A power system power selling deviation monitoring control method

Abstract

The present application relates to the technical field of power system electricity sales management, and relates to a power system electricity sales deviation monitoring and control method.The present application identifies and corrects abnormal values of real-time power consumption data of a user side in a current period collected by an intelligent metering terminal, forms an actual power consumption data sequence from the corrected power consumption data and historical set period actual power consumption data, compares and marks a deviation time window and an actual electricity sales deviation value, triggers an early warning signal when the actual electricity sales deviation value exceeds a dynamic electricity sales deviation threshold value determined according to a user industry type and historical deviation characteristic data, produces the effect of precise early warning triggering, fuses and analyzes user production plan data and power grid operation state data to locate the root cause type of electricity sales deviation, and generates a customized control strategy, so as to realize precise tracing of the root cause of deviation, increase the pertinence of the adjustment strategy in the later period, improve the adjustment control efficiency and reduce the power system regulation loss.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system electricity sales management, and relates to a power system electricity sales deviation monitoring control method. BACKGROUND

[0002] With the deepening of the reform of the electricity market, the electricity sales company balances the electricity according to the medium and long-term contract electricity. However, the actual electricity load of the user is disturbed by various factors such as production plan adjustment and power grid operation state, resulting in a significant deviation between the actual electricity and the contract electricity, and further causing contract settlement risk and loss of electricity sales company revenue. Therefore, how to accurately monitor the electricity sales deviation has become a core problem that needs to be solved in the electricity market.

[0003] The prior art such as Chinese patent publication No. CN109066661A discloses a kind of electricity sales deviation control method and electricity sales control system, which obtains the bidding electricity of user, long-term cooperation electricity, load forecast electricity and actual electricity, calculates electricity sales deviation result, and sends control instruction when deviation result exceeds preset range, adjusts power generation equipment, energy storage equipment or load state, to balance electricity sales deviation.

[0004] However, the prior art has the following problems: 1. The prior art directly uses the collected actual electricity to calculate the deviation, without considering the collection error, instantaneous fluctuation and other abnormal data that may occur in the intelligent metering terminal. Abnormal data will cause the deviation result to be distorted, and then the subsequent adjustment instruction will deviate from the actual demand, reducing the accuracy of deviation control.

[0005] 2. The prior art uses a fixed preset range as the deviation judgment standard, and the fixed preset range is difficult to adapt to the electricity consumption law of users of different industries, which is easy to cause false alarm for industry users with strong volatility or miss the deviation risk for stable users.

[0006] 3. The prior art only outputs the deviation result and triggers equipment adjustment, without analyzing the root cause of the deviation, which will cause the adjustment strategy to lack pertinence, for example, the deviation caused by temporary change of user production plan is misjudged as power grid problem, causing unnecessary equipment adjustment and increasing operation cost. SUMMARY

[0007] The purpose of the present application is to overcome the defects of the prior art, and to provide a power system electricity sales deviation monitoring control method, which realizes the refinement of electricity sales deviation monitoring, the accuracy of root cause identification and the individualization of control strategy.

[0008] The technical scheme adopted by the present application to solve its technical problems is: a power system electricity selling deviation monitoring control method, comprising: S1, collecting real-time power consumption data of the user side in the current period through an intelligent metering terminal in the power system, identifying and correcting the real-time power consumption data based on a preset abnormal value detection rule, and generating corrected real-time power consumption data.

[0009] S2, forming actual power consumption data time sequence based on the corrected real-time power consumption data and historical set period actual power consumption data, and comparing the actual power consumption data time sequence with planned power consumption data of the electricity selling plan contract to mark a deviation time window.

[0010] S3, performing dynamic deviation analysis on the actual power consumption data of the deviation time window and the planned power consumption data of the corresponding time window, and outputting an actual electricity selling deviation value.

[0011] S4, determining an electricity selling dynamic deviation threshold value of the deviation time window according to the user industry type and historical deviation characteristic data, and triggering a warning signal when the actual electricity selling deviation value exceeds the electricity selling dynamic deviation threshold value.

