DC bus voltage stability control method, system and device for building light storage DC flexible micro-grid, and storage medium

Abstract

The invention discloses a building optical storage direct flexible micro-grid direct current bus voltage stability control method, system and device and a storage medium, and relates to the technical field of micro-grid control, and the method comprises the steps: collecting the real-time operation parameters of a micro-grid, updating a historical database after filtering and abnormal value processing, constructing an ARIMA-LSTM model to predict the voltage, and adjusting the parameters according to errors; calculating the optimal power of each source by using a power balance model and a grading strategy in combination with a predicted value and a system state; according to the error and the power regulation PI parameter, a multi-target model is constructed to solve an optimal control sequence; and finally, issuing an instruction, monitoring an effect and updating parameters according to feedback to form closed-loop control and guarantee voltage stability. According to the method, the stability of the DC bus voltage of the building photovoltaic storage DC flexible micro-grid is remarkably improved, voltage fluctuation caused by photovoltaic output intermittency and load random fluctuation is effectively inhibited, the equipment operation risk and the system energy consumption are reduced, and the power supply reliability and the new energy consumption capability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of micro-grid control, and in particular to a building photovoltaic-storage-dc-flexible micro-grid direct-current bus voltage stability control method, system, device and storage medium. BACKGROUND

[0002] With the deepening of global action on climate change, the low-carbon transformation of the building field, as an important source of carbon emissions, is imminent. The building photovoltaic-storage-dc-flexible (PSDF) micro-grid technology integrates photovoltaic power generation, energy storage systems, direct-current distribution and flexible loads, providing an effective solution for the green and efficient operation of building energy systems. However, in the actual operation of the system, the stability of the direct-current bus voltage faces severe challenges: on the one hand, building loads have significant randomness and volatility; on the other hand, photovoltaic output is intermittent due to weather conditions, coupled with the complex coupling of energy storage system charging and discharging characteristics, making the direct-current bus voltage prone to severe fluctuations, seriously affecting the power supply reliability and power quality of the system.

[0003] Currently, for the control of micro-grid direct-current bus voltage, the existing technology mostly adopts linear control strategies based on traditional PI control. This type of method usually relies on real-time voltage deviation for feedback adjustment, although the structure is simple, but the response is lagging, and the controller parameters are fixed, making it difficult to adapt to the complex working conditions of random and rapid changes of multi-source power in building scenarios. Specifically, the traditional method has the disadvantages of large voltage adjustment deviation, obvious overshoot in dynamic response process, long recovery time, etc., especially unable to prospectively suppress the voltage trend fluctuations caused by changes in photovoltaic and load; in summary, the existing technology lacks deep fusion analysis of historical voltage data and external influencing factors, and fails to achieve multi-source power prospective coordination distribution based on prediction information, resulting in obvious deficiencies in the control performance of building photovoltaic-storage-dc-flexible micro-grid in this specific application scenario. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is: how to provide a stable control method that can effectively deal with the direct-current bus voltage fluctuation problem in building photovoltaic-storage-dc-flexible micro-grid.

[0006] To solve the above technical problems, the present application provides the following technical solutions: In a first aspect, the present application provides a building photovoltaic-storage-dc-flexible micro-grid direct-current bus voltage stability control method, comprising: Collecting various types of real-time operating parameters of the micro-grid system, updating the historical database after filtering and outlier detection processing; Based on the updated historical database, an ARIMA-LSTM hybrid prediction model is established to predict the change trend of the DC bus voltage in the future period, obtain the voltage prediction value, and adaptively adjust the model parameters according to the real-time prediction error. Based on the voltage prediction value and the current system state, the optimal power output of each source is calculated by establishing a power balance constraint model and adopting a hierarchical control strategy. According to the voltage prediction error generated by the voltage prediction value and the optimal power output of each source, the parameters of the PI controller are dynamically adjusted. Based on the voltage prediction value and the optimal power output of each source, a multi-objective optimization model is established in the prediction time domain, and a particle swarm optimization algorithm is used to solve the optimal control sequence. The optimal control sequence is sent to each device as a control instruction, the control effect is monitored in real time, the control parameters are updated according to the feedback information, and a closed-loop control is formed.

