A real-time monitoring method and system for campus energy consumption data based on data analysis

Abstract

The present application relates to the field of data processing technology, and specifically to a real-time monitoring method and system for campus energy consumption data based on data analysis, the method comprising: obtaining various electrical parameter data of each classroom in the campus; comparing the change difference between the current power consumption data and the historical power consumption data, obtaining the power consumption ratio, and extracting suspected abnormal classrooms; obtaining all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom; obtaining the current fluctuation of each suspected abnormal classroom; combining voltage data and effective power, obtaining the invalid power ratio and correcting it to obtain the invalid power ratio degree; based on the current fluctuation and the invalid power ratio degree, obtaining the classroom with abnormal energy consumption. The present application aims to analyze whether the energy consumption of each classroom in the campus is a normal load fluctuation, and to improve the sensitivity and accuracy of abnormal energy consumption data identification.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a real-time monitoring method and system for campus energy consumption data based on data analysis. Background Art

[0002] Energy consumption monitoring on campus is an important way to improve energy efficiency. By deploying intelligent energy consumption monitoring equipment, it is possible to collect data on the use of various energy sources such as electricity in real time, and analyze energy consumption trends and abnormal fluctuations. Through the data visualization system, these data will be displayed centrally, making it easier for managers to quickly identify problems and optimize resource allocation. Energy consumption monitoring can not only effectively reduce operating costs, but also help realize green campus construction and promote environmental protection.

[0003] Traditional power monitoring systems mainly rely on parameters such as power factor, voltage, current waveform and total power to monitor energy consumption anomalies, but when faced with changes in power load, these systems often have difficulty distinguishing between normal reactive power fluctuations and fluctuations caused by abnormal energy consumption data. In particular, when the characteristics of power loads change, an increase in reactive power may cause greater fluctuations in energy consumption data, and this change is not always a sign of a fault, which in turn triggers unnecessary alarms or incorrect fault judgments. Summary of the invention

[0004] In view of the above, it is necessary to provide a real-time monitoring method and system for campus energy consumption data based on data analysis to solve the above problems.

[0005] The first aspect of the present application provides a method for real-time monitoring of campus energy consumption data based on data analysis, the method comprising:

[0006] Obtain voltage data, current data, power consumption data, and effective power of each classroom on campus at all times;

[0007] Preset the time window for each moment, and obtain the power consumption proportion at each moment based on the change difference between the power consumption data in the time window at each moment and the power consumption data in the preset number of historical time periods, and extract all suspected abnormal classrooms at each moment;

[0008] At each moment, according to the current data in each suspected abnormal classroom, combined with the clustering algorithm, all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are obtained; according to the distribution of current data in each suspected abnormal classroom at each moment, combined with the number distribution of high current continuous segmented sequences and low current continuous segmented sequences, the current fluctuation of each suspected abnormal classroom at each moment is obtained;

[0009] At each moment, according to the number of elements of each high current continuous segmented sequence of each suspected abnormal classroom and the voltage data and effective power at the corresponding moment of the element, the invalid power ratio of each high current continuous segmented sequence of each suspected abnormal classroom is obtained; according to the numerical distribution of each high current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power ratio is corrected to obtain the invalid power ratio degree of each suspected abnormal classroom at each moment;

[0010] According to the current fluctuation and the proportion of the reactive power, the suspected abnormal classrooms are screened to obtain the classrooms with abnormal energy consumption.

[0011] The power consumption ratio at each moment is obtained as follows:

[0012] Based on each classroom, all the electricity consumption data in the time window at each moment are combined into a reference electricity consumption data sequence at each moment in chronological order; the elements and values ​​of the reference electricity consumption data sequence are calculated; and the reference electricity consumption data sequence with the largest element and value in a preset number of historical time periods is obtained as each historical reference electricity consumption data sequence;

[0013] Analyze the change difference between the reference electricity consumption data sequence at each moment and all historical reference electricity consumption data to obtain the electricity consumption proportion at each moment: obtain the difference between the last element and the first element of the reference electricity consumption data sequence at each moment, and record it as the first change; record the difference between the last element and the first element of each historical reference electricity consumption data sequence as the second change; obtain the average level of the second change of all historical reference electricity consumption data sequences, and record it as the mean change; take the product of the negative correlation mapping result of the mean change and the first change as the electricity consumption proportion at each moment.

