Distributed photovoltaic cluster active power control method and system

Abstract

The invention belongs to the technical field of photovoltaic power generation, and discloses a distributed photovoltaic cluster active power control method and system. The method comprises the following steps: taking historical node voltage and historical generation power of a distributed photovoltaic cluster in different time periods as input data, and performing model training in combination with a BP neural network to obtain a power prediction model; determining ideal output power of the distributed photovoltaic cluster based on the power prediction model; obtaining the maximum output power of all power generation equipment of the distributed photovoltaic cluster; and controlling the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power, and reasonably controlling the inverter in combination with the ideal output power and the maximum output power by means of the BP neural network model through the above mode, so that the power adjustment error can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a distributed photovoltaic cluster active power control method and system. Background Art

[0002] With the continuous advancement of social industrialization, the demand for energy is also increasing, which also makes the consumption of bioenergy continue to increase. In order to change this situation, it is proposed to use solar power generation to meet its own electricity needs. However, in the application process, the disadvantages of photovoltaic power generation itself, such as volatility and intermittency, gradually become prominent, and this problem has gradually been taken seriously.

[0003] In order to solve this problem, the current approach is to evenly distribute the active power of the photovoltaic cluster or directly switch on and off the inverter, but this approach will cause a large power regulation error.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a distributed photovoltaic cluster active power control method and system, aiming to solve the technical problem that the current active power control method will cause large power regulation errors.

[0006] To achieve the above object, the present invention provides a distributed photovoltaic cluster active power control method, the distributed photovoltaic cluster active power control method comprising the following steps:

[0007] The historical node voltage and historical power generation of distributed photovoltaic clusters in different time periods are used as input data, combined with BP neural network for model training, to obtain a power prediction model;

[0008] Determining the ideal output power of the distributed photovoltaic cluster based on the power prediction model;

[0009] Obtaining the maximum output power of all power generation equipment in the distributed photovoltaic cluster;

[0010] The inverter of the distributed photovoltaic cluster is controlled based on the ideal output power and the maximum output power, and the output power of the inverter is associated with the active power of the distributed photovoltaic cluster.

[0011] In some embodiments, determining the ideal output power of the distributed photovoltaic cluster based on the power prediction model includes:

[0012] Determine a first predicted voltage, a second predicted voltage, a predicted current, a predicted number of times, and a predicted time of the distributed photovoltaic cluster based on the power prediction model;

[0013] The ideal output power is calculated based on the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time, and in combination with the impedance characteristics of the photovoltaic cluster, the initial current and the neural network threshold. The calculation formula is:

[0014]

[0015] Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

[0016] In some embodiments, obtaining the maximum output power of all power generation devices in the distributed photovoltaic cluster includes:

[0017] Obtaining the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment of the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, and the material transmission coefficient;

[0018] The maximum output power is calculated based on the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the material itself, the material transmission coefficient and the number of equipment. The calculation formula is:

[0019]

[0020] Among them, Q max represents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

[0021] In some embodiments, the controlling the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power includes:

[0022] Calculating a power difference between the ideal output power and the maximum output power;

[0023] Comparing the power difference with a preset difference threshold;

[0024] The start / stop quantity and output power of the inverters of the distributed photovoltaic cluster are adjusted based on the comparison result.

[0025] In some embodiments, adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result includes:

[0026] If the comparison result is that the power difference is greater than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster;

[0027] Determine the maximum number of shutdowns according to the start-stop state matrix and the preset difference threshold;

[0028] Determining a target shutdown number according to the minimum operation number of the inverter and the maximum shutdown number;

[0029] Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target shutdown quantity;

[0030] The output power of the inverter after the start / stop state is adjusted is controlled.

[0031] In some embodiments, adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result includes:

[0032] If the comparison result is that the power difference is less than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster;

[0033] Determine the minimum startup quantity according to the start-stop state matrix and the preset difference threshold;

[0034] Determine a target startup number according to the minimum running number of the inverter and the minimum startup number;

[0035] Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target startup quantity;

[0036] The output power of the inverter after the start / stop state is adjusted is controlled.

