtaining a matching combination of the micro-grid power distribution quantity under the constraint of constraint conditions, and formulating an optimization scheduling instruction according to the obtained matching combination; executing the optimization scheduling instruction; feeding back the system state after the optimization scheduling instruction is executed; and according to the feedback system state, the elasticity measurement in the elasticity matching is optimized and corrected through the neural network prediction model. Flexible networking is carried out based on the elasticity measurement corrected by the neural network, and the elasticity measurement is adopted to carry out combination optimization coordination control on controllable distributed power supplies, energy storage devices and the like in different modules, so that energy consumption elasticity and power cost minimization are realized while flexible networking of the micro-grid secondary system is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to flexible networking of a microgrid, and in particular to a microgrid secondary system networking and a control method thereof based on elastic matching. Background Art

[0002] The microgrid secondary system is the power distribution and control system within the microgrid. It is used to manage tasks such as energy flow, power load scheduling, voltage and frequency control within the microgrid. It is usually composed of components such as inverters, distribution equipment, battery energy storage systems, and intelligent controllers. It can monitor, control and optimize various equipment within the microgrid. Compared with distributed power generation technology, the advantages of microgrids are more prominent. It can improve the power supply reliability of the power system while realizing coordinated interaction between sources, grids and loads, and multi-energy complementarity between distributed energy sources, increase the distribution network's ability to absorb distributed power sources, and improve the utilization rate of clean energy. However, the access of a large number of constant power loads will affect the stable operation of the microgrid. The switching of the working state of the networking device in different modes will also bring intermittent and random disturbances to the system. Various unstable factors in the system may cause the bus voltage to fluctuate at the critical point of the voltage range, exacerbating the system oscillation. Summary of the invention

[0003] Purpose of the invention: In view of the above shortcomings, the present invention provides a microgrid secondary system networking based on elastic matching, which can improve the reliability of microgrid operation control, realize energy consumption flexibility and minimize electricity costs.

[0004] The present invention also provides a control method for microgrid secondary system networking based on elastic matching.

[0005] Technical solution: To solve the above problems, the present invention adopts a microgrid secondary system networking based on elastic matching, including:

[0006] Information collection layer, used to collect system data in real time;

[0007] The optimization scheduling layer is used to obtain the matching combination of microgrid power distribution under the constraints of constraints based on the collected system data, with the goal of minimizing the total cost and elasticity metric, and formulate the optimization scheduling instructions based on the obtained matching combination; the microgrid power distribution includes the purchase of additional power, the charging power of the energy storage system, and the discharge power of the energy storage system; the elasticity metric includes the supply elasticity that reflects the response ability of distributed energy to changes in environmental conditions, the load balancing elasticity that reflects the balancing ability of the system under load changes, and the demand response elasticity that reflects the degree of user response to changes in electricity prices;

[0008] Module control layer, used to execute optimization scheduling instructions;

[0009] Information feedback layer, used to feedback the system status after executing the optimization scheduling instructions;

[0010] The parameter optimization layer is used to modify the elasticity metric through the neural network prediction model according to the feedback system status.

[0011] Furthermore, the information collection layer includes an operation monitoring data acquisition module and a microgrid comprehensive monitoring index calculation module;

[0012] The operation monitoring data acquisition module is used to collect the operation monitoring parameters of the microgrid operation status in real time, specifically including: total power demand value, total power supply value, distributed power generation comprehensive energy efficiency, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, and microgrid communication equipment data;

[0013] The microgrid comprehensive monitoring index calculation module is used to calculate the microgrid comprehensive monitoring index data according to the real-time collected operation monitoring parameters, specifically including: microgrid whole network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage equipment charging and discharging efficiency stability index, key equipment working status monitoring index, and network communication reliability index.

[0014] Further, the module control layer includes: a PCC module, a microgrid AC regulation module, a microgrid AC non-adjustable module, a microgrid DC regulation module, a microgrid DC non-adjustable module and an interconnection module;

[0015] The PCC module switches the operation of the microgrid between networking and off-grid in a limited exchange power control mode;

[0016] The microgrid AC regulation module includes one or more distributed power sources, energy storage systems and grid-connected devices;

[0017] The microgrid AC non-adjustable module includes an AC load, an undispatched distributed power source and a networking device;

[0018] The microgrid DC regulation module includes an energy storage system with regulation capability and a bidirectional DC / DC chopper, which is used to control the DC bus voltage of the microgrid;

[0019] The microgrid DC non-adjustable module includes a DC load, a non-dispatched distributed power source and a grid-connected device;

[0020] The interconnection module comprises an interconnection converter, and two ends of the interconnection converter are respectively connected to the microgrid AC bus and the microgrid DC bus.

[0021] Furthermore, the parameter optimization layer uses a BO-BiGRU-Attention hybrid neural network prediction model to correct the elasticity metric, and the specific steps are as follows:

[0022] Step 51: Obtain historical data of distributed energy, historical data of charging and discharging power time series of energy storage system, historical data of total power demand of microgrid, and historical data of power demand of each user device or system in microgrid, and perform preprocessing;

[0023] Step 52: construct an initial BiGRU-Attention model, train the BiGRU-Attention model with the preprocessed data, and obtain the initial BiGRU-Attention model;

[0024] Step 53: Hyperparameter optimization: using the Bayesian optimization algorithm to optimize the learning rate, training window size, number of hidden layer neurons, and number of BiGRU layer neurons of the initial BiGRU-Attention model, and obtaining the BO-BiGRU-Attention model based on the optimized parameters of the initial BiGRU-Attention model;

[0025] Step 54: The distributed energy data, the energy storage system charging and discharging data, the total power demand data of the microgrid, and the power demand data of each user device or system in the microgrid are predicted by the BO-BiGRU-Attention model, and the elasticity metric is calculated based on the predicted data to obtain a corrected elasticity metric.