[0007] As an optimal solution of the building light storage straight flexible microgrid DC bus voltage stability control method, wherein: The ARIMA-LSTM hybrid prediction model is established based on the updated historical database, the change trend of the DC bus voltage in the future period is predicted, the voltage prediction value is obtained, and the model parameters are adaptively adjusted according to the real-time prediction error. Based on the updated historical database, an ARIMA-LSTM hybrid prediction model is established, and in the hybrid prediction model, the ARIMA model is used to process the historical trend of the DC bus voltage, and the LSTM model is used to integrate external factors to predict the voltage trend.

[0008] The beneficial effects of the preferred technical solution are: the ARIMA model focuses on processing the historical trend of the DC bus voltage, which can effectively capture the linear characteristics and long-term trend of the voltage data; the LSTM model integrates external factors to predict the voltage trend, which can fully consider the influence of external factors such as light intensity, temperature, load change, etc. on the DC bus voltage, so that the hybrid prediction model can more comprehensively and accurately predict the change trend of the DC bus voltage in the future period, and improve the accuracy and reliability of voltage prediction.

[0009] As an optimal solution of the building light storage straight flexible microgrid DC bus voltage stability control method, wherein: The ARIMA-LSTM hybrid prediction model is established based on the updated historical database, the change trend of the DC bus voltage in the future period is predicted, the voltage prediction value is obtained, and the model parameters are adaptively adjusted according to the real-time prediction error. The historical voltage data and external influencing factors are analyzed by the mixed prediction model to predict the change trend of the DC bus voltage in a future period of time, and a voltage prediction value is obtained.

[0010] As a preferred solution of the building photovoltaic energy storage direct flexible micro-grid DC bus voltage stability control method, wherein: The optimal power output of each source is calculated based on the voltage prediction value and the current system state by establishing a power balance constraint model and adopting a hierarchical control strategy. Based on the voltage prediction result and the current system state, a power balance constraint model is established to calculate the optimal power output of each source; a hierarchical control strategy is adopted to determine the response order and mode of each source.

[0011] As a preferred solution of the building photovoltaic energy storage direct flexible micro-grid DC bus voltage stability control method, wherein: The optimal power output of each source is calculated based on the voltage prediction value and the current system state by establishing a power balance constraint model and adopting a hierarchical control strategy. In the hierarchical control strategy, the first-level response is undertaken by the energy storage system with millisecond-level response capability, which is realized through fast charging and discharging; The second-level response is achieved through maximum power point tracking adjustment of photovoltaic and load power regulation; The third-level response is completed through grid power exchange and load scheduling.

[0012] As a preferred solution of the building photovoltaic energy storage direct flexible micro-grid DC bus voltage stability control method, wherein: Based on the voltage prediction value and the optimal power output of each source, a multi-objective optimization model is established within the prediction time domain, and a particle swarm optimization algorithm is used to solve the optimal control sequence. Based on the voltage prediction value and the optimal power output of each source, a multi-objective optimization model is established within the prediction time domain using a rolling optimization control strategy; the multi-objective optimization model is optimized to achieve the optimal state of the relevant indicators; a particle swarm optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal control sequence.

[0013] The beneficial effects of the preferred technical solution are: the rolling optimization control strategy can continuously update the optimization process according to the real-time state and prediction information of the system, and adapt to the dynamic changes of the system; the particle swarm optimization algorithm is used to solve the multi-objective optimization model, which can quickly find the optimal control sequence in a complex solution space, realize accurate control of the micro-grid system, and improve the overall performance and operation efficiency of the system.

[0014] As a preferred solution of the building photovoltaic energy storage direct flexible micro-grid DC bus voltage stability control method, wherein: The multi-objective optimization model based on the voltage prediction value and the optimal power output of each source further comprises: The target factor considered by the multi-objective optimization model includes making the voltage output as close as possible to the preset ideal reference value.

