Power balance evaluation method and device based on new energy fluctuation

Abstract

The application discloses a new energy fluctuation-based power balance evaluation method and device, and belongs to the technical field of power balance. When the singular value in the performance parameter value of the new energy is replaced and handled via the performance parameter value mode, the number of parameters sent to the performance parameter value handling mode will affect the accuracy of the parameters obtained after the singular value is replaced. If the number of parameters sent to the performance parameter value handling mode is not large, the small number of singular values will have a considerable effect on the accuracy of the parameters obtained by the mode handling. If the number of parameters sent to the performance parameter value handling mode is not small, the strength of the flexible handling of the singular values is usually not large, so the number of sent parameters of the parameters handled by the most appropriate mode is obtained according to the fluctuation amplitude of the parameters and the number of singular values identified by the singular value algorithm, the mode is added to the sent parameters, and the derived parameters are more accurate.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power balance, and particularly relates to a power balance evaluation method and device based on new energy fluctuation. BACKGROUND

[0002] Power balance, also known as power system operation simulation, is used to study the improved operation mode of various power stations in the power system and the improved exchange of power between subsystems, so as to determine the capacity and power benefits of each scheme. It is an important part of formulating power planning, design and operation plan.

[0003] In the aspect of power balance of new energy fluctuation, the power balance method of new energy grid-connected operation with a patent publication number of CN111987740B is often used to achieve it, which includes a generator set monitoring unit, a central control system and a power grid monitoring terminal connected in sequence. The generator set monitoring unit is used to detect the performance parameter value of the new energy and whether the performance parameter value is within the normal range. When the performance parameter value of the new energy is detected to be out of the normal range, the detection information is transmitted to the power grid monitoring terminal through the central control system to timely remind maintenance. The performance parameter value of the new energy is the power of the wind turbine generator set (which can be the power per unit time), the temperature of the wind turbine generator set, the wind power of the wind turbine generator set, the power of the photovoltaic generator set (which can be the power per unit time) or the temperature of the photovoltaic generator set, thereby reducing the influence on power balance.

[0004] The generator set monitoring unit samples the performance parameter value of the new energy through the corresponding detection module, which often makes errors in actual use. The current identification of the error value (i.e. singular value) in the performance parameter value of the new energy often identifies the value point with a singular amplitude not less than the singular value in the performance parameter value of the new energy, and replaces it through a self-encoder, that is, through a singular value detection mode of a convolution layer and a pooling layer to process the performance parameter value queue arranged in accordance with the order of sampling time points, and through corresponding learning, continuously improves the identification function of the singular value of the convolution layer and the pooling layer, and improves the singular value detection function of the mode.

[0005] However, when the performance parameter value of the new energy is sent to the self-encoder, even if the identified singular value is relatively accurate, the accuracy of the replaced performance parameter value of the new energy is still not high due to the too large amount of singular values in the performance parameter value of the new energy sent. SUMMARY

[0006] To solve the defects in the prior art, the application provides a power and electricity balance evaluation method and device based on new energy fluctuation, wherein when replacement treatment is performed on singular values in performance parameter values of new energy via a performance parameter value mode, the number of parameters sent to the performance parameter value treatment mode will affect the accuracy of the parameters obtained after the singular values are replaced. If the number of parameters sent to the performance parameter value treatment mode is not large, the small number of singular values will have a considerable effect on the accuracy of the parameters obtained by the mode treatment. If the number of parameters sent to the performance parameter value treatment mode is not small, the strength of flexible treatment performed on the singular values is usually not large, so the number of sent parameters of the parameters treated by the mode is obtained according to the fluctuation amplitude of the parameters themselves and the number of singular values identified by the singular value algorithm, so that the sent parameters of the parameters treated by the mode are added (that is, the singular values are replaced by the mode forming parameters), and the derived parameters are more accurate.

[0007] The application uses the following technical solutions.