[0037] In some embodiments, controlling the output power of the inverter after the start / stop state is adjusted includes:

[0038] Determine a first inverter set before start / stop state adjustment;

[0039] Determine a second inverter set after the start / stop state is adjusted;

[0040] Inverters of the same type or regulation performance in the first inverter set and the second inverter set are set to have the same output power.

[0041] In addition, to achieve the above purpose, the present invention also proposes a distributed photovoltaic cluster active power control system, the distributed photovoltaic cluster active power control system comprising:

[0042] A construction module is used to use the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combine the BP neural network to perform model training to obtain a power prediction model;

[0043] A calculation module, used to determine the ideal output power of the distributed photovoltaic cluster based on the power prediction model;

[0044] The calculation module is used to obtain the maximum output power of all power generation equipment in the distributed photovoltaic cluster;

[0045] A control module is used to control the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power, and the output power of the inverter is associated with the active power of the distributed photovoltaic cluster.

[0046] In some embodiments, the calculation module is used to determine the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time of the distributed photovoltaic cluster based on the power prediction model;

[0047] The ideal output power is calculated based on the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time, and in combination with the impedance characteristics of the photovoltaic cluster, the initial current and the neural network threshold. The calculation formula is:

[0048]

[0049] Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

[0050] In some embodiments, the calculation module is used to obtain the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, and the material transmission coefficient;

[0051] The maximum output power is calculated based on the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the material itself, the material transmission coefficient and the number of equipment. The calculation formula is:

[0052]

[0053] Among them, Q maxrepresents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

[0054] The present invention obtains a power prediction model by taking the historical node voltage and historical power generation of a distributed photovoltaic cluster in different time periods as input data and combining it with a BP neural network for model training; the ideal output power of the distributed photovoltaic cluster is determined based on the power prediction model; the maximum output power of all power generation equipment in the distributed photovoltaic cluster is obtained; and the inverter of the distributed photovoltaic cluster is controlled based on the ideal output power and the maximum output power. In the above manner, the inverter is reasonably controlled with the help of a BP neural network model and in combination with the ideal output power and the maximum output power, so that the power regulation error can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a first embodiment of a distributed photovoltaic cluster active power control method of the present invention;

[0056] Figure 2 This is a structural block diagram of the first embodiment of the distributed photovoltaic cluster active power control system of the present invention.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0059] The embodiment of the present invention provides a distributed photovoltaic cluster active power control method, referring to Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a distributed photovoltaic cluster active power control method according to the present invention.

[0060] In this embodiment, the distributed photovoltaic cluster active power control method includes the following steps:

[0061] Step S10: taking the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combining the BP neural network to perform model training to obtain a power prediction model.

[0062] In this embodiment, the executor of this embodiment is a distributed photovoltaic cluster active power control device, wherein the distributed photovoltaic cluster active power control device has functions such as data processing, data communication and program running. The distributed photovoltaic cluster active power control device can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0063] It should be noted that with the continuous advancement of the social industrialization process, the demand for energy is also increasing, which also makes the consumption of bioenergy continue to increase. In order to change this situation, it is proposed to use solar power generation to meet its own electricity needs. However, in the application process, the disadvantages of the volatility and intermittent nature of photovoltaic power generation have gradually become prominent, and this problem has gradually been taken seriously. In order to solve this problem, the current means are to evenly distribute the active power distribution of the photovoltaic cluster or directly switch on the inverter, but this method will cause a large power regulation error.

[0064] In order to solve the above technical problems, this embodiment uses the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, combines the BP neural network for model training, and obtains a power prediction model; determines the ideal output power of the distributed photovoltaic cluster based on the power prediction model; obtains the maximum output power of all power generation equipment in the distributed photovoltaic cluster; controls the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power. Through the above method, with the help of the BP neural network model, and in combination with the ideal output power and the maximum output power, the inverter is reasonably controlled, which can effectively reduce the power regulation error. Specifically, it can be achieved as follows.

[0065] In the specific implementation, in this embodiment, a power prediction model is first constructed. Specifically, the historical node voltage and historical power generation power of the distributed photovoltaic cluster in different time periods are used as input data, and the BP neural network is combined for model training to obtain a power prediction model.

