CN117349624A

CN117349624A - Electric power energy monitoring method, system, terminal equipment and storage medium

Info

Publication number: CN117349624A
Application number: CN202311410550.6A
Authority: CN
Inventors: 方宇林; 刘洋
Original assignee: Nanjing Guorui Energy Technology Co ltd
Current assignee: Nanjing Guorui Energy Technology Co ltd
Priority date: 2023-10-26
Filing date: 2023-10-26
Publication date: 2024-01-05

Abstract

The present disclosure relates to the field of energy monitoring technologies, and in particular, to a method, a system, a terminal device, and a storage medium for monitoring electric power energy. If the power quality evaluation coefficient meets a preset power energy monitoring standard, carrying out time sequence analysis on target power energy data in an energy data monitoring group to generate corresponding periodic trend characteristics; importing the periodic trend characteristics into a preset regression model for training, and generating a corresponding electric power operation prediction mode as an electric power energy monitoring result; if the power quality evaluation coefficient does not accord with the preset power energy monitoring standard, acquiring and marking a corresponding abnormal energy data monitoring group to generate a corresponding abnormal data analysis group; and then, carrying out abnormal characteristic analysis on the abnormal data analysis group to form a corresponding abnormal classification ranking table, and generating a corresponding abnormal classification early warning mechanism plan as a power energy monitoring result according to the abnormal classification ranking table. The application scheme can promote electric power energy monitoring effect.

Description

Electric power energy monitoring method, system, terminal equipment and storage medium

Technical Field

The present disclosure relates to the field of energy monitoring technologies, and in particular, to a method, a system, a terminal device, and a storage medium for monitoring electric power energy.

Background

The electric power energy monitoring refers to the process of monitoring, collecting, analyzing and processing key parameters, indexes and data in an electric power system in real time by utilizing advanced technical means. The energy-saving system aims at ensuring safe operation of the power system, optimizing energy utilization efficiency, reducing energy loss and improving reliability and stability of the power energy system.

Power energy monitoring involves a number of aspects including monitoring and analysis of power parameters such as voltage, current, power factor, harmonics, power quality, etc.; acquiring and analyzing information such as the running state, the load condition, fault diagnosis and the like of the power equipment in real time; and monitoring and managing the standby capacity, load prediction, power market operation and the like of the power network. Through electric power energy monitoring, faults and problems in an electric power system can be quickly found and positioned, measures are timely taken to treat, and the occurrence and duration of power failure accidents are avoided or reduced. Meanwhile, the monitoring and management of the power utilization behavior of the electric power can be realized, the reasonable distribution and utilization of the electric power resources are promoted, and the utilization efficiency and sustainable development level of the energy are improved.

In practical application, aiming at mass data generated by an electric power energy monitoring system, a traditional data monitoring method cannot fully mine potential rules and information, and has low processing efficiency on large-scale data, some complex and important data features may be omitted, so that the electric power energy monitoring effect is poor.

Disclosure of Invention

In order to improve the electric power energy monitoring effect, the application provides an electric power energy monitoring method, an electric power energy monitoring system, terminal equipment and a storage medium.

In a first aspect, the present application provides a method for monitoring electric power energy, including the steps of:

acquiring electric power energy data, and dividing the electric power energy data according to a preset energy data classification monitoring strategy to form a corresponding energy data monitoring group;

performing evaluation analysis on the energy data monitoring group according to a preset energy data evaluation index to generate a power quality evaluation coefficient corresponding to the energy data monitoring group;

if the power quality evaluation coefficient meets a preset power energy monitoring standard, carrying out time sequence analysis on target power energy data in the energy data monitoring group, and generating periodic trend characteristics corresponding to the energy data monitoring group;

Importing the periodic trend characteristics into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result;

if the power quality evaluation coefficient does not accord with the preset power energy monitoring standard, acquiring a corresponding abnormal energy data monitoring group, marking the abnormal power energy data in the abnormal energy data monitoring group, and generating a corresponding abnormal data analysis group;

performing abnormal characteristic analysis on the abnormal data analysis group to generate a corresponding abnormal analysis type, and performing security level sequencing on the abnormal analysis type according to a preset power operation security standard to form a corresponding abnormal classification sequencing table;

and generating a corresponding abnormality grading early warning mechanism plan as the electric power energy monitoring result according to the abnormality classification ranking table.