[0015] The beneficial effects of the preferred technical solution are that the target factor considered by the multi-objective optimization model is clear, and the voltage output is as close as possible to the preset ideal reference value. The setting of this target helps to stabilize the DC bus voltage in an ideal range, reduces the influence of voltage fluctuation on various devices in the micro-grid system, improves the operation stability and service life of the devices, and at the same time is also conducive to ensuring the reliable operation of the entire building light storage direct flexible micro-grid system.

[0016] In a second aspect, the present application provides a building light storage direct flexible micro-grid DC bus voltage stabilization control system, comprising: A data acquisition and preprocessing module is configured to acquire various real-time operation parameters of the micro-grid system, and update a historical database after filtering and outlier detection processing; A voltage prediction and parameter adjustment module is configured to establish an ARIMA-LSTM hybrid prediction model based on the updated historical database, predict the trend of DC bus voltage change in the future period, obtain a voltage prediction value, and adaptively adjust model parameters according to real-time prediction errors; A power output calculation module is configured to calculate the optimal power output of each source based on the voltage prediction value and the current system state by establishing a power balance constraint model and adopting a hierarchical control strategy; A controller parameter adjustment module is configured to dynamically adjust the parameters of a PI controller according to the voltage prediction error generated by the voltage prediction value and the optimal power output of each source; An optimization sequence solving module is configured to establish a multi-objective optimization model in the prediction time domain based on the voltage prediction value and the optimal power output of each source, and solve the optimal control sequence by using a particle swarm optimization algorithm; A closed-loop control execution module is configured to issue the optimal control sequence as a control instruction to each device, monitor the control effect in real time, update the control parameters according to the feedback information, and form a closed-loop control.

[0017] In a third aspect, the present application provides a computer device, comprising: A memory and a processor; The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which realize the steps of the building light storage direct flexible micro-grid DC bus voltage stabilization control method when executed by the processor.

[0018] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which, when executed by a processor, implement the steps of the building photovoltaic energy storage direct-flexible microgrid direct-current bus voltage stability control method.

[0019] The control method provided by the present application has the following advantages: the control method provided by the present application has significant benefits in practical engineering applications; the core value lies in the deep integration of advanced prediction algorithms and multi-source coordinated control strategies, which directly solves the key problems in the engineering practice of the building photovoltaic energy storage direct-flexible microgrid; specifically, the method can effectively cope with typical disturbance scenarios such as power drop caused by photovoltaic cloud cover and sudden start-stop of building load, control the fluctuation range of the direct-current bus voltage within the allowable range, and avoid the action of protection devices or equipment shutdown caused by voltage out-of-limit, thereby greatly improving the continuity and reliability of system operation. Through the millisecond-level fast response of the energy storage system and the optimized regulation and control of photovoltaic and load, the dependence on power support of the power grid is reduced, the power fluctuation is smoothed, the self-generation and self-use rate of photovoltaic is improved, and the power grid purchase cost and power impact are reduced. The adaptive mechanism ensures that the control system can maintain good performance under different seasons, different weather and different load levels, and reduces the complexity of system debugging and maintenance. Ultimately, the technology provides a solid guarantee for the building to achieve efficient and stable low-carbon energy supply, and brings considerable improvement in operation economy and safety. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a whole flowchart of a building photovoltaic energy storage direct-flexible microgrid direct-current bus voltage stability control method provided by the present application.

[0022] Figure 2 is a building photovoltaic energy storage direct-flexible microgrid 21 node diagram of a building photovoltaic energy storage direct-flexible microgrid direct-current bus voltage stability control method provided by the present application.

[0023] Figure 3 is a multi-source power coordinated control process experimental result diagram in a simulation example of a building photovoltaic energy storage direct-flexible microgrid direct-current bus voltage stability control method provided by the present application. DETAILED DESCRIPTION