[0026] The present invention also adopts a control method for microgrid secondary system networking based on elastic matching, comprising the following steps:

[0027] Step 1: Collect system data in real time;

[0028] Step 2: Based on the collected system data, with the goal of minimizing the total cost and elasticity metric, a matching combination of microgrid power distribution is obtained under the constraints of the constraints, and an optimization dispatch instruction is formulated according to the obtained matching combination; the microgrid power distribution includes the purchase of additional power, the charging power of the energy storage system, and the discharge power of the energy storage system; the elasticity metric includes the supply elasticity that reflects the ability of distributed energy to respond to changes in environmental conditions, the load balancing elasticity that reflects the system's balancing ability under load changes, and the demand response elasticity that reflects the degree of user response to changes in electricity prices;

[0029] Step 3: Execute the optimization scheduling instruction;

[0030] Step 4: Feedback the system status after executing the optimized scheduling instruction;

[0031] Step 5: According to the feedback system status, the elasticity metric in elastic matching is corrected through the neural network prediction model;

[0032] Step 6: Formulate an optimized scheduling instruction based on the matching combination of the modified elasticity metrics, and return to execute step 3.

[0033] Furthermore, the collected system data includes total power demand value, total power supply value, distributed power generation comprehensive energy efficiency, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, microgrid communication equipment data, microgrid full network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage device charging and discharging efficiency stability index, key equipment working status monitoring index, network communication reliability index

[0034] Furthermore, taking the power balance, voltage stability, and frequency stability of the microgrid as constraints, the conjugate gradient algorithm is used to solve the optimization problem of minimizing the total cost and elasticity metric of the microgrid secondary system:

[0035]

[0036] In the formula, w c is the cost weight, w d is the demand response elasticity weight, w L is the supply elasticity weight, w s is the load balancing elastic weight, E d is the demand response elasticity, E L For load balancing elasticity, E s is the supply elasticity, C buy is the cost of purchasing additional electricity, C charge The cost of charging the energy storage system, C discharge is the cost corresponding to the energy storage system discharge, α is the ratio of the energy storage system charging power to the energy storage system discharge power, P charge is the charging power of the energy storage system, P max_charge is the maximum charging power of the energy storage system, P discharge is the discharge power of the energy storage system, P max_discharge is the maximum discharge power of the energy storage system, P renewable is the total electricity generated by renewable energy, P load is the total load demand within the microgrid, P buy The additional power purchased, V min is the minimum limit value of the voltage at each node in the microgrid, V node is the voltage of each node in the microgrid, V max is the maximum limit value of the voltage at each node in the microgrid, f min is the minimum limit value of the power frequency in the microgrid, f grid is the power frequency in the microgrid, f max It is the maximum limit value of the power frequency in the microgrid.

[0037] Furthermore, the relative position L(a) of the middle point is calculated according to the data shape tree establishment rule. i a1,a n ), and mapped to the charging power of the energy storage system and the discharging power of the energy storage system; the data shape tree establishment rules are specifically as follows:

[0038] Curve A consists of a series of sampling points (a1, a2, ..., a n ), select a point a on curve A i As the midpoint, use L(a i a1,a n ) represents point a i Relative to point a1 and point a n The position of point a i Relative to point a1 and point a n Bookstein coordinates of point a i Relative to point a1 and point a n The position L(a i a1,a n )=(a (1) ,a (2) ), where (a (1) ,a (2) ) The specific calculation formula is:

[0039]

[0040] In the formula, for a k Two-dimensional plane coordinates, k = 1, 2,…, n.

[0041] Furthermore, the BO-BiGRU-Attention hybrid neural network prediction model is used to correct the elasticity metric. The specific steps are as follows:

[0042] Step 51: Obtain historical data of distributed energy, historical data of charging and discharging power time series of energy storage system, historical data of total power demand of microgrid, and historical data of power demand of each user device or system in microgrid, and perform preprocessing;

[0043] Step 52: construct an initial BiGRU-Attention model, train the BiGRU-Attention model with the preprocessed data, and obtain the initial BiGRU-Attention model;

[0044] Step 53: Hyperparameter optimization: using the Bayesian optimization algorithm to optimize the learning rate, training window size, number of hidden layer neurons, and number of BiGRU layer neurons of the initial BiGRU-Attention model, and obtaining the BO-BiGRU-Attention model based on the optimized parameters of the initial BiGRU-Attention model;

[0045] Step 54: The distributed energy data, the energy storage system charging and discharging data, the total power demand data of the microgrid, and the power demand data of each user device or system in the microgrid are predicted by the BO-BiGRU-Attention model, and the elasticity metric is calculated based on the predicted data to obtain a corrected elasticity metric.

[0046] The present invention also adopts a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the above method when executing the computer program.

[0047] The present invention also adopts a computer-readable storage medium on which a computer program is stored, characterized in that the computer program implements the steps of the above method when executed by a processor.

[0048] Beneficial effect: Compared with the prior art, the significant advantage of the present invention is that it uses a flexible matching algorithm based on neural network correction for flexible networking. By taking the system's power demand, volatility, priority and other parameters as indicators, and stability and reliability as constraints, a flexible matching algorithm is used to combine and optimize the coordinated control of controllable distributed power sources, energy storage and other equipment in different modules, thereby achieving energy consumption flexibility and minimization of electricity costs while flexibly networking the microgrid secondary system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a technical flow chart of flexible networking of the microgrid secondary system in the present invention.