By adopting the technical scheme, the electric power energy data are classified into groups and evaluated and analyzed, so that the electric power quality problem can be timely and effectively found and the running condition of various electric power energy sources can be predicted, namely, various target electric power energy source data in the energy data group in a normal running state are subjected to time sequence analysis to obtain corresponding periodic trend characteristics, the corresponding electric power running prediction mode is analyzed according to the periodic trend characteristics, and the abnormal electric power energy source data in the abnormal energy source data group are analyzed and graded early-warned, so that various electric power abnormal conditions can be timely dealt with, further, an electric power energy source system can be effectively regulated and optimized, and the power supply quality and the energy utilization efficiency are further improved. Because various electric power energy data are divided into groups, the electric power energy data under normal operation are subjected to time sequence analysis to obtain corresponding electric power operation modes, various abnormal energy data monitoring groups are subjected to marking analysis and sequencing, and corresponding grading early warning mechanisms are made, so that the electric power energy monitoring effect is improved.

Optionally, the acquiring the electric power energy data and dividing the electric power energy data according to a preset energy data classification monitoring policy to form a corresponding energy data monitoring group includes the following steps:

acquiring associated influence data corresponding to the electric power energy data according to the preset energy data classification monitoring strategy;

performing association attribute analysis on the electric power energy data and the association influence data to generate a corresponding association influence mode;

acquiring operation characteristics corresponding to the electric power energy data in the association influence mode, and generating corresponding monitoring classification indexes according to the operation characteristics;

and dividing the electric power energy data according to the monitoring classification indexes to form corresponding energy data monitoring groups.

By adopting the technical scheme, the electric power energy data and the associated influence data thereof are subjected to associated attribute analysis, corresponding monitoring classification indexes are generated according to the operation characteristics of the electric power energy data and the associated influence data, and the electric power energy data can be subjected to classified clustering monitoring according to the various monitoring classification indexes, so that the electric power energy monitoring effect is improved.

Optionally, after acquiring the associated influence data corresponding to the electric power energy data according to the preset energy data classification monitoring policy, the method further includes the following steps:

Acquiring the data type of the associated influence data;

if the data type is the electric power energy data, calibrating corresponding independent variable electric power energy data and dependent variable electric power energy data according to the association relation between the electric power energy data and the association influence data;

acquiring a corresponding association influence mode between the independent variable power energy data and the dependent variable power energy data, and acquiring a corresponding safety monitoring index according to the association influence mode;

and generating a first electric power energy monitoring strategy corresponding to the electric power energy data by combining the association influence mode and the safety monitoring index.

By adopting the technical scheme, the independent variable electric power energy data and the dependent variable electric power energy data can be calibrated according to the association relation between the electric power energy data and the association influence data. Therefore, the relation between the electric power energy data and the associated influence data can be better understood, a more accurate electric power energy monitoring strategy is generated, the electric power energy monitoring effect can be improved, and the stability and safety of the electric power energy are ensured.

Optionally, after acquiring the data type of the association influence data, the method further comprises the following steps:

If the data type is the non-electric power energy data, acquiring the associated influence characteristics of the associated influence data relative to the electric power energy data;

if the associated influence features are multiple, a multi-source associated influence model corresponding to the electric power energy data is established according to each associated influence feature, and a corresponding abnormal trend prediction instruction is output;

and according to the abnormal trend prediction indication, formulating an abnormal monitoring index corresponding to the electric power energy data as a second electric power energy monitoring strategy.

By adopting the technical scheme, a multi-source association influence model corresponding to the electric power energy data is established according to each association influence characteristic. The model can consider a plurality of influence factors at the same time, so that the change condition of the electric power energy source can be more comprehensively and deeply understood, and the monitoring efficiency is improved.

