Intelligent voltage regulation and control method applied to photovoltaic cluster

Abstract

The invention provides an intelligent voltage regulation and control method applied to a photovoltaic cluster. The method comprises the following steps: acquiring historical operation data of the photovoltaic cluster; the voltage prediction model takes minutes as a time unit, records rated voltages of the photovoltaic cluster in different time periods, and draws a first voltage fluctuation circle, a second voltage fluctuation circle and a third voltage fluctuation circle of which the radii are sequentially reduced at the rated voltages in the different time periods by taking the rated voltages in the different time periods as circle centers; calculating the number of tangency and intersection between the first voltage fluctuation circle, the second voltage fluctuation circle and the third voltage fluctuation circle and the preset voltage; and dynamically adjusting the voltage of the photovoltaic cluster according to the voltage deviation number. Compared with the prior art, the intelligent voltage regulation and control method applied to the photovoltaic cluster provided by the invention has the advantages that the voltage regulation is faster, the cooperative control is better, and the stability, the reliability and the economical efficiency of power grid operation are remarkably improved.

Description

Technical Field

[0001] The present invention is applicable to the field of photovoltaic technology, and in particular relates to an intelligent voltage control method applied to a photovoltaic cluster. Background Art

[0002] With the urgent global demand for clean energy, photovoltaic power generation, with its green and sustainable characteristics, shows great development potential and broad prospects. However, photovoltaic power generation systems have significant drawbacks. Their output power is significantly affected by natural environmental factors such as light intensity and ambient temperature, and exhibits significant intermittency and volatility. This unstable power output can easily cause frequent fluctuations in grid voltage, posing a serious challenge to the safe and stable operation of the grid.

[0003] Traditional voltage regulation methods suffer from slow response times, making it difficult to accurately match the rapidly changing dynamic operating characteristics of photovoltaic clusters. Furthermore, due to the lack of effective coordinated control mechanisms for multiple photovoltaic nodes, local voltages often exceed safety limits or equipment overloads during actual operation, significantly threatening the reliability of the grid system and the lifespan of equipment.

[0004] Currently, the industry widely uses fixed-configuration reactive power compensation devices, such as static VAR compensators (SVCs) and static VAR generators (SVGs), to maintain grid voltage stability by adjusting reactive power output. However, these technologies rely on preset thresholds to trigger regulation and lack the ability to proactively predict voltage fluctuations. This results in regulation behavior consistently lagging behind actual voltage fluctuations, making it impossible to fundamentally guarantee grid voltage stability. Furthermore, existing technologies lack a global, coordinated control concept for photovoltaic clusters. Each node operates independently, making the system prone to imbalances caused by local reactive power redundancy or insufficient compensation during operation, seriously impacting the optimal allocation and utilization efficiency of reactive resources.

[0005] In addition, existing technologies have obvious shortcomings. They generally lack the ability to monitor and accurately predict the global situation of photovoltaic clusters in real time. The control strategy is too single, making it difficult to simultaneously meet multiple optimization goals in the operation of the power grid, such as voltage stability, power balance, and economic operation.

[0006] Therefore, there is an urgent need for a new intelligent voltage control method applied to photovoltaic clusters to solve the above technical problems. Summary of the Invention

[0007] The present invention provides an intelligent voltage control method applied to photovoltaic clusters, aiming to solve the problems of voltage regulation lag, insufficient coordinated control, lack of multi-objective optimization, etc. in the existing technology, and significantly improve the stability, reliability and economy of power grid operation.