[0008] A power and electricity balance evaluation method based on new energy fluctuation, comprising:

[0009] The generator set monitoring unit treats the performance parameter values of the sampled new energy and detects whether the treated performance parameter values are within a normal range. When it is detected that the performance parameter values of the new energy are not within the normal range, detection information is transmitted to the power grid monitoring terminal via the central control system to timely remind maintenance. The performance parameter values of the new energy are the electricity of the wind turbine generator set, the temperature of the wind turbine generator set, the wind of the wind turbine generator set, the electricity of the photovoltaic generator set or the temperature of the photovoltaic generator set, thereby reducing the influence on the power and electricity balance.

[0010] A method for treating the performance parameter values of the sampled new energy by the generator set monitoring unit, comprising:

[0011] Step 1, sampling the performance parameter values of the new energy in a plurality of time intervals;

[0012] Step 2, for any time interval, determining the singular value probability of each value point, and performing grouping according to the singular value probability to obtain a predefined number of groups. For any group, it is determined whether the group is a singular value group according to the average of the singular value probabilities of the value points in the group.

[0013] Step 3, calculating a reasonable amplitude factor Q y : The optimal solution of the reasonable amplitude factor Q y is calculated by a greedy algorithm to determine the corresponding sent number y, which is defined as the target sent number y B .

[0014] Step 4, using the pre-defined performance parameter value treatment mode to perform treatment on the performance parameter value of the new energy, to obtain the performance parameter value of the new energy after replacing the singular value, which is taken as the treated performance parameter value.

[0015] Further, in Step 2, the numerical points are the performance parameter values of the new energy.

[0016] Further, in Step 2, the algorithm for grouping the numerical points is the K-means method, the K value is six, and when grouping, the time point value corresponding to each sampling time in a time interval and the singular value probability value of each numerical point are respectively subjected to standardization treatment by using the Z-score method.

[0017] Further, in Step 2, the method for determining the singular value probability of each numerical point is: obtaining the number p of parameters of the kth numerical point of each time interval being a singular value k , here, whether the kth numerical point is a singular value is determined by piecewise linear regression method; the probability of the kth numerical point being a singular value is obtained: Here, q k is the probability of the kth numerical point of each time interval being a singular value, and P is the number of time intervals;

[0018] Then, the method for determining whether a group is a singular value group according to the mean of the singular value probability of the numerical points in the group is: for any group, calculating the mean of the singular value probability of each numerical point in the group; if the mean is higher than the critical amount, the group is determined to be a singular value group; if the mean is higher than the critical amount, the group is determined to be a non-singular value group.

[0019] Further, in Step 2, the critical amount is thirty percent.

[0020] Further, in Step 3, the equation for calculating B y is: v j is the number of parameters of all parameters in the jth singular value group in a time interval, N is the total number of singular value groups in a time interval, v U is the pre-defined number of parameters.

[0021] Further, in Step 3, the method for calculating C y is: calculating the standard deviation of the performance parameter value corresponding to the kth numerical point of all time intervals in the performance parameter value of the new energy , and performing standardization treatment on the standard deviation of the kth numerical point by using the Z-score method, to obtain the criticality factor b k of the kth numerical point of each time interval; obtaining the self-information amount T k; facing any one parameter subgroup, sequentially extracting a number of parameters in the time interval using the order of the time of the sampling value point to obtain the number y of the number of parameters sent to the mode; facing any one operation parameter group, the cumulative value of the product of the key degree factor and the self-information amount of each value point in the operation parameter group is obtained, and the fluctuation amplitude of the operation parameter group is obtained;

[0022] Here, the self-information amount T of the kth value point of each time interval is k That is, using the kth value point as the midpoint, selecting the performance parameter value of the new energy of the number u of the sampling time on both sides, and performing operation on the performance parameter value of the new energy of the number u of the sampling time on both sides of the kth value point to obtain the self-information amount T of the kth value point k .

[0023] Further, in Step4, the performance parameter value processing mode performs enhancement on the input parameters via the Transformer, so that the number of input parameters is the same as the number of output parameters.