Optionally, the step of introducing the periodic trend feature into a preset regression model for training, and generating the power operation prediction mode corresponding to the energy data monitoring group as the power energy monitoring result includes the following steps:

importing the periodic trend characteristics into a preset regression model for training, and generating a corresponding electric power energy prediction value;

Acquiring a numerical value difference between the electric power energy predicted value and an electric power energy observed value corresponding to the electric power energy data, and judging whether the numerical value difference is in a preset difference threshold value interval or not;

and if the numerical value difference is in the preset difference threshold interval, extracting power operation related characteristics corresponding to the power energy predicted value, and generating the power operation prediction mode corresponding to the energy data monitoring group according to the power operation related characteristics to serve as the power energy monitoring result.

By adopting the technical scheme, the electric power operation prediction mode can be updated in real time to reflect the latest change condition of the electric power energy, so that the abnormal condition of the electric power energy can be found in time, the internal rule and trend of the electric power energy can be further predicted, and the monitoring effect of the electric power energy is improved.

Optionally, performing abnormal feature analysis on the abnormal data analysis group to generate a corresponding abnormal analysis type, and performing security level ranking on the abnormal analysis type according to a preset power operation security standard to form a corresponding abnormal classification ranking table, where the steps include:

if the number of the abnormal analysis types is multiple, obtaining abnormal attributes corresponding to the abnormal analysis types, and setting an abnormal label corresponding to the abnormal analysis type according to the abnormal attributes;

Classifying the plurality of abnormal analysis types according to the abnormal labels, generating corresponding abnormal feature sets, and constructing a corresponding abnormal electric power energy source mode library according to the abnormal feature sets.

By adopting the technical scheme, various abnormal analysis types are subjected to characteristic analysis, so that the abnormal conditions of the electric power energy can be more accurately identified, the corresponding abnormal electric power energy mode library is further classified and constructed, and the abnormal conditions and the processing method of the electric power energy can be accumulated and summarized, thereby improving the monitoring effect of the electric power energy and being beneficial to reducing the operation risk of the electric power energy.

Optionally, after obtaining the exception attribute corresponding to each exception analysis type if the exception analysis types are multiple, setting the exception label corresponding to the exception analysis type according to the exception attribute, further includes the following steps:

if abnormal association exists between the abnormal analysis types, a corresponding target abnormal analysis type is obtained, and a corresponding abnormal association group is generated according to the target abnormal analysis type;

and establishing a corresponding abnormal superposition prediction model according to the abnormal association indication corresponding to the abnormal association group, and outputting a power energy abnormality prediction result corresponding to the abnormal association group.

By adopting the technical scheme, the corresponding abnormal association group is generated according to the target abnormal analysis type, the corresponding abnormal superposition prediction model is further established, and the influence of a plurality of abnormal analysis types can be simultaneously considered through the abnormal superposition prediction model, so that the change condition of the electric power energy source is more comprehensively and deeply understood, and the monitoring efficiency is improved.

In a second aspect, the present application provides an electrical energy monitoring system comprising:

the monitoring classification module is used for acquiring electric power energy data, and dividing the electric power energy data according to a preset energy data classification monitoring strategy to form a corresponding energy data monitoring group;

the quality evaluation module is used for performing evaluation analysis on the energy data monitoring group according to a preset energy data evaluation index and generating an electric power quality evaluation coefficient corresponding to the energy data monitoring group;

the time sequence feature analysis module is used for carrying out time sequence analysis on target electric power energy data in the energy data monitoring group and generating periodic trend features corresponding to the energy data monitoring group if the electric power quality evaluation coefficient accords with a preset electric power energy monitoring standard;

The first monitoring module is used for importing the periodic trend characteristics into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result;

the abnormal marking module is used for acquiring a corresponding abnormal energy data monitoring group and marking the abnormal power energy data in the abnormal energy data monitoring group to generate a corresponding abnormal data analysis group if the power quality evaluation coefficient does not accord with the preset power energy monitoring standard;

the abnormal analysis module is used for carrying out abnormal characteristic analysis on the abnormal data analysis group, generating a corresponding abnormal analysis type, and carrying out security level sequencing on the abnormal analysis type according to a preset power operation security standard to form a corresponding abnormal classification sequencing table;

and the second monitoring module is used for generating a corresponding abnormality grading early warning mechanism plan as the electric power energy monitoring result according to the abnormality classification ranking table.