[0008] The present invention provides an intelligent voltage control method applied to a photovoltaic cluster, the intelligent voltage control method comprising the following steps:

[0009] S1. Obtain historical operation data of the photovoltaic cluster;

[0010] S2. Building a voltage prediction model based on a long short-term memory network and the historical operation data of the photovoltaic cluster, wherein the voltage prediction model is used to predict the voltage change trend of the photovoltaic cluster;

[0011] S3. Obtaining the to-be-predicted operating data of the photovoltaic cluster, and using the to-be-predicted operating data of the photovoltaic cluster as input to the voltage prediction model for prediction. The voltage prediction model records the rated voltage of the photovoltaic cluster in different time periods in minutes, and uses the rated voltage in different time periods as the center of the circle to draw three voltage fluctuation circles, namely, a first voltage fluctuation circle, a second voltage fluctuation circle, and a third voltage fluctuation circle, with decreasing radii at the rated voltage in different time periods.

[0012] Calculating the number of tangents and intersections between the first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle and a preset voltage to obtain a voltage deviation number;

[0013] S4. Dynamically adjust the voltage of the photovoltaic cluster according to the voltage deviation.

[0014] Preferably, the radius of the first voltage fluctuation circle is 0.05V, the radius of the second voltage fluctuation circle is 0.033V, and the radius of the third voltage fluctuation circle is 0.017V.

[0015] Preferably, the preset voltage is 1.05V.

[0016] Preferably, step S4 includes the following sub-steps:

[0017] S41, defining the voltage deviation as N1, and the total operating time of the photovoltaic cluster operating data to be predicted as N;

[0018] S42, when When , the voltage of the photovoltaic cluster is not adjusted;

[0019] when When; regulating the voltage of the photovoltaic cluster;

[0020] when When; quickly respond and adjust the voltage of the photovoltaic cluster.

[0021] Preferably, the voltage variation trend of the photovoltaic cluster in different time periods is calculated based on the photovoltaic cluster operation data to be predicted, and a total value of the voltage variation trend is obtained;

[0022] Determine whether the total value of the voltage change trend exceeds a preset threshold: if so, adjust the voltage of the photovoltaic cluster.

[0023] Preferably, the photovoltaic cluster operation data to be predicted includes voltage data, current data and power data.

[0024] Compared with the existing technology, the present invention obtains historical operating data of the photovoltaic cluster; constructs a voltage prediction model based on the long-short-term memory network and the historical operating data of the photovoltaic cluster, and uses the voltage prediction model to predict the voltage change trend of the photovoltaic cluster; obtains the photovoltaic cluster operating data to be predicted, and uses the photovoltaic cluster operating data to be predicted as input to the voltage prediction model for prediction. The voltage prediction model records the rated voltage of the photovoltaic cluster in different time periods in minutes, and uses the rated voltage in different time periods as the center of the circle to draw three voltage fluctuation circles with decreasing radii at the rated voltage in different time periods. The first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle are calculated. The number of tangents and intersections between the first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle and the preset voltage is obtained to obtain the voltage deviation number; and the voltage of the photovoltaic cluster is dynamically adjusted according to the voltage deviation number. In this way, the intelligent voltage control method for photovoltaic clusters proposed by the present invention has faster voltage regulation and better coordinated control, significantly improving the stability, reliability, and economic efficiency of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention will be described in detail below with reference to the accompanying drawings. The above and other aspects of the present invention will become clearer and easier to understand through the detailed description made with reference to the following drawings. In the accompanying drawings:

[0026] Figure 1 This is a flowchart of an intelligent voltage control method for a photovoltaic cluster provided by an embodiment of the present invention;

[0027] Figure 2 It is a structural schematic diagram of a first voltage fluctuation circle, a second voltage fluctuation circle and a third voltage fluctuation circle of an intelligent voltage control method applied to a photovoltaic cluster provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0029] Please refer to Figure 1-Figure 2 The present invention provides an intelligent voltage control method for a photovoltaic cluster, the intelligent voltage control method comprising the following steps:

[0030] S1. Obtain historical operation data of the photovoltaic cluster.

[0031] In an embodiment of the present invention, Hall effect sensors are used to collect voltage U, current I, and power P data of each node in the photovoltaic cluster in real time to obtain historical operation data of the photovoltaic cluster.