[0024] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0025] Embodiment 1, refer to Figure 1 For the first embodiment of the present application, the embodiment provides a building light storage direct flexible micro-grid DC bus voltage stability control method, comprising: S1: Collecting various types of real-time operation parameters of the micro-grid system, updating the historical database after filtering and abnormal value detection processing; S2: Based on the updated historical database, an ARIMA-LSTM hybrid prediction model is established to predict the voltage change trend in the future period, obtain the voltage prediction value, and adaptively adjust the model parameters according to the real-time prediction error; S3: Based on the voltage prediction value and the current system state, the optimal power output of each source is calculated by establishing a power balance constraint model and adopting a hierarchical control strategy; S4: According to the voltage prediction error generated by the voltage prediction value and the optimal power output of each source, the parameters of the PI controller are dynamically adjusted; S5: Based on the voltage prediction value and the optimal power output of each source, a multi-objective optimization model is established in the prediction time domain, and a particle swarm optimization algorithm is used to solve the optimal control sequence; S6: The optimal control sequence is issued as a control instruction to each device, the control effect is monitored in real time, the control parameters are updated according to the feedback information, and a closed-loop control is formed.

[0026] It should be noted that through steps S1-S6, the real-time collected data can be fully utilized, and the DC bus voltage change trend can be accurately predicted by means of the ARIMA-LSTM hybrid prediction model. Based on this prediction result, the optimal power output of each source is reasonably calculated by combining the power balance constraint model and the hierarchical control strategy, and the PI controller parameters are dynamically adjusted. At the same time, by establishing a multi-objective optimization model and using a particle swarm optimization algorithm to solve the optimal control sequence, dynamic optimal control of the micro-grid system is realized. Finally, through closed-loop control, the control parameters are continuously updated according to the feedback information, effectively improving the stability of the DC bus voltage of the building light storage direct flexible micro-grid and the reliability and economy of the system operation, reducing the damage caused by voltage fluctuations to the micro-grid system and related equipment, and providing a strong guarantee for the stable and efficient operation of the building light storage direct flexible micro-grid.

[0027] Embodiment 2, refer to Figures 1-2As one embodiment of the present invention, based on the previous embodiment, a method for stabilizing the DC bus voltage of a building-integrated photovoltaic-storage-DC-flexible microgrid is provided, comprising: In this embodiment, the process of collecting various real-time operating parameters of the microgrid system in step S1, and updating the historical database after filtering and outlier detection, includes: It should be noted that the building-integrated photovoltaic-storage-DC-flexible microgrid system described in this invention adopts a hierarchical distributed architecture, comprising a two-level DC power distribution network of a 750V DC main bus and a 375V DC secondary bus. For example... Figure 2 As shown, the system is connected to the AC grid via the PCC (Point of Common Coupling) and then connected to the 750V DC main bus via an AC / DC converter. Photovoltaic systems PV1 and PV2 are connected to nodes 9 and 8 respectively, with a single photovoltaic system having an installed capacity of 50kW. They employ a maximum power point tracking (MPPT) control strategy with a power response time of 1 second. The photovoltaic systems are connected to the DC bus via a DC / DC boost converter with a switching frequency of 20kHz and an efficiency of 96%.

[0028] The energy storage system ES access node 7 has a capacity of 100kWh, a rated power of 50kW, a charge / discharge efficiency of 93%, and a power response time of 50ms. The energy storage system achieves rapid charge / discharge control through a bidirectional DC / DC converter, providing the system with millisecond-level power regulation capabilities.

[0029] The building load distribution is connected to each node, with a total load capacity of 200kW, including a mixture of constant power loads and constant impedance loads. The 750V DC main bus is stepped down to the 375V secondary bus through a DC / DC converter to supply power to the terminal loads.

[0030] A distributed measurement, control, and protection device is constructed to collect various real-time operating parameters of the microgrid system, including key parameters such as DC bus voltage, photovoltaic power, energy storage power, load power, and ambient temperature. The collected data is filtered and outlier detected, and the historical database is updated to provide training samples for the subsequent ARIMA-LSTM prediction model. The data acquisition cycle is on the order of seconds to ensure the real-time requirements of the control algorithm.

[0031] The distributed measurement, control and protection device is designed based on the ARM Cortex-A7 processor and adopts a modular architecture, including a CPU motherboard, I / O expansion board, communication board and power supply board; the distributed measurement, control and protection device includes an intelligent management system and distributed measurement, control and protection devices.

[0032] The intelligent management system adopts a two-layer control architecture, including an upper predictive optimization layer and a lower rapid response layer.