By adopting the technical scheme, the electric power energy data are classified into groups and evaluated and analyzed according to the monitoring classification module and the quality evaluation module, so that the electric power quality problem can be timely and effectively found and the running condition of various electric power energy sources can be predicted, namely, various target electric power energy data in the energy data group in a normal running state are subjected to time sequence analysis through the time sequence feature analysis module to obtain corresponding periodic trend features, the first monitoring module analyzes the corresponding electric power running prediction mode according to the periodic trend features, and the abnormality marking module and the abnormality analysis module analyze and perform grading early warning on the abnormal electric power energy data in the abnormal energy data group, namely, a corresponding abnormality grading early warning mechanism is established through the second monitoring module, various electric power abnormal conditions can be timely responded, the electric power energy system can be effectively regulated and optimized, and the power supply quality and the energy utilization efficiency can be further improved. Because various electric power energy data are divided into groups, the electric power energy data under normal operation are subjected to time sequence analysis to obtain corresponding electric power operation modes, various abnormal energy data monitoring groups are subjected to marking analysis and sequencing, and corresponding grading early warning mechanisms are made, so that the electric power energy monitoring effect is improved.

In a third aspect, the present application provides a terminal device, which adopts the following technical scheme:

the terminal equipment comprises a memory and a processor, wherein the memory stores computer instructions capable of running on the processor, and the processor adopts the electric power energy monitoring method when loading and executing the computer instructions.

By adopting the technical scheme, the computer instruction is generated by the electric power energy monitoring method and is stored in the memory to be loaded and executed by the processor, so that the terminal equipment is manufactured according to the memory and the processor, and the use is convenient.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

a computer readable storage medium having stored therein computer instructions which, when loaded and executed by a processor, employ a method of power energy monitoring as described above.

By adopting the technical scheme, the computer instruction is generated by the electric power energy monitoring method and is stored in the computer readable storage medium to be loaded and executed by the processor, and the computer instruction is convenient to read and store by the computer readable storage medium.

In summary, the present application includes at least one of the following beneficial technical effects: the power energy data are classified into groups and evaluated and analyzed, so that the power quality problem can be effectively found out and the running condition of various power energy sources can be predicted timely, namely, various target power energy source data in the energy data group in a normal running state are subjected to time sequence analysis to obtain corresponding periodic trend characteristics, the corresponding power running prediction mode is analyzed according to the periodic trend characteristics, the abnormal power energy source data in the abnormal energy source data group are analyzed and graded early-warning is carried out, various power abnormal conditions can be timely dealt with, and further, a power energy source system can be effectively regulated and optimized, and the power supply quality and the energy utilization efficiency are further improved. Because various electric power energy data are divided into groups, the electric power energy data under normal operation are subjected to time sequence analysis to obtain corresponding electric power operation modes, various abnormal energy data monitoring groups are subjected to marking analysis and sequencing, and corresponding grading early warning mechanisms are made, so that the electric power energy monitoring effect is improved.

Drawings

Fig. 1 is a schematic flow chart of steps S101 to S107 in the power energy monitoring method of the present application.

Fig. 2 is a schematic flow chart of steps S201 to S204 in the power energy monitoring method of the present application.

Fig. 3 is a schematic flow chart of steps S301 to S304 in the power energy monitoring method of the present application.

Fig. 4 is a schematic flow chart of steps S401 to S403 in the power energy monitoring method of the present application.

Fig. 5 is a schematic flow chart of steps S501 to S503 in the power energy monitoring method of the present application.

Fig. 6 is a schematic flow chart of steps S601 to S602 in the power energy monitoring method of the present application.

Fig. 7 is a schematic flow chart of steps S701 to S702 in the power energy monitoring method of the present application.

Fig. 8 is a schematic block diagram of an electrical energy monitoring system according to the present application.

Reference numerals illustrate:

1. a monitoring classification module; 2. a quality assessment module; 3. a timing sequence feature analysis module; 4. a first monitoring module; 5. an anomaly marking module; 6. an anomaly analysis module; 7. and a second monitoring module.