[0032] S2. Building a voltage prediction model based on a long short-term memory network (LSTM) and the historical operation data of the photovoltaic cluster. The voltage prediction model is used to predict the voltage change trend of the photovoltaic cluster.

[0033] In an embodiment of the present invention, the present invention introduces a prediction model based on a long short-term memory network (LSTM), which can identify voltage fluctuation trends in advance, realize the upgrade from "ex post regulation" to "ex ante prediction and active intervention", and effectively improve the timeliness and accuracy of voltage regulation.

[0034] S3. Obtaining the to-be-predicted operating data of the photovoltaic cluster, and using the to-be-predicted operating data of the photovoltaic cluster as input to the voltage prediction model for prediction. The voltage prediction model records the rated voltage of the photovoltaic cluster in different time periods in minutes, and uses the rated voltage in different time periods as the center of the circle to draw three voltage fluctuation circles, namely, a first voltage fluctuation circle, a second voltage fluctuation circle, and a third voltage fluctuation circle, with decreasing radii at the rated voltage in different time periods.

[0035] Calculate the number of tangencies and intersections between the first, second, and third voltage fluctuation circles and a preset voltage (the preset voltage is 1.05V) (calculate the total number of tangencies and intersections between the three voltage fluctuation circles and 1.05V per minute from the start time to the end time) to obtain a voltage deviation number;

[0036] In the embodiment of the present invention, the radius of the first voltage fluctuation circle is 0.05V, the radius of the second voltage fluctuation circle is 0.033V, and the radius of the third voltage fluctuation circle is 0.017V.

[0037] The photovoltaic cluster operation data to be predicted includes voltage data, current data and power data.

[0038] S4. Dynamically adjust the voltage of the photovoltaic cluster according to the voltage deviation.

[0039] In this embodiment of the present invention, step S4 includes the following sub-steps:

[0040] S41. Define the voltage deviation as N1, and the total operating time of the photovoltaic cluster operating data to be predicted as N (if the total operating time is 35 minutes, then N is 35);

[0041] S42, when When , it indicates that the voltage is within the normal fluctuation range. At this time, only data is recorded, no regulation is triggered, and the voltage of the photovoltaic cluster is not adjusted;

[0042] when When the voltage fluctuation is slight, it is necessary to activate the dynamic adjustment mechanism and start the regulation to adjust the voltage of the photovoltaic cluster;

[0043] when Moderate fluctuations require rapid response and regulation to prevent subsequent severe voltage overshoots. Rapid response regulation is performed on the voltage of the PV cluster.

[0044] In an embodiment of the present invention, the voltage variation trend of the photovoltaic cluster in different time periods is calculated based on the to-be-predicted operation data of the photovoltaic cluster to obtain a total value of the voltage variation trend.

[0045] Specifically, by calculating the vertical coordinate difference ΔU and the horizontal coordinate difference Δt of the photovoltaic cluster at each minute voltage point, using the basic slope formula (where U t1 、U t2 The voltage change trend between two adjacent points is calculated by calculating the voltage values ​​at two adjacent time points t1 and t2 respectively.

[0046] Determine whether the total value of the voltage change trend exceeds a preset threshold: if so, adjust the voltage of the photovoltaic cluster.

[0047] Specifically, if K>1, it indicates that the voltage between the two points is on an upward trend; if K<1, it indicates that the voltage is on a downward trend. The K values ​​calculated from the beginning to the end of each stage are accumulated to obtain the total K value (the total value of the voltage change trend), that is, If K 总 >1, indicating that the overall voltage is on an upward trend, which may cause voltage deviation and requires timely intervention; if K 总 <1, the overall voltage shows a downward trend.

[0048] The present invention constructs a multi-turn voltage deviation identification model and a voltage trend evaluation mechanism, sets three response levels of "normal, mild, and moderate", and combines the cumulative judgment of real-time voltage change trends (K values) to achieve graded response and dynamic regulation, better adapting to the nonlinear fluctuation characteristics of voltage.