[0050] Figure 2 This is a flow chart of the elastic matching algorithm in the present invention.

[0051] Figure 3 This is a structural diagram of the functional modular microgrid in the present invention.

[0052] Figure 4 This is a structural diagram of the BO-BiGRU-Attention hybrid neural network prediction model in the present invention. DETAILED DESCRIPTION

[0053] Example 1

[0054] like Figure 1As shown, in this embodiment, a microgrid secondary system networking based on elastic matching is divided into five levels based on determining the types and control methods of each distributed power source or energy storage in the microgrid, including:

[0055] The information collection layer is used to collect system data in real time; it includes an operation monitoring data acquisition module and a microgrid comprehensive monitoring index calculation module. The operation monitoring data acquisition module is used to monitor the operation monitoring parameter data of the microgrid operation status in real time, including: total power demand value, total power supply value, distributed power generation comprehensive energy efficiency, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, and microgrid communication equipment data. The microgrid comprehensive monitoring index calculation module is used to calculate the microgrid comprehensive monitoring index data based on the real-time collected operation monitoring parameter data, including: microgrid full network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage equipment charging and discharging efficiency stability index, key equipment working status monitoring index, and network communication reliability index.

[0056] The calculation method of the microgrid's total power balance index is as follows: the total power demand value and the total power supply value of the microgrid are read at a certain time interval, and the number of readings is numbered; based on this, a model formula of the microgrid's total power balance index is constructed;

[0057] The formula of the microgrid power balance index is shown in (1):

[0058]

[0059] Where MGEL m0 is the microgrid power balance index at the m0th reading, e is a natural constant, m0 is the number of readings, m0 = 1, 2, ..., m, m is the total number of readings, ES m0 is the total power supply value read for the m0th time, ED m0 is the total power demand value read for the m0th time, and τ is the correction factor of the power balance index of the entire microgrid. By considering the total power demand and supply value of the microgrid, the index can comprehensively evaluate the power balance of the microgrid, help the system to more comprehensively understand the power status inside the microgrid, and provide basic data for optimizing power scheduling.

[0060] The specific calculation method of the distributed energy response speed index is as follows: extract the distributed power generation comprehensive energy efficiency and energy storage device efficiency of the microgrid from the operation monitoring parameter data; monitor the solar radiation intensity and wind speed at the location of the microgrid power station at regular intervals, and number the monitoring time points; construct a distributed energy response speed index model formula; the specific distributed energy response speed index model formula is shown in (2):

[0061]

[0062] Where DERSI k is the distributed energy response speed index at the kth monitoring time point, k is the number of the monitoring time point, k = 1, 2, ..., k0, k0 is the total number of monitoring time points, DEGE k Comprehensive energy efficiency for distributed generation, IL k is the sunlight intensity at the kth monitoring time point, IL0 is the unit value of sunlight intensity, σ1 is the weight coefficient of sunlight intensity for the comprehensive energy efficiency of distributed generation, WS k is the wind speed at the kth monitoring time point, WS0 is the unit value of wind speed, σ2 is the weight coefficient of wind speed for the comprehensive energy efficiency of distributed generation, λ1 is the weight coefficient of the comprehensive energy efficiency of distributed generation in the distributed energy response speed index, ESR k is the efficiency of the energy storage device, and λ2 is the weight coefficient of the energy storage device efficiency in the distributed energy response speed index. By considering multiple factors such as the comprehensive energy efficiency of distributed power generation, solar illumination intensity, and wind speed, the distributed energy response speed index can more comprehensively and comprehensively evaluate the response speed of distributed energy within the microgrid to changes in the external environment. This helps to fully understand the impact of various factors on energy in the microgrid. Introducing solar illumination intensity and wind speed and adjusting them through weight coefficients can better balance the impact of natural environmental factors in the location of the microgrid on the comprehensive energy efficiency of distributed power generation. This helps the index to more truly reflect the meteorological and geographical conditions of the area where the microgrid is located.

[0063] The specific calculation method of the energy storage device power balance index is as follows: extract the microgrid energy storage device data from the operation monitoring parameter data and number the microgrid energy storage device; monitor the charging efficiency, discharge efficiency, available power and battery capacity of the microgrid energy storage device at regular intervals; and construct the energy storage device power balance index model formula. The specific energy storage device power balance index model formula is shown in (3):

[0064]

[0065] Where, ESSEI k is the energy storage device charge balance index at the kth monitoring time point, i is the number of the microgrid energy storage device, i = 1, 2, ..., i0, i0 is the total number of microgrid energy storage devices, CE k i ,DE k i AE k i , BE ki is the charging efficiency, discharging efficiency, available power and battery capacity of the i-th microgrid energy storage device at the k-th monitoring time point, are the weights of charging efficiency, discharging efficiency, available power and battery capacity in the energy storage device power balance index, It is the correction coefficient of the energy storage device's power balance index. The introduction of factors such as charging efficiency, discharging efficiency, available power and battery capacity can more comprehensively and comprehensively consider the status of the energy storage device inside the microgrid. This helps to comprehensively reflect all aspects of the charging, discharging and energy storage processes in the energy storage device's power balance index, and improves the comprehensiveness and accuracy of the index. Considering the available power and battery capacity helps to judge the energy storage status and energy storage capacity of the energy storage device. This provides more specific reference information for the microgrid when dealing with demand peaks and grid fluctuations.