[0024] Further, Step4 specifically includes:

[0025] Step4-1, constructing a queue with a number of y B ;

[0026] Step4-2, facing any one singular value group: if the number of the queue is higher than the number of the singular value group, let the queue cover the singular value group to perform processing;

[0027] Step4-3, facing any one singular value group: if the number of the queue is lower than the number of the singular value group, make the queue poll the singular value group, and when polling for the first time, let the queue cover the local parameters of the head of the singular value group; during polling, move the queue, and the moved queue covers the local parameters of the singular value group that has not been polled.

[0028] A power balance evaluation device based on new energy fluctuation, comprising:

[0029] The generator set monitoring unit, the central control system and the power grid monitoring terminal are sequentially connected in communication, the generator set monitoring unit is used to process the performance parameter value of the new energy sampled and detect whether the processed performance parameter value is within the normal range, when it is detected that the performance parameter value of the new energy is not within the normal range, the detection information is transmitted to the power grid monitoring terminal through the central control system, timely reminding maintenance, the performance parameter value of the new energy is the power of the wind turbine generator set, the temperature of the wind turbine generator set, the wind of the wind turbine generator set, the power of the photovoltaic generator set or the temperature of the photovoltaic generator set, reducing the influence on the power balance;

[0030] The module running on the generator set monitoring unit comprises:

[0031] a sampling module for sampling the performance parameter values of the new energy source in a plurality of time intervals;

[0032] a grouping module for determining the singular value probability of each value point in a time interval, performing grouping according to the singular value probability, and obtaining a predefined number of groups; and determining whether a group is a singular value group according to the average of the singular value probability of the value points in the group.

[0033] an operation module for calculating a reasonable amplitude factor Q y : determining the corresponding feed number y by calculating the optimal solution of the reasonable amplitude factor Q y , and defining the target feed number y B .

[0034] a processing module for performing processing on the performance parameter values of the new energy source by using a predefined performance parameter value processing mode, so as to obtain the performance parameter values of the new energy source after replacing the singular values, which are used as the processed performance parameter values.

[0035] The technical effects of the present application include:

[0036] When the singular values in the performance parameter values of the new energy source are replaced by the performance parameter value processing mode, the number of parameters fed into the performance parameter value processing mode will affect the accuracy of the parameters obtained after replacing the singular values. For example, if the number of parameters fed into the performance parameter value processing mode is not large, the small number of singular values will have a considerable effect on the accuracy of the parameters obtained by the mode processing; if the number of parameters fed into the performance parameter value processing mode is not small, the intensity of flexible processing on the singular values is often not large, so the number of fed parameters of the parameters processed by the mode is obtained by the fluctuation amplitude of the parameters themselves and the number of singular values identified by the singular value algorithm, so that the mode performs addition (that is, the singular values are replaced by the mode forming parameters) on the fed parameters, and the derived parameters are more accurate.

[0037] And the performance parameter value of the new energy source of each time interval is similar to the change range between the performance parameter value of the new energy source of the time interval and the performance parameter value of the new energy source of another time interval, the singular values converge at the same sampling time in a time interval, and the singular values are generated with a certain probability, so the probability ratio of the singular values generated at the same sampling time in each time interval is the probability of the sampling time interval, and the singular value condition of the sampling time interval can be more accurately identified by comparing the parameters of the time intervals, the problem of a single time interval parameter is prevented, and the accuracy and reliability of the singular value probability are improved.

[0038] The mean of all the value points in the group is the probability of the group being a singular value group, and the singular value range of the group is determined by comprehensively involving the singular value range of all groups, and then the effect of individual singular value points on the identification of the singular value of the group is reduced by using the mean as the identification parameter, thereby reducing the risk of misidentification and improving the accuracy of identification.

[0039] For singular value groups with a small number of parameters, the queue can directly cover, so that this place contains normal parameters and singular values, and the singular values are replaced by the performance parameter value processing mode, and the non-singular values (normal parameters) are covered by the queue to ensure that the replaced parameters can better reflect the true situation, so that the parameters sent by the mode are more accurate. In the face of singular value groups with a large number of parameters, the queue cannot fully cover, at this time, the singular value group is partially polled from the head of the queue, and the queue is moved during polling, and the parameters in the queue are better maintained by localized processing. The source attribute, so as to maintain the integrity and continuity of the parameters.