[0033] In another possible implementation, when collecting various real-time operation parameters of the micro-grid system, a sensor network distributed at various key nodes of the micro-grid system can be used for data collection. For example, high-precision voltage sensors, current sensors and power sensors are installed at positions of photovoltaic cell panels, energy storage devices, DC bus lines and the like. These sensors automatically collect real-time operation parameters such as voltage, current and power at a preset time interval, and transmit data to a data collection terminal through wired or wireless communication.

[0034] In another possible implementation, when collecting various real-time operation parameters of the micro-grid system, a combination of smart meters and monitoring devices can also be used for collection. The smart meters can record power consumption and output of various power-using devices and power-generating devices in real time, while the monitoring devices can monitor parameters such as frequency and phase of the micro-grid system. After integration of these data, various real-time operation parameters are obtained.

[0035] In the embodiment, based on the updated historical database in step S2, an ARIMA-LSTM hybrid prediction model is established to predict the change trend of the DC bus voltage in the future period, to obtain a voltage prediction value, and to adaptively adjust model parameters according to a real-time prediction error, including: In the upper prediction optimization layer of the intelligent management system, a power distribution strategy is formulated based on an ARIMA-LSTM (autoregressive integrated moving average model-long short-term memory network) hybrid prediction model, wherein an ARIMA model processes the historical trend of the DC bus voltage, and a LSTM model fuses external factors such as photovoltaic power, load power and environmental temperature to predict the voltage trend. Specifically, the ARIMA-LSTM hybrid prediction model uses the following prediction formula: wherein, is the k-step predicted voltage, is the processed voltage historical trend, is the fused external influencing factor.

[0036] Based on the ARIMA-LSTM hybrid prediction model, the historical voltage data and external influencing factors are analyzed to predict the change trend of the DC bus voltage in the future 10-30 seconds, and an optimal power distribution strategy is formulated.

[0037] In another possible implementation, when establishing the ARIMA-LSTM hybrid prediction model, the direct current bus voltage data in the historical database can be preprocessed first, including data cleaning, normalization and the like, and then the ARIMA model and the LSTM model are trained independently. The ARIMA model determines the parameters of the model through autoregressive, difference and moving average analysis of the historical voltage data; the LSTM model takes the preprocessed historical voltage data and external influencing factors as input and performs training and learning. Finally, the trained ARIMA model and LSTM model are fused to obtain the ARIMA-LSTM hybrid prediction model.

[0038] In another possible implementation, when establishing the ARIMA-LSTM hybrid prediction model, ensemble learning can also be used; first, the data in the historical database is divided into multiple subsets, and the ARIMA model and the LSTM model are trained on each subset to obtain multiple sub-models. Then, these sub-models are integrated by weighted averaging to form the final ARIMA-LSTM hybrid prediction model. In the integration process, each sub-model is assigned different weights according to its prediction accuracy to improve the overall prediction performance of the hybrid prediction model.

[0039] In the present embodiment, the calculation of the optimal power output of each source based on the voltage prediction value and the current system state in the above step S3 includes: In the lower fast response layer of the intelligent management system, according to the real-time voltage deviation, a multi-source coordinated control strategy is adopted to dynamically adjust the power output of the photovoltaic system, the energy storage system and the flexible load; Specifically, based on the voltage prediction result and the current system state, the optimal power output of each source is calculated, and a power balance constraint model is established, which is expressed as: wherein, Ppv is the photovoltaic output power, Pb is the energy storage power (negative for charging and positive for discharging), Pgrid is the grid exchange power, Pl is the load power, Ploss is the system loss.

[0040] A hierarchical control strategy is adopted: the first-level response is borne by the energy storage system, which has millisecond-level response capability for fast charging and discharging; the second-level response is adjusted through photovoltaic MPPT and load power control; the third-level response is through grid power exchange and load scheduling.

[0041] In another possible implementation, when establishing the power balance constraint model, the power characteristics of various power generation devices and power consumption devices in the micro-grid system can also be considered to establish the power balance constraint model based on mathematical equations. For example, the power generation of photovoltaic panels, the charging and discharging power of energy storage devices, and the load power of power consumption devices are taken as variables, and the power balance equation is established according to the law of conservation of energy, while considering the rated power and efficiency of the devices to form the power balance constraint model.