[0066] The specific calculation method of the energy storage device charging and discharging efficiency stability index is as follows: monitor the charging and discharging efficiency, energy storage device temperature, and energy storage device ambient temperature of the microgrid energy storage device at regular intervals; construct a model formula for the energy storage device charging and discharging efficiency stability index; the specific energy storage device charging and discharging efficiency stability index model formula is shown in (4):

[0067]

[0068] Where, ESESI k is the charging and discharging efficiency stability index of the energy storage device at the kth monitoring time point, CDE k is the charge and discharge efficiency at the kth monitoring time point, ESST k i is the temperature of the energy storage device of the i-th microgrid energy storage device at the k-th monitoring time point, μ1 is the weight ratio of the energy storage device temperature in the energy storage device charging and discharging efficiency stability index, ET k i is the ambient temperature of the energy storage device of the i-th microgrid energy storage device at the k-th monitoring time point, μ2 is the weight ratio of the ambient temperature of the energy storage device in the energy storage device charging and discharging efficiency stability index, It is the correction coefficient of the stability index of the energy storage device's charging and discharging efficiency. The introduction of factors such as charging and discharging efficiency, energy storage device temperature, and energy storage device ambient temperature fully considers the changes in the efficiency and temperature of the energy storage device during operation. This helps to more comprehensively and accurately evaluate the performance of energy storage devices under different conditions. The comprehensive evaluation of charging and discharging efficiency, energy storage device temperature, and energy storage device ambient temperature helps to fully understand the stability of energy storage devices under different conditions. This is of great significance for microgrid managers to formulate operation strategies and prevent potential problems.

[0069] The optimization scheduling layer adopts appropriate optimization scheduling strategies to realize resource scheduling and demand management in the networking process, with the premise of ensuring system stability and security, so as to realize efficient operation and energy optimization of microgrids. It is used to analyze and calculate the collected system data through elastic matching to obtain optimization scheduling instructions; with the lowest total cost as the goal, obtain the matching combination of elastic metrics under the constraints of constraints, and formulate optimization scheduling instructions based on the obtained matching combination or the matching combination of elastic metrics after optimization and correction; adopt elastic matching algorithm, with the system's power demand, volatility, priority and other parameters as indicators, and stability and reliability as constraints, to combine and optimize the coordinated control of controllable distributed power sources, energy storage and interconnected controllers in different modules.

[0070] The module control layer is used to execute optimization scheduling instructions; it includes various functional modules, such as Figure 2 As shown, the functional modular microgrid network includes an isolation transformer 7, an AC bus 8, a DC bus 9, an interconnection module (6), a PCC module (1), an AC microgrid regulation module (2), an AC microgrid non-regulatory module (3), a DC microgrid regulation module (4), and a DC microgrid non-regulatory module (5).

[0071] The PCC module (1) provides an external interface for the AC / DC hybrid microgrid. The right side is connected to the AC bus 8, and the other side is connected to the large power grid through the isolation transformer 7. The internal device of the module is a three-phase AC circuit breaker. The interactive power between the large power grid and the microgrid is limited by the power limit control method in this module.

[0072] The AC microgrid regulation module (2) includes four parts, namely, one or more controllable distributed power sources 10, a distributed power source grid-connected device 11, a power type energy storage system 12, and an energy storage system grid-connected device 13. The controllable distributed power source 10 is connected to the AC bus 8 through the distributed power source grid-connected device 11. The grid-connected inverter included in the distributed power source grid-connected device 11 adopts active power-AC bus frequency (Pf) droop control and reactive power-AC bus voltage (Q-Uac) droop control. The power type energy storage system 13 is connected to the AC bus 8 through the energy storage system grid-connected device 13. The grid-connected inverter included in the energy storage system grid-connected device 13 adopts PQ control.

[0073] The AC microgrid non-adjustable module (3) includes three parts: one or more uncontrollable distributed power sources 14, a distributed power grid-connected device 15, and an AC load 16. The uncontrollable distributed power source 14 is connected to the AC bus 8 through the distributed power grid-connected device 15. The AC load 16 is directly connected to the AC bus 8. The AC bus 8, the PCC module (1), the AC microgrid adjustment module (2), and the AC microgrid non-adjustable module (3) constitute an AC microgrid system.

[0074] The DC microgrid regulation module (4) includes an energy storage system 17 and a bidirectional DC / DC chopper 18. The energy storage system 17 is connected to the DC bus 9 through the grid-connected bidirectional DC / DC chopper 18. The grid-connected bidirectional DC / DC chopper adopts constant DC voltage control.

[0075] The DC microgrid non-adjustable module (5) includes three parts: one or more uncontrollable distributed power sources 19, a distributed power grid-connected device 20, and a DC load 21. The uncontrollable distributed power source 19 is connected to the DC bus 9 through the distributed power grid-connected device 20. The DC load 21 is directly connected to the DC bus 9. The DC micro bus 9, the DC microgrid adjustment module (4), and the DC microgrid non-adjustable module (5) constitute a DC microgrid system.

[0076] The two sides of the interconnection module (6) are respectively connected to the AC bus 8 and the DC bus 9, and an interconnection converter for bidirectional power exchange can be realized inside the module. The interconnection converter adopts active power-DC bus voltage (P-Udc) droop control, and can automatically participate in the regulation of the DC bus voltage Uae when the DC microgrid regulation module (4) fails to perform differential control on the DC bus voltage Udc, thereby establishing a connection between the AC microgrid and the DC microgrid.