Detailed Description

The present application is described in further detail below in conjunction with figures 1-8.

The embodiment of the application discloses a power energy monitoring method, as shown in fig. 1, comprising the following steps:

s101, acquiring electric power energy data, and dividing the electric power energy data according to a preset energy data classification monitoring strategy to form a corresponding energy data monitoring group;

S102, carrying out evaluation analysis on the energy data monitoring group according to a preset energy data evaluation index to generate a power quality evaluation coefficient corresponding to the energy data monitoring group;

s103, if the power quality evaluation coefficient meets a preset power energy monitoring standard, carrying out time sequence analysis on target power energy data in the energy data monitoring group, and generating periodic trend characteristics corresponding to the energy data monitoring group;

s104, importing the periodic trend characteristics into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result;

s105, if the power quality evaluation coefficient does not meet the preset power energy monitoring standard, acquiring a corresponding abnormal energy data monitoring group, marking abnormal power energy data in the abnormal energy data monitoring group, and generating a corresponding abnormal data analysis group;

s106, carrying out abnormal feature analysis on the abnormal data analysis group to generate a corresponding abnormal analysis type, and carrying out security level sequencing on the abnormal analysis type according to a preset power operation security standard to form a corresponding abnormal classification sequencing table;

s107, generating a corresponding abnormality grading early warning mechanism plan as a power energy monitoring result according to the abnormality classification ranking table.

In step S101, the electric power energy data is data about the operation state of the electric power system and the power consumption condition, including voltage, current, power, frequency, power consumption, and the like. These data have important reference values for the operation and management of the power system.

The preset energy data classification monitoring strategy is a preset strategy for dividing and managing the electric power energy data according to the actual running requirements and targets of the electric power system. Such strategies typically include the following: the data types are divided into different categories according to the types of the electric power energy data, such as voltage, current, power and the like; the data sources are divided into different categories according to the sources of the electric power energy data, such as a transformer substation, a power distribution station, a user and the like; the time period is divided into different categories according to the time characteristics of the electric power energy data, such as daily electricity consumption, monthly electricity consumption, annual electricity consumption and the like; the regional range is divided into different categories according to the regional characteristics of the electric power energy data, such as urban electricity consumption, rural electricity consumption and the like.

Next, by such division of the electric power energy data, a corresponding energy data monitoring group can be formed. Each monitoring group corresponds to a specific type or characteristic of the electrical energy data, and can be specially monitored and managed. Thus, not only can the monitoring efficiency and accuracy be improved, but also more detailed and specific information can be provided for the operation and management of the power system.

In step S102, the preset energy data evaluation index is a preset standard or rule for evaluating the quality of the electric energy data. It may include several aspects: the data integrity is used for evaluating whether the electric power energy data are complete or not and whether missing or wrong data exist or not; the accuracy of the data is evaluated, and whether the accuracy of the electric power energy data accords with the actual situation is judged; data consistency, evaluating consistency of electric power energy data, and judging whether contradiction or conflict data exist or not; and (3) evaluating the availability of the data, and evaluating whether the availability of the electric power energy data can meet the requirements of actual operation and management.

Next, by performing such evaluation analysis on the energy data monitoring group, a corresponding power quality evaluation coefficient can be generated. The power quality evaluation coefficient reflects the quality level of the energy data monitoring group, and the higher the power quality evaluation coefficient is, the better the data quality is, and the more the power system operation and management requirements can be met. Meanwhile, according to the power quality evaluation coefficient, different energy data monitoring groups can be compared and ordered, so that more valuable information is provided for the operation and management of a power system.

In step S103, the power quality evaluation coefficient is an index for measuring the quality of the power energy data, and if the coefficient meets the preset power energy monitoring standard, it is indicated that the data quality of the energy data monitoring group is better, and the data quality can be used as the basis of analysis.

Secondly, the time sequence analysis is a process of analyzing the time sequence data of the electric power source, and aims to find out characteristics such as trend, periodicity and the like in the data. In the electric power energy data, these characteristics may include a trend of change in the amount of electricity consumed in daily use, seasonal change in the amount of electricity consumed in month, and the like.