[0042] In another possible implementation, when establishing the power balance constraint model, a simulation-based method can also be used to establish the power balance constraint model. Professional micro-grid simulation software is used to simulate the operation of the micro-grid system. In the simulation process, different parameters of power generation devices and power consumption devices are set to simulate the power flow under various working conditions. Through analysis and summary of the simulation results, the power balance constraint model is established. This method can more intuitively consider the influence of the dynamic characteristics of the system and various complex factors on the power balance.

[0043] In the embodiment, the step of dynamically adjusting the parameters of the PI controller according to the voltage prediction error generated based on the voltage prediction value and the optimal power output of each source in the step S4 includes: The dynamically adjusting the parameters of the PI controller according to the voltage prediction error generated based on the voltage prediction value and the optimal power output of each source is represented as: wherein, , is the parameter of the PI controller, , is the learning rate, is the voltage prediction error, is the power change amount, so that the controller parameters can automatically adapt to the changes in the system operating state, and the adaptability and control accuracy of the control system to different working conditions are improved.

[0044] In another possible implementation, when dynamically adjusting the parameters of the PI controller, the parameters of the PI controller can be dynamically adjusted through a fuzzy control algorithm according to the voltage prediction error and the optimal power output of each source; the voltage prediction error and the optimal power output of each source are taken as inputs of the fuzzy controller, fuzzy reasoning is performed according to a pre-set fuzzy rule base to obtain an adjustment amount of the parameters of the PI controller, and then the adjustment amount is applied to the PI controller to realize dynamic adjustment of the parameters.

[0045] In another possible implementation, the dynamic adjustment of the PI controller parameters can also be achieved using an adaptive control algorithm. Based on the system's real-time operating status and performance indicators, the adaptive control algorithm can automatically adjust the proportional and integral coefficients of the PI controller to ensure good control performance under different operating conditions. For example, when the system load changes, the adaptive control algorithm can quickly adjust the PI controller parameters according to the magnitude and speed of the load change, enabling the system to respond promptly and remain stable.

[0046] In this embodiment, step S5 above, based on the predicted voltage value and the optimal power output of each source, establishes a multi-objective optimization model in the prediction time domain, and uses the particle swarm optimization algorithm to solve for the optimal control sequence, including: Based on the predicted voltage values ​​and the optimal power output of each source, the intelligent management system employs a rolling optimization control strategy in the prediction time domain to establish a multi-objective optimization model, expressed as: in, Let be the objective function. To predict the length of the time domain, This is the voltage reference value. , These are the weighting coefficients. For the first The power output of each power supply.

[0047] In this embodiment, step S6 above, which involves issuing the optimal control sequence as a control command to each device, monitoring the control effect in real time, updating the control parameters based on feedback information, and forming a closed-loop control, includes: The intelligent management system uses measurement and control devices to send the optimal control sequence as control commands to each device and monitors the control effect in real time. The devices provide feedback on the device operating status and control results, and the algorithm updates the control parameters based on the feedback information, forming a complete closed-loop control system.

[0048] Example 3: The above is a schematic scheme of a DC bus voltage stabilization control method for a building-integrated photovoltaic-storage-DC-flexible microgrid according to this embodiment. It should be noted that the technical solution of a DC bus voltage stabilization control system for a building-integrated photovoltaic-storage-DC-flexible microgrid belongs to the same concept as the above-described method for stabilizing the DC bus voltage of a building-integrated photovoltaic-storage-DC-flexible microgrid. Details not described in detail in the technical solution of the DC bus voltage stabilization control system for a building-integrated photovoltaic-storage-DC-flexible microgrid in this embodiment can be found in the description of the above-described method for stabilizing the DC bus voltage of a building-integrated photovoltaic-storage-DC-flexible microgrid.