[0077] The modular structure of AC / DC microgrid can provide a reference for the networking mode of microgrid. Because the above-mentioned different modules play different roles in the entire microgrid, different modules need to use different types of distributed power sources and energy storage systems. In the AC microgrid regulation module, a distributed power source with stable output and easy control is selected. The distributed power source should have the characteristics of stable output and easy control, such as diesel generators, internal combustion engines, wind power plants or photovoltaic power stations equipped with energy storage. The energy storage system in this module is mainly responsible for responding quickly in a short time to stabilize the system when the disturbance is large, so power-type distributed energy storage such as supercapacitor energy storage system should be selected. The DC microgrid regulation module is the key to maintaining the stability of the DC microgrid bus voltage. It is responsible for the smoothing of the active power fluctuations of the entire DC microgrid and needs to provide a long period of power support. Therefore, energy-type distributed energy storage such as battery energy storage system should be selected. If the loss caused by multi-stage power conversion is not considered, a stable and easy-to-control distributed power source can also be used instead of the energy storage system to form a DC microgrid regulation module.

[0078] To realize the multi-mode operation of the modular structure of AC / DC hybrid microgrid based on functional differences. The control type of the module control layer is distributed control, which is responsible for the internal operation control of the module; different modules reasonably allocate different control tasks according to functional differences; when it is detected that a module cannot meet the control task, coordinate the operation between modules; according to the different external characteristics of different modules, different modules are further equivalent; the PCC module is equivalent to a variable power source or load relative to the microgrid; the AC microgrid regulation module is equivalent to a voltage source with voltage and frequency changes; the DC microgrid regulation module is equivalent to a fixed voltage source in the DC microgrid self-control mode, and is equivalent to a fixed output power source or load in the interconnected module control mode; the droop control in the interconnected module can realize the natural conversion of inversion and rectification according to the DC microgrid bus voltage; the DC microgrid non-adjustable module and the AC microgrid non-adjustable module are equivalent to fixed power sources or loads; the control type of the microgrid layer control is centralized control, which is responsible for coordinating the operation of each module after judging the operating parameters of each module. The PCC module needs to determine whether the interactive power exceeds the line; the AC regulation module needs to determine whether the AC bus frequency f and voltage Uac meet the operating requirements; the DC microgrid regulation module and the interconnection module determine whether the DC bus voltage Uae meets the operating requirements. According to the above equivalent process, the microgrid layer does not need to collect and process all information such as all loads, energy storage, and distributed power sources at the same time. It only needs to determine some operating parameters based on the operating characteristics of different modules to coordinate operations between modules.

[0079] The information feedback layer is used to feedback the system status after executing the optimized scheduling instructions; the Kalman filter is used for recursive filtering to ensure accurate estimation of the system status in the presence of noise.

[0080] The parameter optimization layer is used to optimize and correct the elasticity metric in elastic matching based on the feedback system status through the BO-BiGRU-Attention hybrid neural network prediction model.

[0081] Example 2

[0082] The control method of microgrid secondary system networking based on elastic matching in this embodiment includes the following steps:

[0083] Step 1: Collect system data in real time; specifically including: total power demand value, total power supply value, comprehensive energy efficiency of distributed power generation, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, microgrid communication equipment data, microgrid full network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage equipment charging and discharging efficiency stability index, key equipment working status monitoring index, and network communication reliability index.

[0084] Step 2: Analyze and calculate the collected system data through elastic matching to obtain the optimized dispatching instructions; take the total cost, system stability and response speed as the optimal goal, obtain the matching combination of microgrid power distribution under the constraints of constraints, and formulate the optimized dispatching instructions according to the obtained matching combination; the specific steps are as follows:

[0085] Step A, data shape tree establishment:

[0086] Using an open and ordered radial curve, A represents a series of sampling points (a1, a2, ..., a n ) and select a point a on A. i As the middle point, i = (1 + n) / 2 is generally taken. i a1,a n ) means a i Relative point a1 and point a n The position of i Relative to point a1 and point a n The Bookstein coordinates of the two first and last sampling points are mapped to fixed positions to determine the coordinates in a coordinate system. Since the positions of the first and last sampling points are determined, only the Bookstein coordinates of the middle sampling point are needed to well represent the relative position relationship of the three points. Point a i Relative to point a1 and point a n Location

[0087] L(a i a1,a n )=(a (1) ,a (2) ), where (a (1) ,a (2) ) The specific calculation formula can be expressed as follows:

[0088]

[0089] In the formula, for a k (k=1, 2, ..., n) two-dimensional plane coordinates.

[0090] Step B, elasticity metric definition:

[0091] Microgrid resources: Solar energy capacity P solar , wind energy capacity P wind , the energy storage system can charge and discharge power P storage ;

[0092] Microgrid demand: Total power demand P load , and the power demand P of each user, device or system user, P device , P system ;

[0093] Supply elasticity E s :Supply elasticity measures the responsiveness of distributed energy to changes in environmental conditions (such as solar radiation, wind speed, etc.), that is, changes in power supply caused by changes in environmental conditions. The specific formula is as follows:

[0094]

[0095] Among them, ΔG is the change in power generation capacity, G is the initial power generation output, ΔE is the change in environmental conditions (such as solar radiation intensity, wind speed, etc.), and E is the initial environmental conditions.

[0096] Load Balancing Elasticity L :Load balance elasticity measures the system's ability to maintain balance under load changes, that is, the change in system state caused by load changes. The specific calculation formula is as follows:

[0097]

[0098] Among them, ΔB is the change in the system equilibrium state (such as frequency deviation, voltage deviation, etc.), B is the initial equilibrium state (such as standard frequency, standard voltage, etc.), ΔL is the load change, and L is the initial load.

[0099] Demand Response Elasticity d :Demand response elasticity measures the degree of user response to changes in electricity prices, that is, the change in electricity demand caused by changes in electricity prices. The specific formula is as follows:

[0100]

[0101] Among them, ΔD is the change in electricity demand, D is the initial electricity demand, ΔC is the change in electricity price, and C is the initial electricity price.