[0014] The process of extracting all suspected abnormal classrooms at each time is as follows:

[0015] If the proportion of electricity consumption in each classroom at any time is greater than or equal to the preset electricity consumption threshold, the corresponding classroom will be marked as a suspected abnormal classroom.

[0016] The steps of obtaining all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are as follows:

[0017] The sequence of current data in the time window of each suspected abnormal classroom at each moment is recorded as a current data sequence; a clustering algorithm is used on the current data sequence to obtain a preset number of cluster clusters;

[0018] The cluster with the largest mean value of current data is recorded as the high current cluster, and the remaining clusters are recorded as low current clusters;

[0019] For high current clusters, the current data are arranged in chronological order, and the sequence composed of the current data at consecutive moments is recorded as a high current continuous segmented sequence; the low current continuous segmented sequence is obtained using the same method as the high current continuous segmented sequence.

[0020] The current fluctuation of each suspected abnormal classroom at each moment is obtained as follows:

[0021] Obtain the discrete degree of all elements in the current data sequence of each suspected abnormal classroom at each moment;

[0022] Calculate the mean of all elements in the high current cluster corresponding to the current data of each suspected abnormal classroom at each moment, and the mean of all elements in the low current cluster, which are recorded as the first mean and the second mean respectively; obtain the absolute value of the difference between the first mean and the second mean, which is recorded as the high-low difference;

[0023] Obtain the sum and absolute value of the difference between the number of all high-current continuous segmented sequences and the number of low-current continuous segmented sequences in each suspected abnormal classroom at each moment, and record them as the number sum and number difference, respectively; calculate the result of fusing the negative correlation mapping result of the number difference with the number sum to obtain the current fluctuation factor;

[0024] The result of fusing the discrete degree, the high and low difference, and the fluctuation factor is used as the current fluctuation of each suspected abnormal classroom at each moment.

[0025] The specific formula for obtaining the reactive power ratio of each high current continuous segment sequence of each suspected abnormal classroom is: ;in, Indicates The reactive power ratio of the mth high current continuous segment sequence in a suspected abnormal classroom, Represents the total number of elements in the mth high current continuous segment sequence of the yth suspected abnormal classroom; , , They respectively represent the active power, current data, and voltage data corresponding to the fth element in the mth high current continuous segmented sequence of the yth suspected abnormal classroom.

[0026] The process of correcting the reactive power ratio is specifically as follows:

[0027] The element mean and the difference between each element of each high-current continuous segmented sequence of each suspected abnormal classroom are obtained, and the product of the negative correlation mapping result after fusion of all the differences and the invalid power proportion is taken as the corrected invalid power proportion of each high-current continuous segmented sequence of each suspected abnormal classroom.

[0028] The reactive power ratio is specifically the average of the corrected reactive power ratios of all high current continuous segmented sequences of each suspected abnormal classroom at each moment.

[0029] The classrooms with abnormal energy consumption are obtained as follows:

[0030] Taking the normalized value of the product of the current fluctuation of each suspected abnormal classroom at each moment and the reactive power proportion as the abnormal value of each suspected abnormal classroom at each moment;

[0031] If the abnormal value is greater than or equal to a preset abnormal threshold, it is determined that the energy consumption of the suspected abnormal classroom is abnormal.