[0066] It should be noted that the BP neural network has the characteristics of continuous feedback and self-learning. There is no definite mapping relationship between its input data and output data. Its specific principle is to reduce the prediction error through the continuous iteration of a large amount of data, and to continuously feedback and correct the input data so that the error between the final output data and the actual data is minimized. As time goes by, the more initial data it obtains, and through continuous training, the network parameters corresponding to the ideal error output data can be obtained, and based on this, the power prediction output data closest to the actual data can be obtained.

[0067] Step S20: determining the ideal output power of the distributed photovoltaic cluster based on the power prediction model.

[0068] In the specific implementation, the first predicted voltage, second predicted voltage, predicted current, predicted times and predicted time of the distributed photovoltaic cluster can be obtained according to the power prediction model. Then the impedance characteristics, initial current and neural network threshold of the photovoltaic cluster are obtained, and finally the ideal output power Q can be calculated according to the above parameters. e The specific calculation formula is:

[0069]

[0070] Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

[0071] Step S30: Acquire the maximum output power of all power generation equipment in the distributed photovoltaic cluster.

[0072] In the specific implementation, the maximum output power of all power generation equipment in the distributed photovoltaic cluster can be calculated by the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, the material transmission coefficient and the number of equipment. The specific calculation formula is:

[0073]

[0074] Among them, Q max represents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

[0075] Step S40: controlling the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power.

[0076] In the specific implementation, after obtaining the ideal output power and the maximum output power, the power difference between the ideal output power and the maximum output power is calculated, and then the calculated power difference is compared with the preset difference threshold, and finally the start and stop number and output power of the inverter of the distributed photovoltaic cluster are adjusted according to the comparison result.

[0077] It should be noted that the output power of a photovoltaic cluster includes active power and reactive power. The reactive power is usually compensated by grid equipment, while the active power part, that is, the output power of the inverter, can be controlled by adjusting the overall output power of the inverter (for example, adjusting the number of inverter starts and stops and the output power of a single inverter).

[0078] In a specific implementation, the preset difference threshold in this embodiment can be set to 0. Assuming that the power difference between the ideal output power and the maximum output power is △Q, if the comparison result is that the power difference is greater than the preset difference threshold, that is, △Q>0, this situation indicates that when the photovoltaic power station is operating normally, the maximum output power obtained by the photovoltaic inverter it possesses in the next control cycle is greater than the dispatch value of the overall power grid. In view of this situation, a shutdown strategy is adopted in this embodiment. First, it is necessary to construct the start-stop state matrix of the inverter of the distributed photovoltaic cluster, for example, Q1=[Q 11 ,Q 12 ,…,Q 1n ], where the elements in the matrix Q1 represent the start and stop states of the corresponding photovoltaic inverters, that is, when r j =0, it means that the inverter maintains the current operating state; and when r j =1, it means the inverter is in shutdown state. stop =Q1R1, R1=[r1,r2,…,r j ], so the maximum number of downtimes Finally, the judgment is carried out based on the preset difference threshold, for example, b1 = Q1R1-△Q, specifically (1) setting r1 = r2 = ... = r j =0, if b1<0, then continue to execute the following steps; (2) Set r1=1, r2=…=r j =0, if b1<0, then continue to execute the following steps; (3) Set r1=1, r2=1, r3…=r j =0If b1<0, then continue to set r3=1 until r1=r2=…=r j =1 or b≥0, and stop, recording the number of 1s in R at this moment. After obtaining the maximum number of shutdowns, the target number of shutdowns can be calculated based on the minimum number of running and the maximum number of shutdowns of the inverter, for example, N1=ON stop , where O represents the minimum number of PV inverter operations in the next cycle, and N1 is the target shutdown number.