[0102] Step C, matching strategy design:

[0103] Step C1, calculate the total power generation of renewable energy P renewable :

[0104] P renewable =P solar +P wind (9)

[0105] Step C2, calculate the total load demand P inside the microgrid load :

[0106] P load =P user +P device +P system(10)

[0107] Step C3, determine whether the renewable energy generation is sufficient to meet the total load demand:

[0108] If P renewable ≥P load , then renewable energy can meet the load demand within the microgrid without purchasing additional electricity from the main grid;

[0109] If P renewable <P load , it is necessary to purchase additional electricity from the main grid to meet the load demand within the microgrid.

[0110] Step C4, calculate the cost C corresponding to the purchase of additional electricity buy :

[0111] C buy =(P renewable -P load )×R grid (11)

[0112] In the formula, R grid Represents the purchase cost of electricity from the main grid.

[0113] Step C5, setting the charging power P of the energy storage system charge With discharge power P discharge :

[0114] P charge =α×(P renewable -P load ) (12)

[0115] P discharge =(1-α)×(P renewable -P load ) (13)

[0116] Where α is the ratio of charge and discharge power.

[0117] Step C6, calculate the relative position L(a) of the middle point according to the data shape tree establishment rule i |a1,a n ) and mapped to the charging power and discharging power of the energy storage system.

[0118] Specifically, taking multiple power points in time series data as an example, assume that the following power data exists:

[0119] P1=100kW, t1=1 hour; P2=150kW, t2=2 hours; P3=200kW, t3=3 hours. These data points can be mapped to (1,100), (2,150), (3,200) on a conventional two-dimensional plane.

[0120] Fix the two endpoints at specific positions in the coordinate system: assume that the power point P1 at time t1 is mapped to (-0.5, 0), and the power point P3 at time t3 is mapped to (0.5, 0);

[0121] Calculate the relative position of the intermediate point P2: Determine the position of P2 in this coordinate system through standardization and geometric transformation:

[0122]

[0123] Therefore, the position of P2 in the Bookstein coordinate system is (0.5, 0).

[0124] Through this method, power data at a series of time points can be mapped into a standardized plane coordinate system, so as to better capture and analyze the charging and discharging behavior of the energy storage system, help optimize the power dispatch strategy, balance the supply and demand of the system, and improve the stability and efficiency of the system.

[0125] Step C8, calculate the cost C corresponding to the charging and discharging of the energy storage system charge and C discharge :

[0126] C charge =P charge ×R charge (16)

[0127] C discharge =P discharge ×R discharge (17)

[0128] In the formula, R charge is the charging cost of the energy storage system, R discharge is the discharge cost of the energy storage system.

[0129] Step C9, taking the power balance, voltage stability, frequency stability and other conditions of the power grid as constraints, solve the total cost, system stability and response speed optimization of the microgrid secondary system based on the conjugate gradient algorithm:

[0130]

[0131] In the formula, w c is the cost weight, w d is the demand response elasticity weight, w L is the supply elasticity weight, w s is the load balancing elastic weight, E d is the demand response elasticity, E L is the load balancing elasticity, E s is the supply elasticity, C buyis the cost of purchasing additional electricity, C charge The cost of charging the energy storage system, C discharge is the cost corresponding to the energy storage system discharge, α is the ratio of the energy storage system charging power to the energy storage system discharge power, P charge is the charging power of the energy storage system, P max_charge is the maximum charging power of the energy storage system,

[0132] P discharge is the discharge power of the energy storage system, P max_discharge is the maximum discharge power of the energy storage system, P renewable is the total electricity generated by renewable energy, P load is the total load demand within the microgrid, P buy The additional power purchased, V min is the minimum limit value of the voltage at each node in the microgrid, V node is the voltage of each node in the microgrid, V max is the maximum limit value of the voltage at each node in the microgrid, f min is the minimum limit value of the power frequency in the microgrid, f grid is the power frequency in the microgrid, f max It is the maximum limit value of the power frequency in the microgrid.

[0133] Based on the above optimization results, the optimal total cost can be obtained by recalculating the corresponding additional electricity purchased, charging power and discharging power.

[0134] Step 3: Execute the optimized dispatching instruction; execute the optimized dispatching instruction through the functional modular microgrid networking;

[0135] Step 4: Feedback the system state after executing the optimized scheduling instruction; use Kalman filter for recursive filtering to ensure accurate estimation of the system state in the presence of noise.

[0136] The specific steps of recursive filtering of Kalman filter are as follows:

[0137] Step A: Based on the state estimation at the previous moment and the control input of the system, predict the state of the system at the next moment. This prediction process estimates the expected value and covariance matrix of the system state, which represents the uncertainty of the state estimation.

[0138] Step B: By comparing the difference between the predicted value and the actual observed value, the Kalman gain is calculated and used to correct the predicted value.

[0139] Step 5: According to the feedback system status, the elasticity metric in elastic matching is optimized and corrected through the neural network prediction model; the specific steps are as follows:

[0140] Step A, obtain the historical data of solar and wind power production capacity, the historical data of the charging and discharging power time series of the energy storage system, the historical data of the total power demand of the microgrid, and the historical data of the power demand of each user device or system in the microgrid, and perform data preprocessing: In order to avoid the problem of excessive numerical differences, the Min-Max Normalization method is used to normalize the data, and the data set is divided into a training set and a test set with a ratio of 9:1. The specific normalization formula is as follows:

[0141]

[0142] Where: x normalized represents the normalized data, x represents the original data, and x max and x min Represents extremely large data and extremely small data respectively.