[0049] This embodiment also provides a DC bus voltage stability control system for a building-integrated photovoltaic-storage DC-flexible microgrid, including: The data acquisition and preprocessing module is configured to collect various real-time operation parameters of the micro-grid system, and update a historical database after filtering and abnormal value detection processing. The voltage prediction and parameter adjustment module is configured to establish an ARIMA-LSTM hybrid prediction model based on the updated historical database, predict the voltage variation trend in the future period, obtain a voltage prediction value, and adaptively adjust the model parameters according to the real-time prediction error. The power output calculation module is configured to calculate the optimal power output of each source based on the voltage prediction value and the current system state by establishing a power balance constraint model and using a hierarchical control strategy. The controller parameter adjustment module is configured to dynamically adjust the parameters of the PI controller according to the voltage prediction error generated by the voltage prediction value and the optimal power output of each source. The optimization sequence solving module is configured to establish a multi-objective optimization model in the prediction time domain based on the voltage prediction value and the optimal power output of each source, and solve the optimal control sequence using a particle swarm optimization algorithm. The closed-loop control execution module is configured to issue the optimal control sequence as a control instruction to each device, monitor the control effect in real time, update the control parameters according to the feedback information, and form a closed-loop control.

[0050] The embodiment also provides an electronic device suitable for the building light storage straight flexible micro-grid direct current bus voltage stability control method, which comprises: The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the building light storage straight flexible micro-grid direct current bus voltage stability control method according to the above embodiment.

[0051] The embodiment also provides a storage medium having a computer program stored thereon, which is executed by a processor to implement the building light storage straight flexible micro-grid direct current bus voltage stability control method according to the above embodiment.

[0052] The storage medium according to the embodiment belongs to the same inventive concept as the building light storage straight flexible micro-grid direct current bus voltage stability control method according to the above embodiment, and the technical details not described in detail in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0053] Embodiment 4, refer to Figure 3 According to an embodiment of the present application, a building light storage straight flexible micro-grid direct current bus voltage stability control method is provided, and a simulation experiment is performed to scientifically demonstrate the beneficial effects of the present application.

[0054] The effectiveness of the multi-source power coordination control strategy is verified through a comprehensive disturbance experiment, such asFigure 3 As shown, the coordination relationship between the total photovoltaic power, the energy storage power, the grid power and the load power is reflected, and the control effect of the ARIMA-LSTM hybrid prediction algorithm is verified. It can be observed from the experimental results that: in the photovoltaic power decline stage, the energy storage system quickly discharges to compensate for the power shortage, while appropriately increasing the grid power input; in the load surge stage, the algorithm preferentially responds to the energy storage system adjustment to avoid the impact on the grid; the power changes of each power source are smooth and orderly in the whole process, which fully proves the superiority of the multi-source coordinated control strategy. The experimental results verify the effectiveness of the hierarchical control strategy described in the application: the energy storage system of the first-level response realizes millisecond-level fast adjustment, the photovoltaic MPPT adjustment and load power regulation of the second-level response maintain second-level response characteristics, and the grid power exchange and load scheduling of the third-level response provide minute-level long-term optimization, ensuring that the system quickly recovers and operates stably under various disturbance conditions.

[0055] As can be seen from the above, the application has significant effectiveness in dealing with random fluctuations of building loads, intermittent changes of photovoltaic output, and complex coupling of energy storage system charging and discharging. The control method can quickly respond to and accurately control the DC bus voltage fluctuation, and can effectively overcome the limitation of the traditional linear control method in the voltage stability of the building photovoltaic storage direct-flexible microgrid.

[0056] It should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, and they should be included in the scope of the claims of the present application.

Claims

1. A method for voltage stability control of a DC bus of a building light storage flexible microgrid, characterized in that, The application relates to a micro-grid system voltage closed-loop control method. Real-time operation parameters of a micro-grid system are collected, filtered and subjected to abnormal value detection, and a historical database is updated; Based on the updated historical database, an ARIMA-LSTM hybrid prediction model is established to predict the voltage variation trend in a future period, and voltage prediction values are obtained, and model parameters are adaptively adjusted according to real-time prediction errors; Based on the voltage prediction values and the current system state, a power balance constraint model is established and a hierarchical control strategy is adopted to calculate the optimal power output of each source; According to the voltage prediction error caused by the voltage prediction values and the optimal power output of each source, the parameters of a PI controller are dynamically adjusted; Based on the voltage prediction values and the optimal power output of each source, a multi-objective optimization model is established in a prediction time domain, and a particle swarm optimization algorithm is adopted to solve an optimal control sequence; The optimal control sequence is used as a control instruction to be sent to each device, real-time control effects are monitored, control parameters are updated according to feedback information, and a closed-loop control is formed.

