Grid-connected performance evaluation and early warning system and method based on big data

Abstract

The invention discloses a grid-connected performance evaluation and early warning system and method based on big data, and relates to the technical field of grid-connected performance evaluation.The system comprises an equipment data acquisition module, a performance comprehensive evaluation module, a performance prediction module and a grid-connected performance early warning module, and the equipment data acquisition module and the performance comprehensive evaluation module are arranged. The grid-connected performance data of the grid-connected equipment is collected in real time, meanwhile, the operation data of the power equipment connected with the grid-connected equipment is collected, the performance of the grid-connected equipment is deeply and comprehensively analyzed regularly, and the current performance of the grid-connected equipment is accurately analyzed. A performance expression prediction module and a grid-connected performance early warning module are set, a simulation operation model of the grid-connected equipment and the power equipment is constructed, the operation influence condition of the current performance of the grid-connected equipment on other power equipment is simulated and analyzed, and then a comprehensive and three-dimensional grid-connected equipment performance evaluation early warning mechanism is established.

Description

Technical Field

[0001] The present invention relates to the technical field of grid-connected performance evaluation, and more specifically, to a grid-connected performance evaluation early warning system and method based on big data. Background Art

[0002] With the continuous development of power systems and the improvement of their intelligence level, grid-connected equipment plays a vital role in power transmission and distribution. As a bridge connecting power equipment and the power grid, grid-connected equipment ensures efficient and stable exchange of energy and is a key element in building a complete energy conversion and transmission system. They not only need to bear the connection requirements of various types of power equipment such as generators and transformers, but also need to adapt to the complex interactions between different power equipment to ensure the stable operation of the entire power system.

[0003] With the expansion of power grid scale and the increase of electricity demand, grid-connected equipment needs to withstand greater loads and pressures, and its performance stability and reliability become important guarantees for the safe operation of power systems.

[0004] Traditionally, the performance evaluation of grid-connected equipment mainly relies on manual inspections and regular testing. This method is not only time-consuming and labor-intensive, but can only be evaluated based on the current performance data of the grid-connected equipment. It is unable to deeply analyze the impact of the current performance of the grid-connected equipment on the operation of other power equipment.

[0005] Therefore, it is particularly important to develop a grid-connected performance evaluation and early warning system based on big data. Summary of the invention

[0006] In view of the deficiencies in the prior art, the object of the present invention is to provide a grid-connected performance evaluation and early warning system and method based on big data.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The grid-connected performance evaluation and early warning system based on big data includes equipment data acquisition module, performance evaluation module, performance prediction module, and grid-connected performance early warning module;

[0009] The device data acquisition module is used to determine the power equipment to which the grid-connected device is connected, collect various types of grid-connected performance data of the grid-connected device and the operating data of the power equipment in real time, perform feature extraction on the various types of grid-connected performance data of the grid-connected device and the operating data of the power equipment, and obtain the performance characteristics of the various types of grid-connected performance data of the grid-connected device and the operating characteristics of the power equipment;

[0010] The performance comprehensive evaluation module obtains the performance comprehensive evaluation value of the grid-connected device after each performance evaluation period;

[0011] The performance prediction module builds a grid-connected simulation operation model based on the performance characteristics of various types of grid-connected performance data of the grid-connected equipment and the operation characteristics of the power equipment. The grid-connected simulation operation model performs a simulation operation for a performance evaluation duration, thereby obtaining a performance prediction value of the grid-connected equipment;

[0012] The grid-connected performance warning module obtains a grid-connected performance evaluation warning value according to the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, and determines whether to send a grid-connected equipment performance warning signal based on a comparison result between the grid-connected performance evaluation warning value and the grid-connected performance evaluation warning threshold.