[0032] In the second aspect, an embodiment of the present application also provides a real-time monitoring system for campus energy consumption data based on data analysis, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0033] In the above scheme, the voltage data, current data, power consumption data, and effective power of each classroom in the campus at each moment are obtained, which is helpful to provide a data basis for the subsequent analysis of whether the campus energy consumption data is abnormal; the time window of each moment is preset, and the power consumption ratio of each moment is obtained according to the difference between the power consumption data in the time window of each moment and the power consumption data in the preset number of historical time periods, and all suspected abnormal classrooms at each moment are extracted, which has the beneficial effect of screening classrooms that may have abnormal energy consumption based on the change characteristics of power consumption data at different moments, thereby reducing the subsequent calculation amount; for each moment, according to the current data in each suspected abnormal classroom, combined with the clustering algorithm, all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are obtained, which has the beneficial effect of reflecting the drastic change or stable state of the current, which can provide an analysis basis for the subsequent acquisition of the detailed characteristics of the current fluctuation, and help to timely identify the abnormal current fluctuation; according to the distribution of the current data in each suspected abnormal classroom at each moment, combined with the number distribution of the high current continuous segmented sequence and the low current continuous segmented sequence, each suspected abnormal classroom at each moment is obtained. The current fluctuation of normal classrooms has the beneficial effect of reflecting the fluctuation characteristics of current in different classrooms at different times; for each moment, according to the number of elements of each high current continuous segmented sequence of each suspected abnormal classroom and the voltage data and effective power at the corresponding moment of the element, the invalid power ratio of each high current continuous segmented sequence of each suspected abnormal classroom is obtained, and the beneficial effect is that combined with other electrical parameter data, the energy consumption of each suspected abnormal classroom at each moment is further analyzed based on the change of invalid power ratio; the equipment may generate higher invalid power in a specific high current period. According to the numerical distribution of each high current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power ratio is corrected, and the beneficial effect is that by analyzing the details of the numerical distribution, it can be distinguished whether the energy consumption of each classroom is a normal load fluctuation or a manifestation of equipment failure; the suspected abnormal classrooms are screened to obtain classrooms with abnormal energy consumption. The corrected invalid power ratio can improve the sensitivity and accuracy of identifying abnormal energy consumption data of the campus, and avoid misjudgment of normal energy consumption data of the campus due to changes in power load. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a method for real-time monitoring of campus energy consumption data based on data analysis provided in one embodiment of the present application;

[0035] Figure 2 A flowchart for obtaining the reactive power ratio provided in one embodiment of the present application. DETAILED DESCRIPTION

[0036] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0038] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0040] The following is a detailed description of a specific scheme of a real-time monitoring method and system for campus energy consumption data based on data analysis provided by the present application in conjunction with the accompanying drawings.

[0041] See also Figure 1 , which shows a flowchart of a method for real-time monitoring of campus energy consumption data based on data analysis provided by an embodiment of the present application, the method comprising the following steps:

[0042] The first step: obtain the voltage data, current data, power consumption data, and effective power of each classroom in the campus at all times.

[0043] A smart meter is installed in each classroom to comprehensively monitor and record the classroom's electricity usage; the smart meter is used to collect various electrical parameters at every moment in real time. In this embodiment, the electrical parameters include voltage, current, power consumption, and active power; the electrical parameters in this embodiment are collected synchronously, and the collection time interval is 0.5 minutes; the implementer can adjust the type of electrical parameters collected and the time interval for data collection according to actual conditions, and this application does not impose any restrictions on this.

[0044] The second step: preset the time window for each moment, obtain the power consumption proportion at each moment according to the difference between the power consumption data in the time window at each moment and the power consumption data in the preset number of historical time periods, and extract all suspected abnormal classrooms at each moment.

[0045] When the electrical equipment in the classroom has problems such as aging or leakage, it will lead to waste of electric energy, thereby increasing power consumption. Therefore, based on each classroom, a time window of each moment is preset, and all the power consumption data in the time window of each moment are combined into a reference power consumption data sequence of each moment in chronological order; the elements and values ​​of the reference power consumption data sequence are calculated; and the reference power consumption data sequence with the largest element and value in a preset number of historical time periods is obtained as each historical reference power consumption data sequence.