2. The method of claim 1, wherein the method further comprises: determining a voltage of the DC bus; and adjusting the power output of the DC-AC converter based on the determined voltage of the DC bus. The application relates to a micro-grid system voltage closed-loop control method. Based on the updated historical database, an ARIMA-LSTM hybrid prediction model is established, in which an ARIMA model is used to process the historical trend of the DC bus voltage, and an LSTM model is used to fuse external factors to predict the voltage trend.

3. The method for stabilizing the DC bus voltage of a building-integrated photovoltaic-storage-DC-flexible microgrid as described in claim 2, characterized in that, The application relates to a micro-grid system voltage closed-loop control method. The application relates to a micro-grid system voltage closed-loop control method.

4. The method of claim 3, wherein the method further comprises: Based on the voltage prediction results and the current system state, a power balance constraint model is established to calculate the optimal power output of each source; and a hierarchical control strategy is adopted to determine the response sequence and mode of each source. In the hierarchical control strategy, the first-level response is assumed by an energy storage system with millisecond-level response capability, and is realized through rapid charging and discharging; 5. The method of claim 4, wherein the method further comprises: The second-level response is achieved through photovoltaic maximum power point tracking adjustment and load power regulation; The third-level response is completed through grid power exchange and load scheduling. The application relates to a micro-grid system voltage closed-loop control method. ​ 6. The method of claim 5, wherein the method further comprises: ​ The multi-objective optimization model is established in the prediction time domain based on the voltage prediction value and the optimal power output of each source, and the multi-objective optimization model reaches an optimal state of related indexes through optimization control; and the multi-objective optimization model is solved by using a particle swarm optimization algorithm, so as to obtain an optimal control sequence.

7. The method of claim 6, wherein the method further comprises: determining the voltage stability of the DC bus of the building; and adjusting the power output of the energy storage device based on the voltage stability of the DC bus of the building. The multi-objective optimization model is established in the prediction time domain based on the voltage prediction value and the optimal power output of each source, and the multi-objective optimization model reaches an optimal state of related indexes through optimization control; and the multi-objective optimization model is solved by using a particle swarm optimization algorithm, so as to obtain an optimal control sequence. The target factors considered by the multi-objective optimization model include making the voltage output as close as possible to the preset ideal reference value.

8. A building light storage direct flexible micro-grid DC bus voltage stability control system, applying the method of any one of claims 1-7, characterized in that, The method comprises the following steps: The data acquisition and preprocessing module is used for collecting various real-time operation parameters of the micro-grid system, and updating a historical database after filtering and abnormal value detection processing; The voltage prediction and parameter adjustment module is used for establishing an ARIMA-LSTM hybrid prediction model based on the updated historical database, predicting the voltage change trend of the direct-current bus in the future period, obtaining the voltage prediction value, and adaptively adjusting the model parameters according to the real-time prediction error; The power output calculation module is used for calculating the optimal power output of each source based on the voltage prediction value and the current system state by establishing a power balance constraint model and using a hierarchical control strategy; The controller parameter adjustment module is used for dynamically adjusting the parameters of the PI controller according to the voltage prediction error generated by the voltage prediction value and the optimal power output of each source; The optimization sequence solving module is used for establishing a multi-objective optimization model in the prediction time domain based on the voltage prediction value and the optimal power output of each source, and solving the optimal control sequence by using a particle swarm optimization algorithm; The closed-loop control execution module is used for issuing the optimal control sequence as a control instruction to each device, monitoring the control effect in real time, updating the control parameters according to the feedback information, and forming a closed-loop control.

9. An electronic device, comprising: The method comprises the following steps: The memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions, so as to realize the steps of the method according to any one of claims 1 to 7. The memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions, so as to realize the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, ​

Images