[0040] The performance parameter value of the new energy source of the present application is a single type parameter and has an order relationship between each value point, which is suitable for corresponding singular value detection algorithm. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is part of the flow chart of the power and energy balance evaluation method based on the fluctuation of the new energy source described in the present application;

[0042] Figure 2 is part of the structure schematic diagram of the power and energy balance evaluation device based on the fluctuation of the new energy source described in the present application. DETAILED DESCRIPTION

[0043] In order to make the objects, technical solutions and advantages of the present application clearer, the following will combine the drawings in the embodiments of the present application to perform a clear and complete expression of the technical solutions of the present application. The embodiments expressed in the present application are only some embodiments of the present application, but not all embodiments. According to the spirit of the present application, other embodiments obtained by those skilled in the art without making creative efforts fall within the protection scope of the present application.

[0044] As shown in Figure 1 The power balance evaluation method based on new energy fluctuation of the present application comprises:

[0045] The generator set monitoring unit processes the performance parameter value of the new energy sampled and detects whether the processed performance parameter value is within the normal range. When it is detected that the performance parameter value of the new energy is not within the normal range, the detection information is transmitted to the power grid monitoring terminal through the central control system to timely remind the maintenance. The performance parameter value of the new energy is the power of the wind turbine generator set, the temperature of the wind turbine generator set, the wind power of the wind turbine generator set, the power of the photovoltaic generator set or the temperature of the photovoltaic generator set, thereby reducing the influence on the power balance. The new energy is the photovoltaic generator set or the wind turbine generator set.

[0046] The method for processing the performance parameter value of the new energy sampled by the generator set monitoring unit comprises:

[0047] Step 1, sampling the performance parameter value of the new energy of the new energy in a continuous time interval;

[0048] In the preferred but non-limiting embodiments of the present application, in Step 1, the performance parameter value of the new energy is a single type of parameter. The performance parameter value of the new energy is the power of the wind turbine generator set, the temperature of the wind turbine generator set, the wind power of the wind turbine generator set, the power of the photovoltaic generator set or the temperature of the photovoltaic generator set. The performance parameter value of the new energy corresponds to a performance parameter value. The size of the time interval is 1 minute.

[0049] Step 2, for any time interval, determining the singular value probability of each value point and performing grouping according to the singular value probability to obtain a predefined number of groups. For any group, determining whether the group is a singular value group according to the average of the singular value probability of the value points in the group;

[0050] In the preferred but non-limiting embodiments of the present application, in Step 2, the value point is the performance parameter value of the new energy.

[0051] In the preferred but non-limiting embodiment of the present application, in Step 2, the algorithm for grouping the numerical points is the K-means method, the K value is six, and the Z-score method is used to perform standardization treatment on the values of the corresponding time points of all sampling time points in a time interval and the values of the singular value probability of each numerical point when grouping. The numerical points in the group obtained by the K-means method are continuous in the order of sampling time points, that is, a group contains the tenth to twentieth sampling numerical points in a time interval.

[0052] In the preferred but non-limiting embodiment of the present application, in Step 2, the method for determining the singular value probability of each numerical point is to obtain the number p of parameters of the kth numerical point being a singular value in each time interval k , wherein the segmented linear regression method is used to determine whether the kth numerical point is a singular value; and the probability of the kth numerical point being a singular value is obtained: , wherein q k is the probability of the kth numerical point being a singular value in each time interval, and P is the number of time intervals.

[0053] Then, the method for determining whether a group is a singular value group according to the mean of the singular value probabilities of the numerical points in the group is: for any group, the mean of the singular value probabilities of each numerical point in the group is calculated; if the mean is higher than a threshold, the group is determined to be a singular value group; if the mean is lower than the threshold, the group is determined to be a non-singular value group.