[0046] In this embodiment, the time length corresponding to the time window is 10 minutes; the preset number is 30; the time length of the historical time period is one day, and the implementer can adjust it according to the actual situation, and this application does not impose any restrictions on this.

[0047] Analyze the change difference between the reference electricity consumption data sequence at each moment and all historical reference electricity consumption data to obtain the electricity consumption proportion at each moment: obtain the difference between the last element and the first element of the reference electricity consumption data sequence at each moment, and record it as the first change; record the difference between the last element and the first element of each historical reference electricity consumption data sequence as the second change; obtain the average level of the second change of all historical reference electricity consumption data sequences, and record it as the mean change; take the ratio of the first change to the mean change as the electricity consumption proportion at each moment.

[0048] In this embodiment, the difference between two elements is measured by subtraction, and the average level of multiple variables is measured by the average value. It should be noted that since the power consumption at each moment is a cumulative value, that is, the power consumption data increases with time, the first change amount and the second change amount are both greater than or equal to 0; it should be further noted that a denominator of 0 will make the power consumption ratio meaningless, so a preset value greater than zero is added to the denominator, and the value of this embodiment is 0.1.

[0049] It should be understood that the larger the difference between the last element and the first element in the reference power consumption data sequence of each classroom at each moment, the greater the change in power consumption in that time period, and the greater the proportion of power consumption at each moment, and the greater the possibility of abnormal data.

[0050] If the proportion of electricity consumption in each classroom at each moment is greater than or equal to the preset electricity consumption threshold, the corresponding classroom will be marked as a suspected abnormal classroom; in this embodiment, the value of the electricity consumption threshold is 1.2, and the implementer can adjust it according to the actual situation. It should be noted that if there is no suspected abnormal classroom at the current moment, the electricity consumption data of the next moment will continue to be processed.

[0051] The third step: for each moment, based on the current data in each suspected abnormal classroom, combined with the clustering algorithm, all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are obtained; based on the distribution of current data in each suspected abnormal classroom at each moment, combined with the number distribution of high current continuous segmented sequences and low current continuous segmented sequences, the current fluctuation of each suspected abnormal classroom at each moment is obtained.

[0052] When the number of electrical devices in the classroom increases, the overall power consumption also increases, which may interfere with the screening of abnormal data and affect the accuracy of the screening results. Therefore, it is necessary to further screen the abnormal data caused by abnormal devices. In this process, if the device is aging or has leakage problems, its current will become very unstable, showing large fluctuations.

[0053] The sequence composed of the current data in the time window of each suspected abnormal classroom at each moment is recorded as the current data sequence; the clustering algorithm is used to obtain a preset number of cluster clusters for the current data sequence; the clustering algorithm used in this application is the K-means clustering algorithm, and the preset value is 2, which can be adjusted by the implementer according to the actual situation; the cluster cluster with the largest mean of the current data is recorded as the high current cluster cluster, and the remaining cluster clusters are recorded as low current cluster clusters.

[0054] For high current clusters, the current data are arranged in chronological order, and the sequence composed of the current data at consecutive moments is recorded as a high current continuous segmented sequence; for example, the moments corresponding to the current data in the high current cluster are 1, 2, 5, 7, and 8 respectively; then the sequence composed of the current data corresponding to moments 1 and 2 is recorded as the first high current continuous segmented sequence; the sequence composed of the current data corresponding to moment 5 is recorded as the second high current continuous segmented sequence; the sequence composed of the current data corresponding to moments 7 and 8 is recorded as the third high current continuous segmented sequence.

[0055] The same method as the high current continuous segmented sequence is used to obtain the low current continuous segmented sequence of the low current clustering cluster. It should be understood that the current data sequence of a suspected abnormal classroom corresponds to a high current clustering cluster and a low current clustering cluster; a high current clustering cluster corresponds to multiple high current continuous segmented sequences, and a low current clustering cluster corresponds to multiple low current continuous segmented sequences.