[0012] S5, calling user production plan data and power grid operation state data in the deviation time window, performing fusion analysis on the data to locate a root cause type of the electricity selling deviation, and generating a customized control strategy based on the root cause type of the electricity selling deviation.

[0013] Compared with the prior art, the present application has the following beneficial effects: (1) the present application collects real-time power consumption data of the user side in the current period through an intelligent metering terminal, and distinguishes between persistent abnormality and non-persistent abnormality through an abnormal value detection rule, and corrects the data using current period data or linear interpolation, thereby solving the problem of deviation detection inaccuracy caused by abnormal data, significantly improving real-time data quality and deviation calculation accuracy, and making subsequent adjustment instructions meet actual needs.

[0014] (2) the present application filters historical power consumption data deviation values of each sample user side in the deviation time window according to the user industry type, determines an electricity selling dynamic deviation threshold value of the deviation time window based on the maximum historical power consumption data deviation value and the historical power consumption data change rate, solves the problem that a static threshold value cannot adapt to industry differences and load fluctuations, produces the effect of accurate early warning triggering, thereby reducing false positive rate and false negative rate, and improving the pertinence and economy of electricity selling deviation control.

[0015] (3) the present application calls user production plan data and power grid operation state data, performs fusion analysis on the data to locate a root cause type of the electricity selling deviation, generates a customized control strategy based on the root cause type of the electricity selling deviation, realizes accurate tracing of the root cause of the deviation, increases the pertinence of the adjustment strategy in the later period, improves adjustment control efficiency and reduces power system regulation loss. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed for the description of the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0017] Figure 1 The method steps of the present application are shown in the schematic diagram.

[0018] Figure 2 The correction method of real-time power consumption data in the present application is shown in the schematic diagram.

[0019] Figure 3 The content flow of S2 in the present application is shown in the schematic diagram. DETAILED DESCRIPTION

[0020] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. Note that the relative arrangement, numerical expressions, and numerical values of the components and steps set forth in these embodiments are not limiting to the scope of the present application unless otherwise specifically stated. It should also be understood that the sizes of the various portions shown in the drawings are not drawn to scale for the sake of convenience of description.

[0021] The following description of at least one example embodiment is merely illustrative in nature and is in no way limiting to the scope of the application and its applications or uses. Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification, where appropriate.

[0022] In all examples shown and discussed herein, any specific values should be interpreted as merely illustrative and not as a limitation. Thus, other examples of the example embodiments can have different values.

[0023] Referring to Figure 1 As shown, the present application provides a power system electricity sales deviation monitoring control method, comprising: S1, collecting real-time power consumption data of the user side in the current period through the intelligent metering terminal in the power system, identifying and correcting the real-time power consumption data based on the pre-set abnormal value detection rule, and generating the corrected real-time power consumption data.

[0024] In the embodiments of the present application, the power consumption data can be power consumption or power load.

[0025] As Figure 2The correction method of the real-time power consumption data is shown as follows: S11, acquiring the power consumption data average value of the user side in the current period and the power consumption data change rate of each time point and its adjacent time point according to the collected real-time power consumption data of the user side at each time point in the current period, and identifying whether there is an abnormal value in the real-time power consumption data in the current period by using the preset abnormal value detection rule. The abnormal value is identified from the overall and local change dimensions, so as to improve the accuracy of the abnormal value identification and provide accurate identification results for the subsequent abnormal value correction.

[0026] S12, when there is an abnormal value in the real-time power consumption data in the current period, the real-time power consumption data of each time point in the current period is used to form a current power consumption data time point sequence, and the continuity of the current power consumption data time point sequence is determined.

[0027] S13, if the current power consumption data time point sequence is continuously abnormal, the abnormal value corresponding time point is removed from the current period, and the real-time power consumption data average value of the remaining time points is used as the correction value to correct the real-time power consumption data of the abnormal value, if the current power consumption data time point sequence is not continuously abnormal, the real-time power consumption data of the abnormal value is corrected by using linear interpolation. The abnormal value is properly handled by using a reasonable correction method, and the corrected power consumption data can better reflect the real power consumption condition of the user, thereby providing reliable data support for the operation and management of the power system.