[0143] Step B, build the initial model: through the bidirectional GRU layer, historical and future capacity and load data are considered at the same time, so as to more comprehensively define the elasticity metric and improve the accuracy of elasticity matching. Specifically, the output of the BiGRU neural network is shown in equations (20), (21), and (22)

[0144]

[0145] Where: Represents the state of the forward hidden layer at time t; represents the state of the reverse hidden layer at time t; w t represents the weight of the forward hidden layer state at time t; v t represents the weight of the reverse hidden layer state at time t; b t Represents the bias of the hidden layer state at time t.

[0146] Combined with the Attention mechanism, the attention score is converted into attention weight by using the softmax function, and the most important features are extracted to make the model more robust. The specific calculation formulas are shown in (23), (24), and (25):

[0147] s(x i ,q)=V T tanh(Wx i +b) (23)

[0148]

[0149] Where: a i and x iThey represent the attention score and weight of capacity or load respectively, attention(x,q) represents the output of the attention layer at time i, and W and b represent the learned weight matrix and bias respectively.

[0150] Step C, hyperparameter optimization: Use the Bayesian optimization algorithm to optimize the learning rate, training window size, number of hidden layer neurons, and number of BiGRU layer neurons of the BiGRU-Attention model.

[0151] Furthermore, the Bayesian optimization method is to maximize or minimize a black box objective function based on probability models such as Bayesian theorem and Gaussian process. By continuously selecting the next sampling point in the search space and then estimating the optimal value of the function based on the existing sampling data, it gradually converges to the global optimal solution. The specific expression is shown in (26):

[0152]

[0153] Where: f(h) represents the prior distribution model, h * represents the optimal parameter value of the constraint domain of f(h), and H represents the candidate set.

[0154] Step D, prediction and parameter correction: The BiGRU-Attention model is trained with the training set to adjust and optimize the network model parameters. The BO-BiGRU-Attention model is predicted with the test set to obtain distributed energy data, energy storage system charging and discharging data, microgrid total power demand data, and power demand data of each user device or system within the microgrid. The elasticity metric is corrected based on the predicted data after normalization.

[0155] Step 6: Formulate an optimized scheduling instruction based on the optimized and corrected elasticity metric matching combination, and return to step 2.

[0156] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0157] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, 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 generate 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 flowchart and / or block diagram. 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.

[0158] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0160] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A microgrid secondary system networking based on elastic matching, characterized in that: include: Information collection layer, used to collect system data in real time; The optimization scheduling layer is used to obtain the matching combination of microgrid power distribution under the constraints of constraints based on the collected system data, with the goal of minimizing the total cost and elasticity metric, and formulate the optimization scheduling instructions based on the obtained matching combination; the microgrid power distribution includes the purchase of additional power, the charging power of the energy storage system, and the discharge power of the energy storage system; the elasticity metric includes the supply elasticity that reflects the response ability of distributed energy to changes in environmental conditions, the load balancing elasticity that reflects the balancing ability of the system under load changes, and the demand response elasticity that reflects the degree of user response to changes in electricity prices; Module control layer, used to execute optimization scheduling instructions; Information feedback layer, used to feedback the system status after executing the optimization scheduling instructions; The parameter optimization layer is used to modify the elasticity metric through the neural network prediction model according to the feedback system status.

2. According to the microgrid secondary system networking based on elastic matching according to claim 1, it is characterized in that: The information collection layer includes an operation monitoring data acquisition module and a microgrid comprehensive monitoring index calculation module; The operation monitoring data acquisition module is used to collect the operation monitoring parameters of the microgrid operation status in real time, specifically including: total power demand value, total power supply value, distributed power generation comprehensive energy efficiency, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, and microgrid communication equipment data; The microgrid comprehensive monitoring index calculation module is used to calculate the microgrid comprehensive monitoring index data according to the real-time collected operation monitoring parameters, specifically including: microgrid whole network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage equipment charging and discharging efficiency stability index, key equipment working status monitoring index, and network communication reliability index.

3. The microgrid secondary system networking based on elastic matching according to claim 1 is characterized in that: The module control layer includes: a PCC module, a microgrid AC regulation module, a microgrid AC non-adjustable module, a microgrid DC regulation module, a microgrid DC non-adjustable module and an interconnection module; The PCC module switches the operation of the microgrid between networking and off-grid in a limited exchange power control mode; The microgrid AC regulation module includes one or more distributed power sources, energy storage systems and grid-connected devices; The microgrid AC non-adjustable module includes an AC load, an undispatched distributed power source and a networking device; The microgrid DC regulation module includes an energy storage system with regulation capability and a bidirectional DC / DC chopper, which is used to control the DC bus voltage of the microgrid; The microgrid DC non-adjustable module includes a DC load, a non-dispatched distributed power source and a grid-connected device; The interconnection module comprises an interconnection converter, and two ends of the interconnection converter are respectively connected to the microgrid AC bus and the microgrid DC bus.

4. The microgrid secondary system networking based on elastic matching according to claim 1 is characterized in that: The parameter optimization layer uses the BO-BiGRU-Attention hybrid neural network prediction model to correct the elasticity metric. The specific steps are: Step 51: Obtain historical data of distributed energy, historical data of charging and discharging power time series of energy storage system, historical data of total power demand of microgrid, and historical data of power demand of each user device or system in microgrid, and perform preprocessing; Step 52: construct an initial BiGRU-Attention model, train the BiGRU-Attention model with the preprocessed data, and obtain the initial BiGRU-Attention model; Step 53: Hyperparameter optimization: using the Bayesian optimization algorithm to optimize the learning rate, training window size, number of hidden layer neurons, and number of BiGRU layer neurons of the initial BiGRU-Attention model, and obtaining the BO-BiGRU-Attention model based on the optimized parameters of the initial BiGRU-Attention model; Step 54: The distributed energy data, the energy storage system charging and discharging data, the total power demand data of the microgrid, and the power demand data of each user device or system in the microgrid are predicted by the BO-BiGRU-Attention model, and the elasticity metric is calculated based on the predicted data to obtain a corrected elasticity metric.