[0056] According to the element distribution of the current data sequence of each suspected abnormal classroom at each moment, combined with the number distribution of high current continuous segmented sequences and low current continuous segmented sequences, the current fluctuation of each suspected abnormal classroom at each moment is obtained: the discrete degree of all elements in the current data sequence of each suspected abnormal classroom at each moment is obtained; the mean of all elements in the high current clustering cluster corresponding to the current data of each suspected abnormal classroom at each moment and the mean of all elements in the low current clustering cluster are calculated, which are respectively recorded as the first mean and the second mean; the absolute value of the difference between the first mean and the second mean is obtained, which is recorded as the high-low difference; the sum and absolute values ​​of the difference between the number of all high current continuous segmented sequences and the number of low current continuous segmented sequences of each suspected abnormal classroom at each moment are obtained, which are respectively recorded as the number sum and the number difference; the ratio of the number sum to the number difference is calculated, which is recorded as the current fluctuation factor; the result of fusing the discrete degree, the high-low difference and the fluctuation factor is taken as the current fluctuation of each suspected abnormal classroom at each moment.

[0057] In this embodiment, the current fluctuation of the yth suspected abnormal classroom at each moment is recorded as , its formula form is: ;in, It represents the variance of all elements in the current data sequence of the yth suspected abnormal classroom at each moment, and measures the degree of discreteness of all elements in the electrical parameter data sequence; , They represent the first mean and second mean of the yth suspected abnormal classroom at each moment respectively; Represents the number of high current continuous segment sequences of the yth suspected abnormal classroom at each moment; represents the number of low current continuous segmented sequences of the yth suspected abnormal classroom at each moment; represents a preset value greater than zero, and in this embodiment, the value is 0.1; Denote it as the fluctuation factor of the yth suspected abnormal classroom at each moment.

[0058] It should be understood that the greater the discreteness of all elements in the current data sequence of each suspected abnormal classroom at each moment, the greater the current volatility; the greater the sum of the number of high current continuous segmented sequences and the number of low current continuous segmented sequences, and the smaller the difference in the number of high current continuous segmented sequences and the number of low current continuous segmented sequences, the greater the current volatility of each suspected abnormal classroom at each moment; the greater the change between the first mean and the second mean of the current data sequence of each suspected abnormal classroom, the greater the current volatility of the first and second segments. The greater the current fluctuation of a suspected abnormal classroom at each moment, the greater the possibility that the energy consumption of the corresponding suspected abnormal classroom is abnormal.

[0059] The fourth step: for each moment, according to the number of elements in each high-current continuous segmented sequence of each suspected abnormal classroom and the voltage data and effective power at the corresponding moment of the element, the invalid power proportion of each high-current continuous segmented sequence of each suspected abnormal classroom is obtained; according to the numerical distribution of each high-current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power proportion is corrected to obtain the invalid power proportion degree of each suspected abnormal classroom at each moment.

[0060] In order to improve the accuracy of screening classrooms with abnormal energy consumption, the power change characteristics caused by equipment aging and other conditions can be used for screening. Specifically, when the equipment ages, its ineffective power will increase. This means that when the equipment is running, in addition to consuming effective power, more and more energy will be converted into ineffective power, resulting in energy waste and overall efficiency reduction.

[0061] At each moment, according to the number of elements in each high current continuous segmented sequence of each suspected abnormal classroom and the voltage and effective power data at the corresponding moment of the element, the reactive power ratio of each high current continuous segmented sequence of each suspected abnormal classroom is obtained; The reactive power ratio of the mth high current continuous segment sequence in a suspected abnormal classroom is recorded as , its formula form is: ;in, Represents the total number of elements in the mth high current continuous segment sequence of the yth suspected abnormal classroom; , , They respectively represent the active power, current data, and voltage data corresponding to the fth element in the mth high current continuous segmented sequence of the yth suspected abnormal classroom.