[0028] The power consumption data change rate is obtained by obtaining the power consumption data difference value of the time point and its adjacent time point, and the ratio of the power consumption data difference value to the power consumption data of the adjacent time point is used as the power consumption data change rate.

[0029] The linear interpolation is obtained by obtaining the real-time power consumption data of the adjacent time points before and after the abnormal value corresponding time point, establishing a coordinate system with the time point as the horizontal axis and the real-time power consumption data as the vertical axis, and obtaining the real-time power consumption data of the abnormal value corresponding time point according to the established coordinate system.

[0030] In a specific embodiment, the preset abnormal value detection rule is set as follows: when the absolute deviation value of the real-time power consumption data of the user side at any time point in the current period and the power consumption data average value in the current period is greater than the set power consumption data deviation value, and the power consumption data change rate of the time point and its adjacent time point is greater than the set power consumption data change rate, the real-time power consumption data in the current period has an abnormal value.

[0031] The set power consumption data deviation value and the set power consumption data change rate are set as follows: the normal power consumption data of each time point in the corresponding period of the user side history is extracted from the intelligent metering terminal, the normal power consumption data difference value of each time point and its adjacent time point is obtained, and the maximum normal power consumption data difference value is selected as the set power consumption data deviation value.

[0032] The normal power consumption data change rate is obtained based on the normal power consumption data difference value of each time point and its adjacent time point, and the maximum power consumption data change rate is screened as the set power consumption data change rate. The user side historical same period can be the same time period in the same month.

[0033] The above sets the deviation value and change rate based on the normal power consumption data of the historical same period corresponding period, so that the set threshold is more in line with the actual power consumption law of the user, improves the adaptability and accuracy of the abnormal value detection, ensures that it can be dynamically adjusted according to the historical power consumption of the user, and enhances the effectiveness of the abnormal value detection.

[0034] In a specific embodiment, the current power consumption data time point sequence is continuously determined in the following manner: if the power consumption data of adjacent continuous multiple time points in the current power consumption data time point sequence is an abnormal value, the current power consumption data time point sequence is determined as a continuous abnormality, and if only the power consumption data of a single time point is an abnormal value and the power consumption data of adjacent time points is not an abnormal value, the current power consumption data time point sequence is determined as a non-continuous abnormality. In the present application, the adjacent continuous multiple time points can be 3 or more time points.

[0035] The present application collects real-time power consumption data of the user side in the current period by using an intelligent metering terminal, and distinguishes between continuous abnormality and non-continuous abnormality through abnormal value detection rules, and corrects using current period data or linear interpolation, solves the problem of deviation detection error caused by abnormal data, significantly improves the real-time data quality and deviation calculation accuracy, so that the subsequent adjustment instruction meets the actual demand.

[0036] S2, based on the corrected real-time power consumption data and the historical set period actual power consumption data, form an actual power consumption data time sequence, and compare it with the planned power consumption data of the formulated power purchase plan to mark the deviation time window. The historical set period is all the periods between the current period in the day.

[0037] As shown in Figure 3 The deviation time window marking method is as follows: S21, the corrected real-time power consumption data is incorporated into the real-time power consumption data of the current period, the real-time power consumption data of the current period and the actual power consumption data of the historical set period are sorted according to the time stamp to form an actual power consumption data time sequence.

[0038] S22, extract the planned power consumption data of the corresponding period from the formulated power purchase plan, and sort it according to the time stamp to form a planned power consumption data time sequence.

[0039] S23, align the actual power consumption data sequence and the planned power consumption data on the same time axis, if the actual power consumption data in a time period of the actual power consumption data sequence is different from the planned power consumption data in the corresponding time period of the planned power consumption data sequence, mark the time period as a deviation time window.

[0040] The application can find the deviation between the actual power consumption and the planned power consumption in time by comparing the actual power consumption data sequence and the planned power consumption data of the formulated power selling plan contract, provide basis for subsequent power consumption adjustment and power selling plan optimization, and guarantee the stable operation of the power system and the smooth execution of the power selling plan.