[0013] Furthermore, the comprehensive performance evaluation value of the grid-connected equipment is obtained through the following steps: obtaining the performance evaluation value of each type of grid-connected performance data, setting the high performance evaluation value and the low performance evaluation value, when the performance evaluation value is greater than or equal to the high performance evaluation value, marking the corresponding type of grid-connected performance data as satisfactory performance data, when the performance evaluation value is less than or equal to the low performance evaluation value, marking the corresponding type of grid-connected performance data as gap performance data, when the performance evaluation value is between the high performance evaluation value and the low performance evaluation value, marking the corresponding type of grid-connected performance data as normal performance data, marking the total number of satisfactory performance data as Bte, marking the total number of gap performance data as Mks, summing the performance evaluation values ​​of the normal performance data and taking the average, obtaining the normal performance evaluation value Pmd, and using the formula The comprehensive performance evaluation value Ustd of the grid-connected equipment is obtained, where ua is the satisfactory performance coefficient, ub is the gap performance coefficient, and uc is the conventional performance coefficient.

[0014] Furthermore, the performance evaluation value of each type of grid-connected performance data is obtained through the following steps: obtaining a performance evaluation model for each type of grid-connected performance data, inputting the performance characteristics of each type of grid-connected performance data into the corresponding performance evaluation model, and outputting the performance evaluation value of each type of grid-connected performance data.

[0015] Furthermore, a grid-connected simulation operation model is constructed based on the performance characteristics of various types of grid-connected performance data of the grid-connected equipment and the operating characteristics of the power equipment. Specifically, simulation software is selected, and a grid-connected equipment body and other power equipment bodies are created in the simulation software based on the performance characteristics of various types of grid-connected performance data of the grid-connected equipment and the operating characteristics of the power equipment. Parameters are set for the grid-connected equipment body and the power equipment body, and an electrical connection is established between the grid-connected equipment body and each power equipment body to construct a grid-connected simulation operation model. The grid-connected simulation operation model can simulate the operation of the grid-connected equipment body and the power equipment body.

[0016] Furthermore, the grid-connected simulation operation model performs a simulation operation for a performance evaluation duration, and then obtains the performance prediction value of the grid-connected equipment, specifically: the performance evaluation duration is divided into m simulation evaluation periods of equal duration, the power equipment impact value of each simulation evaluation period is obtained, the power equipment impact value of all simulation evaluation periods is summed and averaged, and the equipment impact average Kzy is obtained, all power equipment impact values ​​are sorted in the order of the simulation evaluation periods, the two adjacent power equipment impact values ​​after sorting are summed, and the equipment continuous impact value is obtained, and the equipment continuous impact boundary value is set. When the equipment continuous impact value is greater than or equal to the equipment continuous impact boundary value, the continuous impact number is increased by one, and the continuous impact number is marked as Dbp. The difference between the two adjacent power equipment impact values ​​after sorting is calculated and the absolute value is taken to obtain the equipment fluctuation impact value, and the equipment fluctuation impact boundary value is set. When the equipment fluctuation impact value is greater than or equal to the equipment fluctuation impact boundary value, the fluctuation impact number is increased by one, and the fluctuation impact number is marked as Tmg. The formula is used The performance prediction value Astb of the grid-connected equipment is obtained, where m1 is the equipment influence coefficient, m2 is the continuous influence coefficient, and m3 is the fluctuation influence coefficient.

[0017] Furthermore, the impact value of the power equipment in the simulation evaluation period is obtained by the following steps: collecting the operation data of each power equipment body in the simulation evaluation period, extracting the characteristics of the operation data of each power equipment body, obtaining the operation characteristics of each power equipment body, and then obtaining the operation fluctuation value Ecb of each power equipment body, c = 1, 2, ..., C, C is the number of the power equipment body, setting the operation fluctuation coefficient to Fb, summing the operation fluctuation values ​​of the power equipment bodies of the same equipment type and taking the average to obtain the equipment fluctuation value of the equipment type, setting the equipment fluctuation threshold, when the equipment fluctuation value is greater than or equal to the equipment fluctuation threshold, increasing the number of fluctuation equipment types by one, marking the number of fluctuation equipment types as Szx, and using the formula The power equipment impact value Lbs of the simulation evaluation period is obtained, where e1 is the fluctuation equipment type coefficient.