[0062] It should be understood that the reactive power will change with the change of current, so when the current is small, the reactive power will also decrease. Since the reactive power is at a normal value due to the small current, this situation has no reference significance, so this application uses other electrical parameter data at the corresponding moments of the high current continuous segmented sequence for analysis.

[0063] Based on this, each high current continuous segment sequence of each suspected abnormal classroom at each moment has an invalid power ratio.

[0064] Furthermore, according to the numerical distribution of each high-current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power ratio is corrected to obtain the invalid power ratio degree of each suspected abnormal classroom at each moment: the element mean of each high-current continuous segmented sequence of each suspected abnormal classroom and the difference between each element are obtained, and the product of the negative correlation mapping result after fusion of all the differences obtained and the invalid power ratio is used as the corrected invalid power ratio of each high-current continuous segmented sequence of each suspected abnormal classroom; the mean of the corrected invalid power ratios of all high-current continuous segmented sequences of each suspected abnormal classroom is used as the invalid power ratio degree of each suspected abnormal classroom.

[0065] In this embodiment, the corrected ineffective efficiency ratio of the mth high current continuous segment sequence of the yth suspected abnormal classroom at each moment is recorded as , its formula form is: ;in, Represents the total number of elements in the mth high current continuous segment sequence of the yth suspected abnormal classroom; represents the value of the fth element in the mth high current continuous segment sequence of the yth suspected abnormal classroom; represents the element mean of the mth high current continuous segmented sequence of the yth suspected abnormal classroom; Indicates The proportion of reactive power in the mth high current continuous segment sequence of a suspected abnormal classroom; exp() represents an exponential function with a natural constant as the base; The negative correlation mapping result after fusing the element mean of each high current continuous segmented sequence of each suspected abnormal classroom with the difference between all elements.

[0066] Among them, the flowchart for obtaining the reactive power ratio is as follows: Figure 2 shown.

[0067] It should be understood that when the current data in the high-current continuous segmented sequence is relatively stable, the more accurate the calculated reactive power is, the greater the reference significance is; the greater the proportion of reactive power in each high-current continuous segmented sequence of each suspected abnormal classroom, the greater the proportion of reactive power in each suspected abnormal classroom.

[0068] The fifth step: based on the current fluctuation and the proportion of the invalid power, the suspected abnormal classrooms are screened to obtain the classrooms with abnormal energy consumption.

[0069] If the current fluctuation of each suspected abnormal classroom at each moment is greater, and the proportion of its ineffective power is also greater, the possibility of abnormal energy consumption in the suspected abnormal classroom is greater. Based on this, the normalized value of the product of the current fluctuation of each suspected abnormal classroom at each moment and the proportion of the ineffective power is used as the abnormal value of each suspected abnormal classroom at each moment. In this embodiment, the normalization method uses the sigmoid function.

[0070] If the abnormal value is greater than or equal to the preset abnormal threshold, the energy consumption of the suspected abnormal classroom is judged to be abnormal, and the staff is reminded to check the classroom with abnormal energy consumption to eliminate hidden dangers. In this embodiment, the abnormal threshold is 0.7, and the implementer can adjust it according to the actual situation.

[0071] Based on the same inventive concept as the above method, an embodiment of the present application also provides a real-time monitoring system for campus energy consumption data based on data analysis, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned methods for real-time monitoring of campus energy consumption data based on data analysis.