[0041] S3, dynamically analyze the actual power consumption data of the deviation time window and the planned power consumption data of the corresponding time window, and output the actual power selling deviation value.

[0042] It should be noted that the real-time power selling deviation value output method is to extract the actual power consumption data of the deviation time window from the intelligent metering terminal, compare the difference value between the actual power consumption data and the planned power consumption data of the corresponding time window in the formulated power selling plan, and output the actual power selling deviation value.

[0043] S4, determine the power selling dynamic deviation threshold of the deviation time window according to the user industry type and the historical deviation characteristic data, and trigger a warning signal when the actual power selling deviation value exceeds the power selling dynamic deviation threshold.

[0044] It should be noted that the power selling dynamic deviation threshold of the deviation time window is determined by screening the average historical power consumption data of each time window of each sample user side in a set time period from the power system power selling historical record, wherein the set time period can be weekly or monthly.

[0045] The same as the user industry attribute means that the user type, power consumption scale, power consumption time period and region are the same, and the user type includes but is not limited to industrial users, commercial users and agricultural users.

[0046] The screened average historical power consumption data of each sample user side in each time window is analyzed for deviation and change rate, and the historical power consumption data deviation value and the historical power consumption data change rate are output.

[0047] The historical power consumption data deviation value of each sample user side in the deviation time window is selected, the maximum historical power consumption data deviation value is coupled with the dynamic adjustment coefficient determined based on the historical power consumption data change rate for coupling analysis, and the power selling dynamic deviation threshold of the deviation time window is obtained.

[0048] The deviation analysis is to analyze the difference between the average historical power consumption data and the corresponding planned power consumption data, and output the historical power consumption data deviation value. The deviation analysis directly obtains the historical power consumption data deviation value, and clearly reflects the difference between the actual power consumption and the planned power consumption.

[0049] The change rate analysis is to analyze the difference between the historical power consumption data deviation value of a certain time window and the historical power consumption data deviation value of the corresponding previous time window, and take the ratio between the difference analysis result and the time length between the time windows as the historical power consumption data change rate. The change rate analysis reflects the change trend and speed of the deviation, and provides a key basis for determining the dynamic adjustment coefficient.

[0050] The time length between the time windows is the difference between the end time of a certain time window and the end time of the corresponding previous time window.

[0051] In a specific embodiment, the dynamic adjustment coefficient is determined based on the historical power consumption data change rate, specifically: determining the power consumption data deviation change trend according to the historical power consumption data change rate of each sample user side in each time window, and screening the power consumption data deviation change trend of the deviation time window and the adjacent time windows before and after the deviation time window.

[0052] If the power consumption data deviation change trend of the deviation time window and the adjacent time windows before and after the deviation time window is a monotonic trend, then the dynamic adjustment coefficient is output by exponential operation according to the average of the historical power consumption data change rates of the deviation time window and the adjacent time windows before and after the deviation time window. The monotonic trend includes a monotonic upward trend and a monotonic downward trend.

[0053] If the power consumption data deviation change trend of the deviation time window and the adjacent time windows before and after the deviation time window is a fluctuation trend, then the dynamic adjustment coefficient is output by exponential operation based on the change rate calculation result of the historical power consumption data deviation value of the deviation time window and the adjacent time windows before and after the deviation time window. The exponential operation is a standard form of a sigmoid function, and the change rate is taken as the independent variable of the sigmoid function.

[0054] When the historical power consumption data change rate of a certain time window is positive, the power consumption data deviation change trend of the time window is an upward trend. When the historical power consumption data change rate of a certain time window is negative, the power consumption data deviation change trend of the time window is a downward trend.

[0055] When the power consumption data deviation change trend of the deviation time window and the adjacent time windows before and after the deviation time window has both an upward trend and a downward trend, and the upward and downward trends are alternating, it is determined as a fluctuation trend.