5. A control method for microgrid secondary system networking based on elastic matching, characterized in that: The following steps are involved: Step 1: Collect system data in real time; Step 2: Based on the collected system data, with the goal of minimizing the total cost and elasticity metric, a matching combination of microgrid power distribution is obtained under the constraints of the constraints, and an optimization dispatch instruction is formulated according to the obtained matching combination; the microgrid power distribution includes the purchase of additional power, the charging power of the energy storage system, and the discharge power of the energy storage system; the elasticity metric includes the supply elasticity that reflects the ability of distributed energy to respond to changes in environmental conditions, the load balancing elasticity that reflects the system's balancing ability under load changes, and the demand response elasticity that reflects the degree of user response to changes in electricity prices; Step 3: Execute the optimization scheduling instruction; Step 4: Feedback the system status after executing the optimized scheduling instruction; Step 5: According to the feedback system status, the elasticity metric in elastic matching is corrected through the neural network prediction model; Step 6: Formulate an optimized scheduling instruction based on the matching combination of the modified elasticity metrics, and return to execute step 3.

6. The control method according to claim 5, characterized in that: The collected system data include total power demand value, total power supply value, comprehensive energy efficiency of distributed power generation, energy storage device efficiency, microgrid energy storage device data, microgrid key equipment data, microgrid communication equipment data, microgrid network power balance index, distributed energy response speed index, energy storage device power balance index, energy storage equipment charging and discharging efficiency stability index, key equipment working status monitoring index, and network communication reliability index.

7. The control method according to claim 5, characterized in that: Taking the power balance, voltage stability and frequency stability of the microgrid as constraints, the conjugate gradient algorithm is used to solve the optimization problem of minimizing the total cost and elasticity metric of the microgrid secondary system: In the formula, w c is the cost weight, w d is the demand response elasticity weight, w L is the supply elasticity weight, w s is the load balancing elastic weight, E d is the demand response elasticity, E L For load balancing elasticity, E s is the supply elasticity, C buy is the cost of purchasing additional electricity, C charge The cost of charging the energy storage system, C discharge is the cost corresponding to the energy storage system discharge, α is the ratio of the energy storage system charging power to the energy storage system discharge power, P charge is the charging power of the energy storage system, P max_charge is the maximum charging power of the energy storage system, P discharge is the discharge power of the energy storage system, P max_discharge is the maximum discharge power of the energy storage system, P renewable is the total electricity generated by renewable energy, P load is the total load demand within the microgrid, P buy The additional power purchased, V min is the minimum limit value of the voltage at each node in the microgrid, V node is the voltage of each node in the microgrid, V max is the maximum limit value of the voltage at each node in the microgrid, f min is the minimum limit value of the power frequency in the microgrid, f grid is the power frequency in the microgrid, f max It is the maximum limit value of the power frequency in the microgrid.

8. The microgrid secondary system networking based on elastic matching according to claim 5 is characterized in that: According to the data shape tree, the relative position L(a) of the middle point is calculated according to the rules established i |a1,a n ), and mapped to the charging power of the energy storage system and the discharging power of the energy storage system; the data shape tree establishment rules are specifically as follows: Curve A consists of a series of sampling points (a1, a2, ..., a n ), select a point a on curve A i As the midpoint, use L(a i |a1,a n ) represents point a i Relative to point a1 and point a n The position is point a i Relative to point a1 and point a n Bookstein coordinates of point a i Relative to point a1 and point a n The position L(a i |a1,a n )=(a (1) ,a (2) ), where (a (1) ,a (2) ) The specific calculation formula is: In the formula, for a k Two-dimensional plane coordinates, k = 1, 2,…, n.

9. The control method according to claim 5, characterized in that: The BO-BiGRU-Attention hybrid neural network prediction model is used to optimize and correct the elasticity metric. The specific steps are as follows: Step 51: Obtain historical data of distributed energy, historical data of charging and discharging power time series of energy storage system, historical data of total power demand of microgrid, and historical data of power demand of each user device or system in microgrid, and perform preprocessing; Step 52: construct an initial BiGRU-Attention model, train the BiGRU-Attention model with the preprocessed data, and obtain the initial BiGRU-Attention model; Step 53: Hyperparameter optimization: using the Bayesian optimization algorithm to optimize the learning rate, training window size, number of hidden layer neurons, and number of BiGRU layer neurons of the initial BiGRU-Attention model, and obtaining the BO-BiGRU-Attention model based on the optimized parameters of the initial BiGRU-Attention model; Step 54: The distributed energy data, the energy storage system charging and discharging data, the total power demand data of the microgrid, and the power demand data of each user device or system in the microgrid are predicted by the BO-BiGRU-Attention model, and the elasticity metric is calculated based on the predicted data to obtain a corrected elasticity metric.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 5 to 9 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 5 to 9 are implemented.

Citation Information

Patent Citations

  • Elastic operation control method for AC / DC hybrid distribution network

    CN109830976A

  • Active power distribution network scheduling method considering source storage load interaction

    CN112800658A

  • Micro-grid three-stage optimization control method based on rolling optimization of energy storage system

    CN114944661A

  • Regional power grid elastic optimization scheduling method and system supported by distributed power supply

    CN117394360A

  • Microgrid networking interconnection and flexible switching strategy system and method

    CN117728395A