[0079] Furthermore, if the comparison result is that the power difference is less than the preset difference threshold, that is, △Q < 0, this situation indicates that when the photovoltaic power station is operating normally, the maximum output power of the photovoltaic inverter it possesses in the next control cycle is less than the dispatch value of the entire power grid. In view of this situation, the startup strategy is adopted in this embodiment. First, the start-stop state matrix of the inverter of the distributed photovoltaic cluster needs to be constructed, for example, Q2 = [Q 21 ,Q 22 ,…,Q 2n ], where the elements in the matrix Q2 represent the start / stop states of the corresponding photovoltaic inverters, that is, when r k =0, it means that the inverter maintains the current operating state; and when r k =1, it means the inverter is in shutdown state. start =Q2R2, R2=[r1,r2,…,r k ], so the maximum number of downtimes Finally, the judgment is carried out based on the preset difference threshold, for example, b2 = Q2R2-△Q, specifically (1) setting r1 = r2 = ... = r k =0, if b2<0, then continue to execute the following steps; (2) Set r1=1, r2=…=r k =0, if b2<0, then continue to execute the following steps; (3) Set r1=1, r2=1, r3…=r k =0If b2<0, then continue to set r3=1 until r1=r2=…=r k =1 or b2≥0, and stop, recording the number of 1s in R2 at this moment. After obtaining the maximum number of startups, the target startup number can be calculated based on the minimum number of running and the maximum number of shutdowns of the inverter, for example, N2=ON start , where O represents the minimum number of PV inverters in operation in the next cycle, and N2 is the target number of startups.

[0080] The above method is to control the start and stop number of inverters, shut down or start the corresponding number of inverters according to the target shutdown number or the target startup number. After completing the adjustment of the start and stop state, the output power is also adjusted in this embodiment, specifically, determining the first inverter set before the start and stop state adjustment; determining the second inverter set after the start and stop state adjustment; setting the inverters with the same type or adjustment performance in the first inverter set and the second inverter set to the same output power.

[0081] It should be noted that when the shutdown strategy is adopted, the number of inverters in the first inverter set is greater than the number of inverters in the second inverter set. After stopping some inverters in the first inverter set, inverters with the same type or regulation performance are determined from the second inverter set, and then the current output power of these inverters is adjusted to the historical output power of the inverters that have been stopped. Similarly, when the startup strategy is adopted, the number of inverters in the first inverter set is less than the number of inverters in the second inverter set. For this situation, in this embodiment, an inverter with the same type or regulation performance as the already running inverter in the first inverter set is determined from the newly started inverters in the second inverter set, and then its power is set to the output power of the inverter with the same type or regulation performance as the already running inverter.

[0082] This embodiment uses the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combines the BP neural network for model training to obtain a power prediction model; determines the ideal output power of the distributed photovoltaic cluster based on the power prediction model; obtains the maximum output power of all power generation equipment in the distributed photovoltaic cluster; and controls the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power. In the above manner, with the help of the BP neural network model, and in combination with the ideal output power and the maximum output power, the inverter is reasonably controlled, which can effectively reduce the power regulation error.

[0083] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the distributed photovoltaic cluster active power control system of the present invention.

[0084] like Figure 2 As shown, the distributed photovoltaic cluster active power control system proposed in the embodiment of the present invention includes:

[0085] The construction module 10 is used to use the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combine the BP neural network to perform model training to obtain a power prediction model.

[0086] The calculation module 20 is used to determine the ideal output power of the distributed photovoltaic cluster based on the power prediction model.

[0087] The calculation module 20 is used to obtain the maximum output power of all power generation devices in the distributed photovoltaic cluster.

[0088] The control module 30 is used to control the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power, and the output power of the inverter is associated with the active power of the distributed photovoltaic cluster.

[0089] This embodiment uses the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combines the BP neural network for model training to obtain a power prediction model; determines the ideal output power of the distributed photovoltaic cluster based on the power prediction model; obtains the maximum output power of all power generation equipment in the distributed photovoltaic cluster; and controls the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power. In the above manner, with the help of the BP neural network model, and in combination with the ideal output power and the maximum output power, the inverter is reasonably controlled, which can effectively reduce the power regulation error.