[0018] Furthermore, the operation fluctuation value of the power equipment body is obtained through the following steps: obtaining the equipment type of the power equipment body, obtaining an operation fluctuation analysis model of the equipment type, inputting the operation characteristics of the power equipment body into the operation fluctuation analysis model, and outputting the operation fluctuation analysis model to obtain the operation fluctuation value of the power equipment body.

[0019] Furthermore, the grid-connected performance evaluation warning value is obtained according to the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, specifically: using the formula The grid-connected performance evaluation warning value Rsw is obtained, where f1 is the comprehensive performance evaluation coefficient and f2 is the performance prediction coefficient.

[0020] Furthermore, the grid connection performance evaluation and early warning method based on big data includes the following steps:

[0021] Step 1: Determine the power equipment to which the grid-connected equipment is connected, and collect various types of grid-connected performance data of the grid-connected equipment and the operation data of the power equipment in real time;

[0022] Step 2: Extracting features of various types of grid-connected performance data of grid-connected equipment and operating data of power equipment to obtain performance features of various types of grid-connected performance data of grid-connected equipment and operating features of power equipment;

[0023] Step 3: After each performance evaluation period, obtain the comprehensive performance evaluation value of the grid-connected equipment;

[0024] Step 4: Building a grid-connected simulation operation model based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operation characteristics of power equipment;

[0025] Step 5: The grid-connected simulation operation model performs a simulation operation for a performance evaluation period to obtain the performance prediction value of the grid-connected equipment;

[0026] Step 6: Obtain a grid-connected performance evaluation warning value based on the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, and determine whether to send a grid-connected equipment performance warning signal based on a comparison result between the grid-connected performance evaluation warning value and the grid-connected performance evaluation warning threshold.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The method of the present invention can accurately analyze the current performance of the grid-connected equipment, and simultaneously simulate and analyze the impact of the current performance of the grid-connected equipment on the operation of other power equipment. Combined with the performance of the grid-connected equipment itself and the impact on the operation of the power equipment, the performance dynamic early warning of the grid-connected equipment is met;

[0029] 2. The system of the present invention not only collects the grid-connected performance data of the grid-connected equipment in real time, but also collects the operating data of the power equipment connected to the grid-connected equipment by setting up an equipment data acquisition module and a performance evaluation module, and regularly conducts in-depth and comprehensive analysis of the performance of the grid-connected equipment. It sets up a performance prediction module and a grid-connected performance early warning module, constructs a simulation operation model of the grid-connected equipment and the power equipment, and then establishes a comprehensive and three-dimensional grid-connected equipment performance evaluation and early warning mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1A method flow chart of a grid-connected performance evaluation and early warning method based on big data;

[0031] Figure 2 System module diagram of the grid-connected performance evaluation and early warning system based on big data;

[0032] Figure 3 The present invention is a flow chart for obtaining the operation fluctuation value of the power equipment body. DETAILED DESCRIPTION

[0033] Example 1: Reference Figure 1 , the grid-connected performance evaluation and early warning method based on big data includes the following steps:

[0034] Step 1: Determine the power equipment to which the grid-connected equipment is connected, and collect various types of grid-connected performance data of the grid-connected equipment and the operating data of the power equipment in real time.

[0035] Step 2: Extract features of various types of grid-connected performance data of grid-connected equipment and operating data of power equipment to obtain performance features of various types of grid-connected performance data of grid-connected equipment and operating features of power equipment.

[0036] Step 3: After each performance evaluation period, obtain the comprehensive performance evaluation value of the grid-connected equipment.

[0037] Step 4: Construct a grid-connected simulation operation model based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operation characteristics of power equipment.

[0038] Step 5: The grid-connected simulation operation model performs a simulation operation for a performance evaluation period to obtain the performance prediction value of the grid-connected equipment.