[0054] In the preferred but non-limiting embodiment of the present application, in Step 2, the threshold is 30%.

[0055] Step 3: Calculate the reasonable range factor Q y : The optimal solution of the reasonable range factor Q y is calculated by the greedy algorithm to determine the corresponding number of inputs y, which is defined as the target number of inputs y B .

[0056] , wherein B y is the number of performance parameter values of the input new energy and the number of parameters of each singular value group, C y is the value of the input number y and the value of the numerical point is associated with its self-information, e is Euler's number, the reasonable range factor Q y is proportional to B y , the reasonable range factor Q y is proportional to C y .

[0057] In the preferred but non-limiting embodiment of the present application, in Step 3, the equation for calculating B y is: v jis the number of parameters in all parameters in the jth singular value group in a time interval, N is the total number of singular value groups in a time interval, v U is a predefined parameter number. Here, B y is proportional to the square of the number of parameters in all parameters in each singular value group, and B y is lower, meaning that the ratio of parameters in the singular value group in the input parameters is smaller, and the accuracy of the derived parameters obtained by adding the input parameters is higher.

[0058] In the preferred but non-limiting embodiment of the present application, in Step 3, the method of calculating C y is to calculate the standard deviation of the performance parameter value of the kth value point of all time intervals in the calculated performance parameter value of the new energy , and to perform standardization processing on the standard deviation of the kth value point using the Z-score method to obtain the criticality factor b k of the kth value point of each time interval; to obtain the self-information amount T k of the kth value point of each time interval; for any parameter subgroup, sequentially extract a number of parameters y from the operation parameter group in the order of the time of the sampling value points in a time interval; for any operation parameter group, calculate the cumulative value of the amount obtained by multiplying the criticality factor and the self-information amount corresponding to each value point in the operation parameter group, to obtain the fluctuation amplitude of the operation parameter group; the highest amount of the fluctuation amplitudes in all operation parameter groups is C y . Here, the lower Bx is, the lower the fluctuation of the input parameters sent to the pattern (the amount obtained by multiplying the standard deviation and the self-information amount corresponding to the value point is not large) in the sampled parameters in a time interval, and the accuracy of the derived parameters sent out by the pattern is higher. The parameters sent out by the pattern are the parameters sent out by the pattern, and the derived parameters sent out by the pattern are the parameters sent out by the pattern;

[0059] Here, the self-information amount T k of the kth value point of each time interval is obtained by using the kth value point as the midpoint, selecting the performance parameter values of the new energy of the number u of adjacent sampling times on both sides of the kth value point, and performing calculation on the performance parameter values of the new energy of the number u of adjacent sampling times on both sides of the kth value point to obtain the self-information amount T k of the kth value point. The method of obtaining the self-information amount is an existing method, which will not be described here.

[0060] In summary, the lower B y is, the lower Q y is, and the accuracy of the derived parameters sent out by the pattern is higher; the lower C y is, the lower Q yThe lower the value is, and the greater the accuracy of the mode-derived parameter is, in B y The higher the value is, and the smaller the accuracy of the mode-derived parameter is, in C y The higher the value is, and the smaller the accuracy of the mode-derived parameter is. y The higher the value is, and the smaller the accuracy of the mode-derived parameter is. y The higher the value is, and the smaller the accuracy of the mode-derived parameter is.

[0061] Step4, using a pre-defined performance parameter value processing mode to process the performance parameter value of the new energy source, to obtain the performance parameter value of the new energy source after replacement of the singular value, which is taken as the processed performance parameter value.

[0062] In the preferred but non-limiting embodiment of the present application, in Step4, the performance parameter value processing mode performs enhancement on the input parameters via the Transformer, so that the number of input parameters is the same as the number of output parameters.

[0063] Here, the number of parameters of the input performance parameter value processing mode is the target input number y B , and the singular value is the value point of the performance parameter value of the new energy source belonging to the singular value group.