[0056] The application calculates the dynamic adjustment coefficient by different methods according to different change trends of the power consumption data deviation, so that the adjustment coefficient can accurately reflect the change characteristics of the deviation, and the adaptability of the dynamic deviation threshold is improved, and the response capability of the threshold to complex power consumption conditions is enhanced.

[0057] It should be noted that the dynamic deviation threshold for selling electricity is obtained in the following manner: when the change trends of the power consumption data deviation of the deviation time window and its adjacent time windows before and after the deviation time window are both monotonous rising trends, or the change trends of the power consumption data deviation of the deviation time window and its adjacent time windows before and after the deviation time window are fluctuation trends and the change rate between the historical power consumption data deviation values of the adjacent time windows before and after the deviation time window is positive, the product of the maximum historical power consumption data deviation value and the dynamic adjustment coefficient is obtained, and the sum of the product and the maximum historical power consumption data deviation value is taken as the dynamic deviation threshold for selling electricity.

[0058] When the change trends of the power consumption data deviation of the deviation time window and its adjacent time windows before and after the deviation time window are both monotonous decreasing trends, or the change trends of the power consumption data deviation of the deviation time window and its adjacent time windows before and after the deviation time window are fluctuation trends and the change rate between the historical power consumption data deviation values of the adjacent time windows before and after the deviation time window is negative, the product of the maximum historical power consumption data deviation value and the dynamic adjustment coefficient is obtained, and the difference between the maximum historical power consumption data deviation value and the product is taken as the dynamic deviation threshold for selling electricity.

[0059] According to the user industry type, the application screens the historical power consumption data deviation values of each sample user side in the deviation time window, determines the dynamic deviation threshold for selling electricity in the deviation time window by the maximum historical power consumption data deviation value and the historical power consumption data change rate, solves the problem that the static threshold cannot adapt to the industry difference and load fluctuation, produces the effect of accurate early warning triggering, thereby reducing the false positive rate and the false negative rate, and improving the pertinence and economy of the selling electricity deviation control.

[0060] S5, user production plan data and power grid operation state data in the deviation time window are called, and the selling electricity deviation root type is positioned by fusion analysis, and a customized control strategy is generated based on the selling electricity deviation root type.

[0061] It should be noted that the positioning method of the selling electricity deviation root type is as follows: the user production plan data in the deviation time window and the corresponding original production plan data and the power grid operation state data and the safe operation state data are compared, and the selling electricity deviation root type is determined according to the comparison result.

[0062] In a specific embodiment, the specific content of judging the type of the deviation of the electricity sales according to the comparison result is as follows: if the user production plan data is inconsistent with the corresponding original production plan data, and the number of times of adjusting the user production plan data is greater than the set number of times of adjustment, the change of the user production plan is taken as the type of the deviation of the electricity sales.

[0063] If the grid operation state data deviates from the safe operation state data, and the deviation degree of the grid operation state data is greater than the set deviation degree threshold, the grid operation failure is taken as the type of the deviation of the electricity sales.

[0064] It should be noted that the set number of times of adjustment can refer to the production stability requirement of the user industry and the historical production plan adjustment situation. The production rhythm and flexibility of different industries are different, the production process of industrial users is relatively fixed, and too frequent adjustment may affect the production efficiency and product quality; the adjustment number of commercial users can be relatively high due to the greater influence of market changes; the electricity plan of agricultural users is relatively simple, and the adjustment demand is less; at the same time, the historical data statistics are combined to analyze the production plan adjustment frequency of the same industry and similar scale users in the past set period of time, and the average number of times of adjustment is taken as the set number of times of adjustment.

[0065] The set deviation degree threshold can refer to the historical grid failure data, and the critical value of the grid failure caused by the deviation degree of each parameter of the grid operation state data in the historical record is taken as the set deviation degree threshold of the corresponding parameter to avoid the occurrence of failure in advance.

[0066] The user production plan data includes the equipment start-stop plan, production shift arrangement plan and the like of industrial users; the business hours, promotion activity plan data of commercial users; and the electricity habit time, electricity duration of agricultural users.