[0039] Step 6: Obtain a grid-connected performance evaluation warning value based on the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, and determine whether to send a grid-connected equipment performance warning signal based on a comparison result between the grid-connected performance evaluation warning value and the grid-connected performance evaluation warning threshold.

[0040] The above method can accurately analyze the current performance of the grid-connected equipment, and simultaneously simulate and analyze the impact of the current performance of the grid-connected equipment on the operation of other power equipment. Combined with the performance of the grid-connected equipment itself and its impact on the operation of power equipment, the performance warning of the grid-connected equipment can be dynamically completed.

[0041] Example 2: Reference Figure 2-Figure 3 The grid-connected performance evaluation and early warning system based on big data includes equipment data acquisition module, performance comprehensive evaluation module, performance prediction module and grid-connected performance early warning module.

[0042] Equipment data acquisition module: determine the power equipment connected to the grid-connected equipment (grid-connected equipment is a device that connects power equipment to the power grid for energy exchange. It is mainly used to connect power equipment such as generators and transformers in the power system to the power grid to form a complete energy conversion and transmission system. Therefore, the grid-connected equipment needs to be connected to multiple power equipment at the same time, and there are multiple types of power equipment), collect various types of grid-connected performance data of the grid-connected equipment and the operating data of the power equipment in real time, and extract features from various types of grid-connected performance data of the grid-connected equipment (grid-connected performance data types include active power data, reactive power data, current harmonic total distortion data, etc., and various types of grid-connected performance data jointly reflect the performance of the grid-connected equipment) and the operating data of the power equipment to obtain the performance characteristics of various types of grid-connected performance data of the grid-connected equipment and the operating characteristics of the power equipment.

[0043] Performance evaluation module: Set the performance evaluation duration to T asse (T asse It is the duration preset by the system. When the grid-connected equipment is running, the performance evaluation duration is infinitely looped). After each performance evaluation duration, the comprehensive performance evaluation value of the grid-connected equipment is obtained.

[0044] The comprehensive performance evaluation value of the grid-connected equipment is obtained through the following steps: obtaining a performance evaluation model for each type of grid-connected performance data, inputting the performance characteristics of each type of grid-connected performance data into the corresponding performance evaluation model, outputting a performance evaluation value for each type of grid-connected performance data, setting a high performance evaluation value and a low performance evaluation value (the high performance evaluation value is greater than the low performance evaluation value, and both the high performance evaluation value and the low performance evaluation value are system preset values), when the performance evaluation value is greater than or equal to the high performance evaluation value, marking the corresponding type of grid-connected performance data as satisfactory performance data, when the performance evaluation value is less than or equal to the low performance evaluation value, marking the corresponding type of grid-connected performance data as gap performance data, when the performance evaluation value is between the high performance evaluation value and the low performance evaluation value, marking the corresponding type of grid-connected performance data as normal performance data, marking the total number of satisfactory performance data as Bte, marking the total number of gap performance data as Mks, summing the performance evaluation values ​​of normal performance data and taking the average to obtain a normal performance evaluation value Pmd, and using the formula The comprehensive performance evaluation value Ustd of the grid-connected equipment is obtained, where ua is the satisfactory performance coefficient, ub is the gap performance coefficient, and uc is the conventional performance coefficient. The value of ua is 0.89, the value of ub is 0.81, and the value of uc is 1.25.

[0045] Different types of grid-connected performance data have different judgment criteria. Therefore, each type of grid-connected performance data corresponds to an independent performance evaluation model. The difference between each performance evaluation model lies in the difference in training data. Therefore, this embodiment only illustrates the construction method of the performance evaluation model of one type of grid-connected performance data, and no longer enumerates the construction methods of the performance evaluation models of various types of grid-connected performance data.