[0064] In the preferred but non-limiting embodiment of the present application, Step4 specifically includes:

[0065] Step4-1, constructing a queue with the number of y B ;

[0066] Step4-2, for any singular value group: if the number of the queue is higher than the number of the singular value group, let the queue cover the singular value group to perform processing;

[0067] Step4-3, for any singular value group: if the number of the queue is lower than the number of the singular value group, let the queue poll the singular value group, and when polling for the first time, let the queue cover the local parameters of the head of the singular value group; during polling, move the queue, and the moved queue covers the local parameters of the singular value group that has not been polled.

[0068] Specifically, the process involves replacing the numerical points belonging to singular value groups within a time interval (removing them and forming new data from the numerical points of non-singular value groups). When the number of parameters in a singular value group is less than the queue size, the midpoint of the queue is aligned with the midpoint of the parameters in the singular value group, and the parameters in the queue are fed into the pattern as input parameters. When the number of parameters in a singular value group is greater than the queue size, the queue covers the partial parameters at the head of the singular value group, and the parameters in the queue are fed into the pattern (which can be an autoencoder). The parameters derived from the pattern are then replaced with the source parameters in the queue, and the queue is moved to cover the unprocessed parameters belonging to that singular value group, until the queue polls all singular value groups.

[0069] Here, the number of queue segments covering the first segment of the singular value group is no more than half the total number of queues. This results in a low parameter ratio within the singular value group, leading to more accurate parameters derived from the pattern.

[0070] like Figure 2 As shown, the present invention provides a power balance assessment device based on new energy fluctuations, comprising:

[0071] The generator set monitoring unit, central control system, and power grid monitoring terminal are sequentially connected. The generator set monitoring unit is used to process the performance parameter values ​​of the sampled new energy and detect whether the processed performance parameter values ​​are within the normal range. When the performance parameter values ​​of the new energy are detected to be outside the normal range, the detection information is transmitted to the power grid monitoring terminal through the central control system to promptly remind maintenance. The performance parameter values ​​of the new energy are the power of the wind turbine generator set (which can be the power per unit time), the temperature of the wind turbine generator set, the wind power of the wind turbine generator set, the power of the photovoltaic generator set (which can be the power per unit time), or the temperature of the photovoltaic generator set, so as to reduce the impact on the power balance.

[0072] The modules running on the generator set monitoring unit include:

[0073] The sampling module is used to sample the performance parameter values ​​of the new energy source over a continuous time interval.

[0074] The grouping module is used to determine the odds of each value point in the face of any time interval, and to perform grouping based on the odds of ...

[0075] The calculation module is used to calculate the reasonable amplitude factor Q. y : The reasonable amplitude factor Q is calculated using a greedy algorithm. yThe optimal solution is used to determine the corresponding number of feeds y, which is defined as the target number of feeds y. B ;

[0076] The processing module is used to process the performance parameter values ​​of new energy sources using a predefined performance parameter value processing mode, so as to obtain the performance parameter values ​​of new energy sources after replacing the singular values, and use these as the processed performance parameter values.

[0077] The beneficial effects of the present invention are as follows: Compared with the prior art, the technical effects of the present invention include:

[0078] When performing outlier replacement processing on the performance parameters of new energy sources using a performance parameter value model, the number of parameters fed into the model affects the accuracy of the parameters obtained after the outlier replacement. For example, if the number of parameters fed into the model is small, the limited number of outliers will significantly impact the accuracy of the parameters obtained; conversely, if the number of parameters fed into the model is large, the intensity of the flexible processing of outliers is often insufficient. Therefore, the optimal number of parameters fed into the model is determined by considering the fluctuation range of the parameters themselves and the number of outliers identified by the outlier algorithm. This allows the model to augment the fed parameters (i.e., replace outliers with model-generated parameters), resulting in more accurate derived parameters.