[0090] In some embodiments, the calculation module 20 is used to determine the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time of the distributed photovoltaic cluster based on the power prediction model;

[0091] The ideal output power is calculated based on the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time, and in combination with the impedance characteristics of the photovoltaic cluster, the initial current and the neural network threshold. The calculation formula is:

[0092]

[0093] Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

[0094] In some embodiments, the calculation module 20 is used to obtain the maximum output power of all power generation devices in the distributed photovoltaic cluster, including:

[0095] Obtaining the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment of the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, and the material transmission coefficient;

[0096] The maximum output power is calculated based on the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the material itself, the material transmission coefficient and the number of equipment. The calculation formula is:

[0097]

[0098] Among them, Q max represents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

[0099] In some embodiments, the control module 30 is used to calculate the power difference between the ideal output power and the maximum output power;

[0100] Comparing the power difference with a preset difference threshold;

[0101] The start / stop quantity and output power of the inverters of the distributed photovoltaic cluster are adjusted based on the comparison result.

[0102] In some embodiments, the control module 30, used for adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result, includes:

[0103] If the comparison result is that the power difference is greater than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster;

[0104] Determine the maximum number of shutdowns according to the start-stop state matrix and the preset difference threshold;

[0105] Determining a target shutdown number according to the minimum operation number of the inverter and the maximum shutdown number;

[0106] Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target shutdown quantity;

[0107] The output power of the inverter after the start / stop state is adjusted is controlled.

[0108] In some embodiments, the control module 30, used for adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result, includes:

[0109] If the comparison result is that the power difference is less than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster;

[0110] Determine the minimum startup quantity according to the start-stop state matrix and the preset difference threshold;

[0111] Determine a target startup number according to the minimum running number of the inverter and the minimum startup number;

[0112] Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target startup quantity;

[0113] The output power of the inverter after the start / stop state is adjusted is controlled.

[0114] In some embodiments, the control module 30 is used to control the output power of the inverter after the start / stop state is adjusted, including:

[0115] Determine a first inverter set before start / stop state adjustment;

[0116] Determine a second inverter set after the start / stop state is adjusted;

[0117] Inverters of the same type or regulation performance in the first inverter set and the second inverter set are set to have the same output power.

[0118] An embodiment of the present application also provides a distributed photovoltaic cluster active power control device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store the distributed photovoltaic cluster active power control program; the processor is used to implement the above-mentioned distributed photovoltaic cluster active power control method when executing the program stored in the memory.

[0119] The communication bus mentioned in the above distributed photovoltaic cluster active power control device can be a peripheral component interconnect standard (English: Peripheral Component Interconnect, referred to as: PCI) bus or an extended industry standard architecture (English: Extended Industry Standard Architecture, referred to as: EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0120] The communication interface is used for communication between the above-mentioned distributed photovoltaic cluster active power control device and other devices.

[0121] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0122] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0123] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0124] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0125] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0126] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0127] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0128] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0129] In addition, for technical details not fully described in this embodiment, reference may be made to the distributed photovoltaic cluster active power control method provided in any embodiment of the present invention, and will not be repeated here.

[0130] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0131] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0133] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0134] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

Claims

1. A distributed photovoltaic cluster active power control method, characterized in that: The distributed photovoltaic cluster active power control method comprises: The historical node voltage and historical power generation of distributed photovoltaic clusters in different time periods are used as input data, combined with BP neural network for model training, to obtain a power prediction model; Determining the ideal output power of the distributed photovoltaic cluster based on the power prediction model; Obtaining the maximum output power of all power generation equipment in the distributed photovoltaic cluster; The inverter of the distributed photovoltaic cluster is controlled based on the ideal output power and the maximum output power, and the output power of the inverter is associated with the active power of the distributed photovoltaic cluster.

2. The distributed photovoltaic cluster active power control method according to claim 1, characterized in that: The determining the ideal output power of the distributed photovoltaic cluster based on the power prediction model includes: Determine a first predicted voltage, a second predicted voltage, a predicted current, a predicted number of times, and a predicted time of the distributed photovoltaic cluster based on the power prediction model; The ideal output power is calculated based on the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time, and in combination with the impedance characteristics of the photovoltaic cluster, the initial current and the neural network threshold. The calculation formula is: Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

3. The distributed photovoltaic cluster active power control method according to claim 1, characterized in that: The obtaining of the maximum output power of all power generation equipment in the distributed photovoltaic cluster includes: Obtaining the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment of the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, and the material transmission coefficient; The maximum output power is calculated based on the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the material itself, the material transmission coefficient and the number of equipment. The calculation formula is: Among them, Q max represents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

4. The distributed photovoltaic cluster active power control method according to claim 1, characterized in that: The controlling the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power includes: Calculating a power difference between the ideal output power and the maximum output power; Comparing the power difference with a preset difference threshold; The start / stop quantity and output power of the inverters of the distributed photovoltaic cluster are adjusted based on the comparison result.