[0046] The performance evaluation model of active power data is constructed as follows: collect n groups of active power data, extract features for each group of active power data, obtain multiple performance features of the active power data, construct a neural network model, use the performance features of the active power data as training data for the neural network model, assign a performance evaluation value to each performance feature, and the performance evaluation value range is (3.0-4.9). The larger the performance evaluation value, the better the performance of the active power, and the smaller the performance evaluation value, the worse the performance of the active power. The training data is divided into a 60% training set and a 40% validation set, and the neural network is iteratively trained on the training set and the validation set. After the training is completed, a performance evaluation model of active power data is constructed.

[0047] If it is a performance evaluation model of reactive power data, n groups of reactive power data are collected. The larger the performance evaluation value, the better the performance of reactive power, and the smaller the performance evaluation value, the worse the performance of reactive power.

[0048] The equipment data acquisition module and the performance evaluation module are set up to not only collect the grid-connected performance data of the grid-connected equipment in real time, but also collect the operating data of the power equipment connected to the grid-connected equipment, conduct in-depth and comprehensive analysis of the performance of the grid-connected equipment on a regular basis, and accurately analyze the current performance of the grid-connected equipment itself.

[0049] Performance prediction module: A grid-connected simulation operation model is constructed based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operating characteristics of power equipment. The grid-connected simulation operation model performs a simulation operation for a performance evaluation period to obtain the performance prediction value of the grid-connected equipment.

[0050] A grid-connected simulation operation model is constructed based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operating characteristics of power equipment. Specifically, MATLAB / Simu link simulation software is selected, and a grid-connected equipment body and other power equipment bodies are created in the simulation software based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operating characteristics of power equipment. Parameters are set for the grid-connected equipment body and the power equipment body, and power connection is established between the grid-connected equipment body and each power equipment body to construct a grid-connected simulation operation model. The grid-connected simulation operation model can simulate the operation of the grid-connected equipment body and the power equipment body.

[0051] The grid-connected simulation operation model performs a simulation operation for a performance evaluation duration, and then obtains the performance prediction value of the grid-connected equipment. Specifically, the performance evaluation duration is divided into m simulation evaluation periods of equal duration, and the power equipment impact value of each simulation evaluation period is obtained. The power equipment impact values ​​of all simulation evaluation periods are summed and averaged to obtain the equipment impact mean Kzy. All power equipment impact values ​​are sorted in the order of the simulation evaluation periods, and the impact values ​​of two adjacent power equipment after sorting are summed to obtain the equipment continuous impact value. The equipment continuous impact limit value is set (the equipment continuous impact limit value is a system preset value). When the equipment continuous impact value is greater than or equal to the equipment continuous impact limit value, the continuous impact quantity is increased by one. When the equipment continuous impact value is less than the equipment continuous impact limit value, no processing is performed and the continuous impact quantity is marked as Dbp. The difference between the two adjacent power equipment impact values ​​after sorting is calculated and the absolute value is taken to obtain the equipment fluctuation impact value. The equipment fluctuation impact limit value is set (the equipment fluctuation impact limit value is a system preset value). When the equipment fluctuation impact value is greater than or equal to the equipment fluctuation impact limit value, the fluctuation impact quantity is increased by one. When the equipment fluctuation impact value is less than the equipment fluctuation impact limit value, no processing is performed and the fluctuation impact quantity is marked as Tmg. Using the formula The performance prediction value Astb of the grid-connected equipment is obtained, where m1 is the equipment influence coefficient, m2 is the continuous influence coefficient, and m3 is the fluctuation influence coefficient. The value of m1 is 0.74, the value of m2 is 0.62, and the value of m3 is 0.81.