[0072] In summary, obtaining the voltage data, current data, power consumption data, and effective power of each classroom in the campus at each moment is helpful to provide a data basis for the subsequent analysis of whether the campus energy consumption data is abnormal; presetting the time window at each moment, and obtaining the power consumption proportion at each moment according to the change difference between the power consumption data in the time window at each moment and the power consumption data in a preset number of historical time periods, and extracting all suspected abnormal classrooms at each moment, which has the beneficial effect of screening classrooms that may have abnormal energy consumption based on the change characteristics of power consumption data at different moments, thereby reducing the subsequent amount of calculation; for each moment, according to the current data in each suspected abnormal classroom, combined with the clustering algorithm, all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are obtained, which has the beneficial effect of reflecting the drastic change or stable state of the current, which can provide an analysis basis for the subsequent acquisition of the detailed characteristics of the current fluctuation, and help to timely identify the abnormal current fluctuation; according to the distribution of the current data in each suspected abnormal classroom at each moment, combined with the number distribution of the high current continuous segmented sequence and the low current continuous segmented sequence, each suspected abnormal classroom at each moment is obtained. The current fluctuation of normal classrooms has the beneficial effect of reflecting the fluctuation characteristics of current in different classrooms at different times; for each moment, according to the number of elements of each high current continuous segmented sequence of each suspected abnormal classroom and the voltage data and effective power at the corresponding moment of the element, the invalid power ratio of each high current continuous segmented sequence of each suspected abnormal classroom is obtained, and the beneficial effect is that combined with other electrical parameter data, the energy consumption of each suspected abnormal classroom at each moment is further analyzed based on the change of invalid power ratio; the equipment may generate higher invalid power in a specific high current period. According to the numerical distribution of each high current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power ratio is corrected, and the beneficial effect is that by analyzing the details of the numerical distribution, it can be distinguished whether the energy consumption of each classroom is a normal load fluctuation or a manifestation of equipment failure; the suspected abnormal classrooms are screened to obtain classrooms with abnormal energy consumption. The corrected invalid power ratio can improve the sensitivity and accuracy of identifying abnormal energy consumption data of the campus, and avoid misjudgment of normal energy consumption data of the campus due to changes in power load.

[0073] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0074] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A real-time monitoring method for campus energy consumption data based on data analysis, characterized in that: The method comprises the following steps: Obtain voltage data, current data, power consumption data, and effective power of each classroom on campus at all times; Preset the time window for each moment, and obtain the power consumption proportion at each moment based on the change difference between the power consumption data in the time window at each moment and the power consumption data in the preset number of historical time periods, and extract all suspected abnormal classrooms at each moment; At each moment, according to the current data in each suspected abnormal classroom, combined with the clustering algorithm, all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are obtained; according to the distribution of current data in each suspected abnormal classroom at each moment, combined with the number distribution of high current continuous segmented sequences and low current continuous segmented sequences, the current fluctuation of each suspected abnormal classroom at each moment is obtained; At each moment, according to the number of elements of each high current continuous segmented sequence of each suspected abnormal classroom and the voltage data and effective power at the corresponding moment of the element, the invalid power ratio of each high current continuous segmented sequence of each suspected abnormal classroom is obtained; according to the numerical distribution of each high current continuous segmented sequence of each suspected abnormal classroom at each moment, the invalid power ratio is corrected to obtain the invalid power ratio degree of each suspected abnormal classroom at each moment; The normalized value of the product of the current fluctuation of each suspected abnormal classroom at each moment and the reactive power proportion is used as the abnormal value of each suspected abnormal classroom at each moment, and the suspected abnormal classrooms are screened according to the abnormal values ​​to obtain classrooms with abnormal energy consumption; The specific formula for obtaining the reactive power ratio of each high current continuous segment sequence of each suspected abnormal classroom is: ;in, Indicates The reactive power ratio of the mth high current continuous segment sequence in a suspected abnormal classroom, Represents the total number of elements in the mth high current continuous segment sequence of the yth suspected abnormal classroom; , , They represent the active power, current data, and voltage data corresponding to the fth element in the mth high current continuous segmented sequence of the yth suspected abnormal classroom respectively; The process of correcting the reactive power ratio is specifically as follows: Obtain the difference between the element mean and each element of each high current continuous segmented sequence of each suspected abnormal classroom, and multiply the product of the negative correlation mapping result after fusion of all the obtained differences and the reactive power proportion as the corrected reactive power proportion of each high current continuous segmented sequence of each suspected abnormal classroom; The reactive power ratio is specifically the average of the corrected reactive power ratios of all high current continuous segmented sequences of each suspected abnormal classroom at each moment.