5. The distributed photovoltaic cluster active power control method according to claim 4, characterized in that: The step of adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result includes: If the comparison result is that the power difference is greater than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster; Determine the maximum number of shutdowns according to the start-stop state matrix and the preset difference threshold; Determining a target shutdown number according to the minimum operation number of the inverter and the maximum shutdown number; Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target shutdown quantity; The output power of the inverter after the start / stop state is adjusted is controlled.

6. The distributed photovoltaic cluster active power control method according to claim 4, characterized in that: The step of adjusting the start / stop quantity and output power of the inverters of the distributed photovoltaic cluster based on the comparison result includes: If the comparison result is that the power difference is less than the preset difference threshold, constructing a start / stop state matrix of the inverter of the distributed photovoltaic cluster; Determine the minimum startup quantity according to the start-stop state matrix and the preset difference threshold; Determine a target startup number according to the minimum running number of the inverter and the minimum startup number; Controlling the start and stop of the inverter of the distributed photovoltaic cluster according to the target startup quantity; The output power of the inverter after the start / stop state is adjusted is controlled.

7. The distributed photovoltaic cluster active power control method according to claim 5 or 6, characterized in that: The controlling of the output power of the inverter after the start / stop state is adjusted includes: Determine a first inverter set before start / stop state adjustment; Determine a second inverter set after the start / stop state is adjusted; Inverters of the same type or regulation performance in the first inverter set and the second inverter set are set to have the same output power.

8. A distributed photovoltaic cluster active power control system, characterized in that: The distributed photovoltaic cluster active power control system includes: A construction module is used to use the historical node voltage and historical power generation of the distributed photovoltaic cluster in different time periods as input data, and combine the BP neural network to perform model training to obtain a power prediction model; A calculation module, used to determine the ideal output power of the distributed photovoltaic cluster based on the power prediction model; The calculation module is used to obtain the maximum output power of all power generation equipment in the distributed photovoltaic cluster; A control module is used to control the inverter of the distributed photovoltaic cluster based on the ideal output power and the maximum output power, and the output power of the inverter is associated with the active power of the distributed photovoltaic cluster.

9. The distributed photovoltaic cluster active power control system according to claim 8, characterized in that: The calculation module is used to determine the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time of the distributed photovoltaic cluster based on the power prediction model; The ideal output power is calculated based on the first predicted voltage, the second predicted voltage, the predicted current, the predicted number of times and the predicted time, and in combination with the impedance characteristics of the photovoltaic cluster, the initial current and the neural network threshold. The calculation formula is: Among them, Q e is the ideal output power, U and U1 are the first predicted voltage and the second predicted voltage respectively, I1 represents the predicted current, I0 represents the initial current, B represents the neural network threshold, L represents the number of predictions, t represents the prediction time, and r represents the impedance characteristics of the photovoltaic cluster.

10. The distributed photovoltaic cluster active power control system according to claim 8, characterized in that: The calculation module is used to obtain the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment of the distributed photovoltaic cluster, the impedance coefficient of the materials themselves, and the material transmission coefficient; The maximum output power is calculated based on the current temperature of the distributed photovoltaic cluster, the temperature coefficient of the materials of all power generation equipment in the distributed photovoltaic cluster, the impedance coefficient of the material itself, the material transmission coefficient and the number of equipment. The calculation formula is: Among them, Q max represents the maximum output power, b represents the temperature coefficient, l represents the impedance coefficient of the material itself, λ1, λ2 and λ3 represent the material transmission coefficient, T represents the current temperature, and N represents the number of devices.

Images