[0052] The impact value of the power equipment during the simulation evaluation period is obtained through the following steps: collecting the operating data of each power equipment body during the simulation evaluation period, extracting features from the operating data of each power equipment body, obtaining the operating features of each power equipment body, and then obtaining the operating fluctuation value Ecb of each power equipment body, c = 1, 2, ..., C, C is the number of the power equipment body, each power equipment body corresponds to an independent number, and the operating fluctuation coefficient is set to Fb, b = 1, 2, 3, ..., b, F1 < F2 < F3 < ... < Fb, each operating fluctuation coefficient corresponds to an operating fluctuation value within a range, and the operation The range of fluctuation values ​​includes (0, Ec1], (Ec1, Ec2], …, (Ecb-1, Ecb], when Ecb∈(0, Ec1], the operation fluctuation coefficient is F1, the operation fluctuation values ​​of the power equipment bodies of the same equipment type are summed and averaged to obtain the equipment fluctuation value of the equipment type, and the equipment fluctuation threshold is set (the equipment fluctuation threshold is a system preset value). When the equipment fluctuation value is greater than or equal to the equipment fluctuation threshold, the number of fluctuating equipment types is increased by one. When the equipment fluctuation value is less than the equipment fluctuation threshold, no processing is performed and the number of fluctuating equipment types is marked as Szx. The formula is used The power equipment impact value Lbs of the simulation evaluation period is obtained, where e1 is the fluctuation equipment type coefficient, and the value of e1 is 1.97.

[0053] The operating fluctuation value of the power equipment body is obtained through the following steps: obtaining the equipment type of the power equipment body (the type of the power equipment body includes generators, transformers, etc.), obtaining an operating fluctuation analysis model of the equipment type, inputting the operating characteristics of the power equipment body into the operating fluctuation analysis model, and the operating fluctuation analysis model outputs the operating fluctuation value of the power equipment body.

[0054] Each type of electric power equipment body corresponds to an independent operation fluctuation analysis model. The difference between each operation fluctuation analysis model lies in the difference in training data. Therefore, this embodiment only illustrates the construction method of the operation fluctuation analysis model of one type of electric power equipment body, and no longer enumerates the construction methods of the operation fluctuation analysis models of various types of electric power equipment bodies.

[0055] The construction method of the generator operation fluctuation analysis model is as follows: collect x groups of generator operation data, extract features from each group of generator operation data, obtain multiple groups of generator operation features, build a neural network model, use the generator operation features as training data for the neural network model, assign an operation fluctuation value to each performance feature, the operation fluctuation value range is (0.1-0.9), the larger the operation fluctuation value, the more unstable the generator operation, the smaller the operation fluctuation value, the more stable the generator operation, the training data is divided into 70% training set and 30% validation set, perform neural network iterative training on the training set and the validation set, and after the training is completed, the generator operation fluctuation analysis model is constructed.

[0056] If it is an operation fluctuation analysis model of a transformer, then the operation data of x groups of transformers are collected. The larger the value of the operation fluctuation value, the less stable the operation of the transformer, and the smaller the value of the operation fluctuation value, the more stable the operation of the transformer.

[0057] Grid-connected performance warning module: obtain the grid-connected performance evaluation warning value according to the comprehensive performance evaluation value and performance prediction value of the grid-connected equipment, set the grid-connected performance evaluation warning threshold (the grid-connected performance evaluation warning threshold is a system pre-set value), and when the grid-connected performance evaluation warning value is greater than or equal to the grid-connected performance evaluation warning threshold, send a grid-connected equipment performance warning signal; when the grid-connected performance evaluation warning value is less than the grid-connected performance evaluation warning threshold, no processing is performed.

[0058] The grid-connected performance evaluation warning value is obtained based on the comprehensive performance evaluation value and performance prediction value of the grid-connected equipment. Specifically, the formula is used: The grid-connected performance evaluation warning value Rsw is obtained, where f1 is the comprehensive performance evaluation coefficient, f2 is the performance prediction coefficient, the value of f1 is 0.47, and the value of f2 is 0.49.

[0059] Set up a performance prediction module and a grid-connected performance warning module, build a simulation operation model of the grid-connected equipment and power equipment, simulate and analyze the impact of the current performance of the grid-connected equipment on the operation of other power equipment, and then establish a comprehensive and three-dimensional grid-connected equipment performance evaluation and early warning mechanism.

[0060] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0061] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or 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 can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can 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 can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can 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. The semiconductor medium can be a solid-state hard disk.