2. A real-time monitoring method for campus energy consumption data based on data analysis as claimed in claim 1, characterized in that: The proportion of electricity consumption at each moment is obtained as follows: Based on each classroom, all the electricity consumption data in the time window at each moment are combined into a reference electricity consumption data sequence at each moment in chronological order; the elements and values ​​of the reference electricity consumption data sequence are calculated; and the reference electricity consumption data sequence with the largest element and value in a preset number of historical time periods is obtained as each historical reference electricity consumption data sequence; Analyze the change difference between the reference power consumption data sequence at each moment and all historical reference power consumption data to obtain the power consumption proportion at each moment: obtain the difference between the last element and the first element of the reference power consumption data sequence at each moment, recorded as the first change; The difference between the last element and the first element of each historical reference power consumption data sequence is recorded as the second variation; The average level of the second variation of all historical reference power consumption data sequences is obtained, recorded as the variation mean; and the product of the negative correlation mapping result of the variation mean and the first variation is taken as the power consumption proportion at each moment.

3. A real-time monitoring method for campus energy consumption data based on data analysis as claimed in claim 1, characterized in that: The process of extracting all suspected abnormal classrooms at each time is as follows: If the power consumption ratio of each classroom at any time is greater than or equal to the preset power consumption threshold, the corresponding classroom will be marked as a suspected abnormal classroom.

4. A real-time monitoring method for campus energy consumption data based on data analysis as claimed in claim 1, characterized in that: The steps of obtaining all high current continuous segmented sequences and low current continuous segmented sequences of each suspected abnormal classroom are: The sequence of current data in the time window of each suspected abnormal classroom at each moment is recorded as a current data sequence; a clustering algorithm is used on the current data sequence to obtain a preset number of cluster clusters; The cluster with the largest mean value of current data is recorded as the high current cluster, and the remaining clusters are recorded as low current clusters; For high current clusters, the current data are arranged in chronological order, and the sequence composed of the current data at consecutive moments is recorded as a high current continuous segmented sequence; the low current continuous segmented sequence is obtained using the same method as the high current continuous segmented sequence.

5. A real-time monitoring method for campus energy consumption data based on data analysis as claimed in claim 4, characterized in that: The current fluctuation of each suspected abnormal classroom at each time is obtained as follows: Obtain the discrete degree of all elements in the current data sequence of each suspected abnormal classroom at each moment; Calculate the mean of all elements in the high current cluster corresponding to the current data of each suspected abnormal classroom at each moment, and the mean of all elements in the low current cluster, which are recorded as the first mean and the second mean respectively; obtain the absolute value of the difference between the first mean and the second mean, which is recorded as the high-low difference; Obtain the sum and absolute value of the difference between the number of all high-current continuous segmented sequences and the number of low-current continuous segmented sequences in each suspected abnormal classroom at each moment, and record them as the sum and the difference, respectively; Calculate the result of fusing the negative correlation mapping result of the quantity difference with the quantity sum value to obtain the current fluctuation factor; The result of fusing the discrete degree, the high and low difference, and the fluctuation factor is used as the current fluctuation of each suspected abnormal classroom at each moment.

6. A real-time monitoring method for campus energy consumption data based on data analysis as claimed in claim 1, characterized in that: The classrooms with abnormal energy consumption are specifically: If the abnormal value is greater than or equal to a preset abnormal threshold, it is determined that the energy consumption of the suspected abnormal classroom is abnormal.

7. A real-time monitoring system for campus energy consumption data based on data analysis, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images