[0079] By using the performance parameter values ​​of new energy sources at various time intervals, and considering that the variation range of the performance parameter values ​​of new energy sources sampled at one time interval is similar to that of new energy sources at other time intervals, outliers will converge at the same sampling time within a time interval. Since the performance parameter values ​​of sampled new energy sources have a significant probability of producing outliers, it is necessary to sample for several time intervals. The ratio of the probability that the sampled parameters at the same sampling time within each time interval are outliers is the probability that each time interval will produce an obstacle at that sampling time. Based on this, by comparing the parameters of several time intervals, the outlier situation at the set sampling time can be identified more accurately, avoiding the problem of a single time interval parameter and improving the accuracy and reliability of the outlier probability.

[0080] The mean of all numerical points within a group is used as the probability that the group is an outlier group. By comprehensively considering the outlier amplitude of all groups, the outlier amplitude of the groups is measured more comprehensively. Then, by using the mean as the identification parameter, the influence of individual outlier numerical points on the identification of outliers of groups can be reduced, thereby reducing the risk of misidentification and improving the accuracy of identification.

[0081] For the singular value group with small number of parameters, the queue can directly cover, so that the normal parameters and singular values are contained here, and the singular values are changed through the performance parameter value processing mode, and the changed parameters can better reflect the true situation by making the queue cover the non-singular values (normal parameters), so that the parameters sent by the mode are more accurate. For the singular value group with large number of parameters, the queue cannot cover comprehensively, and the head of the queue covering the singular value group is partially polled, the motion queue is polled during the polling, and the parameters in the queue are better maintained through localized processing. The source attribute is maintained to maintain the completeness and persistence of the parameters.

[0082] The performance parameter value of the new energy of the application is a single category parameter, and each value point has an order relationship of sampling time, which is suitable for corresponding singular value detection algorithm.

[0083] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable backup medium having loaded thereon computer readable program instructions for causing a processor to achieve various aspects of the present disclosure.

[0084] The computer readable backup medium can be a tangible computer readable storage medium that can retain and store instructions for use by an instruction execution system. The computer readable backup medium can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, semiconductor, or any suitable combination of the foregoing. Further examples (a non-exhaustive list) of computer readable storage media that can be used with the exemplary embodiments include portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), portable compact disc read-only memories (CD-ROM), digital versatile disks (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or punched tape, and any suitable combination thereof. The computer readable backup medium is not, however, a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0085] Computer readable program instructions described herein can be downloaded to respective computing / processing electrical lines from a computer readable removable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge service providers. A wireless network adapter card or wireless modem card of a respective computing / processing electrical line receives computer readable program instructions from the wireless network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing electrical line.

[0086] Computer readable program instructions for carrying out the operations of the present disclosure can be assembly language instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, conditionally executed code, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on a client computer, partly on a client computer, as a stand-alone software package, partly on a client computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the client computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0087] Finally, it should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the application. Accordingly, the legal scope of the application is defined only by the claims.