[0062] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0066] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0067] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A grid-connected performance evaluation and early warning system based on big data, characterized in that: It includes equipment data acquisition module, performance evaluation module, performance prediction module, and grid-connected performance warning module; The device data acquisition module is used to determine the power equipment to which the grid-connected device is connected, collect various types of grid-connected performance data of the grid-connected device and the operating data of the power equipment in real time, perform feature extraction on the various types of grid-connected performance data of the grid-connected device and the operating data of the power equipment, and obtain the performance characteristics of the various types of grid-connected performance data of the grid-connected device and the operating characteristics of the power equipment; The performance comprehensive evaluation module obtains the performance comprehensive evaluation value of the grid-connected device after each performance evaluation period; The performance prediction module builds a grid-connected simulation operation model based on the performance characteristics of various types of grid-connected performance data of the grid-connected equipment and the operation characteristics of the power equipment. The grid-connected simulation operation model performs a simulation operation for a performance evaluation duration, thereby obtaining a performance prediction value of the grid-connected equipment; The grid-connected performance warning module obtains a grid-connected performance evaluation warning value according to the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, and determines whether to send a grid-connected equipment performance warning signal based on a comparison result between the grid-connected performance evaluation warning value and the grid-connected performance evaluation warning threshold.

2. The grid-connected performance evaluation and early warning system based on big data according to claim 1 is characterized in that: The comprehensive performance evaluation value of the grid-connected equipment is obtained through the following steps: obtaining the performance evaluation value of each type of grid-connected performance data, setting the high performance evaluation value and the low performance evaluation value, when the performance evaluation value is greater than or equal to the high performance evaluation value, marking the corresponding type of grid-connected performance data as satisfactory performance data, when the performance evaluation value is less than or equal to the low performance evaluation value, marking the corresponding type of grid-connected performance data as gap performance data, when the performance evaluation value is between the high performance evaluation value and the low performance evaluation value, marking the corresponding type of grid-connected performance data as normal performance data, marking the total number of satisfactory performance data as Bte, marking the total number of gap performance data as Mks, summing the performance evaluation values ​​of the normal performance data and taking the average, obtaining the normal performance evaluation value Pmd, and using the formula The comprehensive performance evaluation value Ustd of the grid-connected equipment is obtained, where ua is the satisfactory performance coefficient, ub is the gap performance coefficient, and uc is the conventional performance coefficient.

3. The grid-connected performance evaluation and early warning system based on big data according to claim 2 is characterized in that: The performance evaluation values ​​of each type of grid-connected performance data are obtained through the following steps: obtaining a performance evaluation model for each type of grid-connected performance data, inputting the performance characteristics of each type of grid-connected performance data into the corresponding performance evaluation model, and outputting the performance evaluation values ​​of each type of grid-connected performance data.

4. The grid-connected performance evaluation and early warning system based on big data according to claim 1 is characterized in that: A grid-connected simulation operation model is constructed based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operating characteristics of power equipment. Specifically, simulation software is selected, and a grid-connected equipment body and other power equipment bodies are created in the simulation software based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operating characteristics of power equipment. Parameters are set for the grid-connected equipment body and the power equipment body, and power connection is established between the grid-connected equipment body and each power equipment body to construct a grid-connected simulation operation model. The grid-connected simulation operation model can simulate the operation of the grid-connected equipment body and the power equipment body.