[0049] Compared with the existing technology, the present invention obtains historical operating data of the photovoltaic cluster; constructs a voltage prediction model based on the long-short-term memory network and the historical operating data of the photovoltaic cluster, and uses the voltage prediction model to predict the voltage change trend of the photovoltaic cluster; obtains the photovoltaic cluster operating data to be predicted, and uses the photovoltaic cluster operating data to be predicted as input to the voltage prediction model for prediction. The voltage prediction model records the rated voltage of the photovoltaic cluster in different time periods in minutes, and uses the rated voltage in different time periods as the center of the circle to draw three voltage fluctuation circles with decreasing radii at the rated voltage in different time periods. The first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle are calculated. The number of tangents and intersections between the first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle and the preset voltage is obtained to obtain the voltage deviation number; and the voltage of the photovoltaic cluster is dynamically adjusted according to the voltage deviation number. In this way, the intelligent voltage control method for photovoltaic clusters proposed by the present invention has faster voltage regulation and better coordinated control, significantly improving the stability, reliability, and economic efficiency of power grid operation.

[0050] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0051] The embodiments of the present invention are described above in conjunction with the accompanying drawings. What is disclosed is only a preferred embodiment of the present invention. However, 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 guidance of the present invention, ordinary technicians in this field can also make many forms and equivalent changes without departing from the scope of protection of the purpose of the present invention and the claims, which are all within the protection of the present invention.

Claims

1. An intelligent voltage control method applied to a photovoltaic cluster, characterized in that: The intelligent voltage control method comprises the following steps: S1. Obtain historical operation data of the photovoltaic cluster; S2. Building a voltage prediction model based on a long short-term memory network and the historical operation data of the photovoltaic cluster, wherein the voltage prediction model is used to predict the voltage change trend of the photovoltaic cluster; S3. Obtaining the to-be-predicted operating data of the photovoltaic cluster, and using the to-be-predicted operating data of the photovoltaic cluster as input to the voltage prediction model for prediction. The voltage prediction model records the rated voltage of the photovoltaic cluster in different time periods in minutes, and uses the rated voltage in different time periods as the center of the circle to draw three voltage fluctuation circles, namely, a first voltage fluctuation circle, a second voltage fluctuation circle, and a third voltage fluctuation circle, with decreasing radii at the rated voltage in different time periods. Calculating the number of tangents and intersections between the first voltage fluctuation circle, the second voltage fluctuation circle, and the third voltage fluctuation circle and a preset voltage to obtain a voltage deviation number; S4. Dynamically adjust the voltage of the photovoltaic cluster according to the voltage deviation.

2. The intelligent voltage control method for photovoltaic clusters according to claim 1, characterized in that: The radius of the first voltage fluctuation circle is 0.05V, the radius of the second voltage fluctuation circle is 0.033V, and the radius of the third voltage fluctuation circle is 0.017V.

3. The intelligent voltage control method for photovoltaic clusters according to claim 1, characterized in that: The preset voltage is 1.05V.

4. The intelligent voltage control method for photovoltaic clusters according to claim 1, characterized in that: Step S4 includes the following sub-steps: S41, defining the voltage deviation as N1, and the total operating time of the photovoltaic cluster operating data to be predicted as N; S42, when When , the voltage of the photovoltaic cluster is not adjusted; when When; regulating the voltage of the photovoltaic cluster; when When; quickly respond and adjust the voltage of the photovoltaic cluster.

5. The intelligent voltage control method for photovoltaic clusters according to claim 1, characterized in that: Calculating the voltage change trend of the photovoltaic cluster in different time periods based on the predicted operation data of the photovoltaic cluster to obtain a total value of the voltage change trend; Determine whether the total value of the voltage change trend exceeds a preset threshold: if so, adjust the voltage of the photovoltaic cluster.

6. The intelligent voltage control method for photovoltaic clusters according to claim 1, characterized in that: The photovoltaic cluster operation data to be predicted includes voltage data, current data and power data.

Images