Claims

1. A new energy fluctuation-based power balance evaluation method, characterized in that, The application comprises the following steps: The generator set monitoring unit processes the performance parameter values of the new energy obtained by sampling and detects whether the processed performance parameter values are within a normal range. When it is detected that the performance parameter values of the new energy are not within the normal range, detection information is transmitted to the power grid monitoring terminal via the central control system to timely remind maintenance, and the performance parameter values of the new energy are the power of the wind turbine generator set, the temperature of the wind turbine generator set, the wind of the wind turbine generator set, the power of the photovoltaic generator set or the temperature of the photovoltaic generator set, thereby reducing the influence on power balance. The application also provides a method for processing the performance parameter values of the new energy obtained by sampling, comprising the following steps: Step 1: sampling the performance parameter values of the new energy in a plurality of time intervals; Step 2: determining the singular value probability of each value point for a random time interval, and performing grouping according to the singular value probability to obtain a predefined number of groups; for a random group, determining whether the group is a singular value group according to the mean of the singular value probability of the value points in the group; Step 3, calculating the reasonable amplitude factor : ; calculating the reasonable amplitude factor via a greedy algorithm to determine the corresponding feed number , defined as the target feed number ; Step 4: using a predefined performance parameter value processing mode to process the performance parameter values of the new energy to obtain the performance parameter values of the new energy after replacing singular values, which are used as the processed performance parameter values; denotes the influence factor of the number of parameters within the singular value group on the reasonable amplitude factor, and its calculation formula is: ； wherein, is the number of parameters within the kth singular value group, M is the total number of singular value groups, and N is the pre-set number of parameters, represents the influence factor of the fluctuation of the performance parameter value on the reasonable amplitude factor. 2.The new energy fluctuation-based power balance evaluation method according to claim 1, characterized in that, In Step 2, the value points are the performance parameter values of the new energy. 3.The new energy fluctuation-based power balance evaluation method according to claim 2, characterized in that, In Step 2, the algorithm for grouping the value points is the K-means method, the K value is six, and the Z-score method is used to perform standardization processing on the corresponding time point values of all sampling time points in a time interval and the singular value probability values of the value points during grouping. 4.The new energy fluctuation-based power balance evaluation method according to claim 3, characterized in that, In Step 2, the method of determining the probability of each value point being a singular value is: obtaining the number of parameters of each time interval value point being a singular value Here, determining whether the first value point is a singular value by piecewise linear regression method; obtaining the probability of the first value point being a singular value: Here, is the probability of the first value point of each time interval being a singular value, is the number of time intervals; Then, the method for determining whether a group is a singular value group according to the mean of the singular value probability of the value points in the group is as follows: for a random group, the mean of the singular value probability of each value point in the group is calculated; if the mean is higher than a threshold, the group is determined to be a singular value group; if the mean is lower than the threshold, the group is determined to be a non-singular value group.

5. The method of claim 4, wherein the method further comprises: In Step 2, the threshold is 30%. 6.The new energy fluctuation-based power balance evaluation method according to claim 5, characterized in that, In Step 3, the equation of is , is the number of parameters in the entire set of parameters within the th singular value group within a time interval, is the total number of singular value groups within a time interval, is the number of parameters defined in advance. 7.The new energy fluctuation-based power balance evaluation method according to claim 6, characterized in that, In Step 3, the operation The method is: the standard deviation of the performance parameter value corresponding to the first The number of value points of the whole time interval of the performance parameter value of the new energy operation The standard deviation of the first The key degree factor of the first The number of value points of each time interval is obtained by performing standardized treatment on the standard deviation of the first The number of value points of each time interval is obtained by performing standardized treatment on the standard deviation of the first ; The self-information amount of the first The operation parameter group of the number of parameters in the mode sent in sequence for any one parameter subgroup in the time interval is sequentially extracted according to the order of the time of the sampling value points; for any one operation parameter group, the cumulative value of the quantity obtained by multiplying the key degree factor and the self-information amount corresponding to each value point in the operation parameter group is obtained. The fluctuation amplitude of the operation parameter group;​ Here, the first time interval of each time period Self-information of each numerical point That is, using the first Taking a given value point as the midpoint, the number of sampling times selected from its two adjacent points is... The performance parameter values ​​of the new energy source, and for the first The number of sampling times between each numerical point and its two adjacent points is The performance parameter values ​​of the new energy were obtained by performing calculations. Self-information of each numerical point . 8.The new energy fluctuation-based power balance evaluation method according to claim 7, characterized in that, In Step 4, the performance parameter value processing mode performs enhancement on the input parameters via a Transformer to make the number of input parameters equal to the number of output parameters. 9.The new energy fluctuation-based power balance evaluation method according to claim 8, characterized in that, Step 4 specifically comprises the following steps: Step 4-1, the number of constructed numbers is the number of destination feeds of the queue; Step 4-2: for a random singular value group, if the number of queues is higher than the number of singular value groups, the queue covers the singular value group to perform processing; Step 4-3: for a random singular value group, if the number of queues is lower than the number of singular value groups, the queue polls the singular value group, and when polling for the first time, the queue covers the local parameters at the head of the singular value group; during polling, the queue is moved, and the moved queue covers the local parameters of the singular value group that has not been polled.

Images