5. The grid-connected performance evaluation and early warning system based on big data according to claim 1 is characterized in that: The grid-connected simulation operation model performs a simulation operation for a performance evaluation duration, and then obtains the performance prediction value of the grid-connected equipment. Specifically, the performance evaluation duration is divided into m simulation evaluation periods of equal duration, and the power equipment impact value of each simulation evaluation period is obtained. The power equipment impact values ​​of all simulation evaluation periods are summed and averaged to obtain the equipment impact average Kzy. All power equipment impact values ​​are sorted in the order of the simulation evaluation periods, and the two adjacent power equipment impact values ​​after sorting are summed to obtain the equipment continuous impact value. The equipment continuous impact boundary value is set. When the equipment continuous impact value is greater than or equal to the equipment continuous impact boundary value, the continuous impact number is increased by one, and the continuous impact number is marked as Dbp. The difference between the two adjacent power equipment impact values ​​after sorting is calculated and the absolute value is taken to obtain the equipment fluctuation impact value. The equipment fluctuation impact boundary value is set. When the equipment fluctuation impact value is greater than or equal to the equipment fluctuation impact boundary value, the fluctuation impact number is increased by one, and the fluctuation impact number is marked as Tmg. The formula is used. The performance prediction value Astb of the grid-connected equipment is obtained, where m1 is the equipment influence coefficient, m2 is the continuous influence coefficient, and m3 is the fluctuation influence coefficient.

6. The grid-connected performance evaluation and early warning system based on big data according to claim 5 is characterized in that: The impact value of the power equipment in the simulation evaluation period is obtained by the following steps: collecting the operation data of each power equipment body in the simulation evaluation period, extracting the characteristics of the operation data of each power equipment body, obtaining the operation characteristics of each power equipment body, and then obtaining the operation fluctuation value Ecb of each power equipment body, c = 1, 2, ..., C, C is the number of the power equipment body, setting the operation fluctuation coefficient to Fb, summing the operation fluctuation values ​​of the power equipment bodies of the same equipment type and taking the average to obtain the equipment fluctuation value of the equipment type, setting the equipment fluctuation threshold, when the equipment fluctuation value is greater than or equal to the equipment fluctuation threshold, increasing the number of fluctuation equipment types by one, marking the number of fluctuation equipment types as Szx, and using the formula The power equipment impact value Lbs of the simulation evaluation period is obtained, where e1 is the fluctuation equipment type coefficient.

7. The grid-connected performance evaluation and early warning system based on big data according to claim 6 is characterized in that: The operation fluctuation value of the power equipment body is obtained through the following steps: obtaining the equipment type of the power equipment body, obtaining an operation fluctuation analysis model of the equipment type, inputting the operation characteristics of the power equipment body into the operation fluctuation analysis model, and the operation fluctuation analysis model outputs the operation fluctuation value of the power equipment body.

8. The grid-connected performance evaluation and early warning system based on big data according to claim 1 is characterized in that: The grid-connected performance evaluation warning value is obtained based on the comprehensive performance evaluation value and performance prediction value of the grid-connected equipment. Specifically, the formula is used: The grid-connected performance evaluation warning value Rsw is obtained, where f1 is the comprehensive performance evaluation coefficient and f2 is the performance prediction coefficient.

9. A grid-connected performance evaluation and early warning method based on big data, applied to a grid-connected performance evaluation and early warning system based on big data as claimed in any one of claims 1 to 8, characterized in that: The steps include: Step 1: Determine the power equipment to which the grid-connected equipment is connected, and collect various types of grid-connected performance data of the grid-connected equipment and the operation data of the power equipment in real time; Step 2: Extracting features of various types of grid-connected performance data of grid-connected equipment and operating data of power equipment to obtain performance features of various types of grid-connected performance data of grid-connected equipment and operating features of power equipment; Step 3: After each performance evaluation period, obtain the comprehensive performance evaluation value of the grid-connected equipment; Step 4: Building a grid-connected simulation operation model based on the performance characteristics of various types of grid-connected performance data of grid-connected equipment and the operation characteristics of power equipment; Step 5: The grid-connected simulation operation model performs a simulation operation for a performance evaluation period to obtain the performance prediction value of the grid-connected equipment; Step 6: Obtain a grid-connected performance evaluation warning value based on the comprehensive performance evaluation value and the performance prediction value of the grid-connected equipment, and determine whether to send a grid-connected equipment performance warning signal based on a comparison result between the grid-connected performance evaluation warning value and the grid-connected performance evaluation warning threshold.

Images