[0067] The original production plan data refers to the production plan data formulated by the user side before the beginning of a production cycle and reported to the power system, which is used as the comparison benchmark of whether the user production plan is changed.

[0068] The safe operation state data refers to a data set that meets the grid safe operation parameter range specified in the relevant national power industry standards, including the standard values and allowable fluctuation ranges of the voltage, frequency, load and the like parameters in normal operation.

[0069] In a specific embodiment, the method for generating a customized control strategy based on the type of the deviation of the electricity sales is as follows: when the type of the deviation of the electricity sales is the change of the user production plan, a real-time communication mechanism of the user production plan information can be established, and the user is required to report to the power system management department one day before adjusting the production plan, and the power system management department arranges special personnel for docking to update the user electricity data in time.

[0070] When the power selling deviation root type is a power grid operation fault, the maintenance and repair of power grid equipment can be strengthened, a comprehensive equipment inspection plan is formulated, and state monitoring is performed on key equipment such as power transmission lines and transformers.

[0071] The application realizes accurate tracing of the deviation root by calling user production plan data and power grid operation state data, fusing and analyzing the data to locate the power selling deviation root type, and generating a customized control strategy based on the power selling deviation root type, increases the pertinence of the later adjustment strategy, improves the adjustment control efficiency, and reduces the power system regulation loss.

[0072] The above formulas are all dimensionless numerical calculations, the formulas are obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0073] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product.

[0074] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. A person skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0075] In addition, the functional modules in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0076] The above is merely 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 can easily think of changes or replacements 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 subject to the protection scope of the claims.

[0077] Finally, the above is only a preferred embodiment of the present application and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A power system power sale deviation monitoring control method, characterized by, The method comprises the following steps: Collecting real-time power consumption data of the user side in the current period through the intelligent metering terminal in the power system, identifying and correcting the real-time power consumption data based on the preset abnormal value detection rule, and generating corrected real-time power consumption data; Forming actual power consumption data time sequence based on the corrected real-time power consumption data and historical set period actual power consumption data, and comparing the actual power consumption data time sequence with the planned power consumption data of the formulated power selling plan to mark the deviation time window; Performing dynamic deviation analysis on the actual power consumption data of the deviation time window and the planned power consumption data of the corresponding time window, and outputting the actual power selling deviation value; Determining the power selling dynamic deviation threshold value of the deviation time window according to the user industry attribute and historical deviation characteristic data, and triggering a warning signal when the actual power selling deviation value exceeds the power selling dynamic deviation threshold value; The determination method of the power selling dynamic deviation threshold value of the deviation time window comprises the following steps: Filtering the average historical power consumption data of each sample user side in each time window within a set time period from the power system power selling historical records according to the same user industry attribute; Performing deviation analysis and change rate analysis on the filtered average historical power consumption data of each sample user side in each time window and the corresponding planned power consumption data, and outputting the historical power consumption data deviation value and the historical power consumption data change rate; Selecting the historical power consumption data deviation value of each sample user side in the deviation time window, coupling the maximum historical power consumption data deviation value with the dynamic adjustment coefficient determined based on the historical power consumption data change rate, and obtaining the power selling dynamic deviation threshold value of the deviation time window; Retrieving the user production plan data and power grid operation state data in the deviation time window, performing fusion analysis and positioning the power selling deviation root type, and generating a customized control strategy based on the power selling deviation root type.

2. The power system power selling deviation monitoring control method according to claim 1, characterized in that: The correction method of the real-time power consumption data comprises the following steps: According to the collected real-time power consumption data of the user side at each time point in the current period, obtaining the average power consumption data of the user side in the current period and the power consumption data change rate of each time point and its adjacent time point, and identifying whether there is an abnormal value in the current period real-time power consumption data through the preset abnormal value detection rule; When there is an abnormal value in the current period real-time power consumption data, the real-time power consumption data of each time point in the current period is formed into a current power consumption data time point sequence, and the current power consumption data time point sequence is continuously determined; If the current power consumption data time point sequence is continuous abnormality, the abnormal value corresponding time point is excluded from the current period, and the average value of the real-time power consumption data of the remaining time points is used as the correction value to correct the real-time power consumption data of the abnormal value, and if the current power consumption data time point sequence is non-continuous abnormality, the real-time power consumption data of the abnormal value is corrected by linear interpolation.

3. The power system power selling deviation monitoring control method according to claim 2, characterized in that: The continuous determination method of the current power consumption data time point sequence comprises the following steps: If the power consumption data of adjacent continuous multiple time points in the current power consumption data time point sequence is abnormal value, the current power consumption data time point sequence is determined as continuous abnormality, and if only the power consumption data of a single time point is abnormal value and the power consumption data of adjacent time points is not abnormal value, the current power consumption data time point sequence is determined as non-continuous abnormality.

4. The power system power selling deviation monitoring control method according to claim 2, characterized in that: The preset abnormal value detection rule is set in the following manner: When the absolute deviation value of the real-time power consumption data of the user side at any time point in the current period from the average value of the power consumption data in the current period is greater than the set power consumption data deviation value, and the power consumption data change rate of the time point and its adjacent time point is greater than the set power consumption data change rate, the real-time power consumption data in the current period has an abnormal value.

5. The power system power selling deviation monitoring control method according to claim 1, characterized in that: The deviation time window marking manner is as follows: The corrected real-time power consumption data is incorporated into the real-time power consumption data in the current period, and the real-time power consumption data in the current period and the actual power consumption data in the historical set period are sorted according to the time stamp to form an actual power consumption data time sequence; The plan power consumption data corresponding to the period is extracted from the formulated power selling plan, and is sorted according to the time stamp to form a plan power consumption data time sequence; The actual power consumption data time sequence and the plan power consumption data time sequence are aligned on the same time axis, and if the actual power consumption data in a certain period in the actual power consumption data time sequence is different from the plan power consumption data in the corresponding period in the plan power consumption data time sequence, the period is marked as a deviation time window.

6. The power system power selling deviation monitoring control method according to claim 5, characterized in that: The real-time power selling deviation value output manner is as follows: The actual power consumption data of the deviation time window is extracted from the intelligent metering terminal, and is compared with the plan power consumption data of the corresponding time window in the formulated power selling plan to output the actual power selling deviation value.

7. The power system power selling deviation monitoring control method according to claim 1, characterized in that: The dynamic adjustment coefficient is determined based on the historical power consumption data change rate in the following manner: The power consumption data deviation change trend of each sample user side in each time window is determined according to the historical power consumption data change rate, and the power consumption data deviation change trends of the deviation time window and its adjacent time windows are screened; If the power consumption data deviation change trends of the deviation time window and its adjacent time windows are monotonous trends, the dynamic adjustment coefficient is output by exponential operation according to the mean value of the historical power consumption data change rates of the deviation time window and its adjacent time windows; If the power consumption data deviation change trends of the deviation time window and its adjacent time windows are fluctuation trends, the historical power consumption data deviation values of the adjacent time windows corresponding to the deviation time window are calculated according to the change rate, and the dynamic adjustment coefficient is output by exponential operation based on the change rate calculation result.

8. The power system power selling deviation monitoring control method according to claim 1, characterized in that: The power selling deviation root type positioning manner is as follows: The user production plan data in the deviation time window and the power grid operation state data are called, the user production plan data is compared with the corresponding original production plan data and the power grid operation state data is compared with the safe operation state data, and the power selling deviation root type is determined according to the comparison result.

9. The power system power selling deviation monitoring control method according to claim 8, characterized in that: The specific content of determining the power selling deviation root type according to the comparison result is as follows: If the user production plan data is inconsistent with the corresponding original production plan data, and the adjustment times of the user production plan data are greater than the set adjustment times, the user production plan change is taken as the power selling deviation root type; If the power grid operation state data deviates from the safe operation state data, and the deviation degree of the power grid operation state data is greater than the set deviation degree threshold, the power grid operation fault is taken as the power selling deviation root type.

Images