Further, the periodic trend feature is a feature in which data repeatedly appears within a certain period of time, and is generally expressed as periodic fluctuations of the data. For example, the amount of electricity used in a day may peak during the morning and evening peak hours, and the amount of electricity used in a week may vary from day to day. The method has the advantages that the use condition of the electric power energy can be better understood and predicted by carrying out time sequence analysis on the target electric power energy data in the energy data monitoring group and generating corresponding periodic trend characteristics, and decision support is provided for the operation and management of the electric power system.

In step S104, the preset regression model is a statistical model for predicting time series data, which can predict data changes in a future period of time based on the trend and the periodic characteristics of the historical data.

The periodic trend features are led into a preset regression model for training, namely the features are used as the input of the model, and the model can be fitted with historical data as much as possible by adjusting parameters of the model, so that an electric power operation prediction mode is generated.

Second, the power operation prediction mode can be used for predicting the power energy use condition in a future period, such as predicting the power consumption of the open day or the next week. The method has important reference value for the operation and management of the power system, can prepare power supply in advance, and avoids production interruption caused by power shortage.

In step S105, the preset electric power source monitoring standard is a series of rules and requirements formulated by the relevant electric power regulatory authorities, aiming at standardizing the monitoring and management of electric power sources. It generally comprises the following aspects: the energy consumption monitoring, namely, the quantitative monitoring of the energy use can be used for knowing the energy consumption conditions of different industries and fields; the power load monitoring, namely, through real-time monitoring and analysis of the power load, the power demand conditions of different time periods and areas can be evaluated, and a power supplier is assisted to make a reasonable power production plan and supply strategy; the system technical requirement, namely, the general technical requirement of the electric power energy efficiency monitoring system is specified, and the system mainly comprises the aspects of an electric power energy efficiency monitoring system technical system, a construction principle, a system structure, basic functions, main technical indexes and the like; and equipment technical specifications, such as technical requirements of functions, performances, interfaces, tests and the like of the electric energy information acquisition terminal.

If the power quality evaluation coefficient does not meet the preset power energy monitoring standard, it is indicated that the data of the energy data monitoring group has problems, and further analysis is needed. And obtaining abnormal energy data monitoring groups corresponding to the power quality evaluation coefficients which do not meet the preset power energy monitoring standard, namely obtaining the energy data monitoring groups with the evaluation coefficients lower than the standard. These data may have problems with missing, erroneous, or inconsistent data, requiring detailed analysis and processing.

Then, these abnormal power energy data are marked to generate a corresponding abnormal data analysis group. An anomaly data analysis group is the result of analyzing and classifying a group of anomaly data, and typically includes various types of anomaly characteristics. These abnormal characteristics may include sudden increases or decreases in electrical load, abnormal fluctuations in voltage or current, equipment failure, etc. By marking and parsing, it is possible to more clearly understand the specifics of such anomalous data, such as which data is problematic, what the nature of the problem is, what the possible reasons are, etc.

In step S106, the abnormal data analysis group is subjected to abnormal feature analysis, i.e., the nature and cause of these abnormal features are further analyzed, and a corresponding abnormal analysis type is generated. For example, if a sudden increase in power load is found, this may be due to overload operation of a certain device; if an abnormal voltage fluctuation is found, it may be caused by instability of the grid.

And secondly, carrying out security level sequencing on the abnormal analysis types according to a preset power operation security standard. The preset power operation safety standard can be formulated by related power supervision authorities, and aims to ensure the safe and stable operation of a power system. Based on this criteria, the severity and possibly the impact of each exception resolution type can be evaluated to determine its security level.

And thirdly, carrying out security level ranking on the current abnormal analysis type according to the preset power operation security standard to form a corresponding abnormal classification ranking table. The abnormal classification ranking table can help operators related to the power system to quickly know the current abnormal power condition, and preferentially process the abnormal types with high safety levels and possibly causing serious influence. Meanwhile, decision support can be provided for operation and management of the power system, and the stability and safety of power supply can be improved.

In step S107, the abnormality classification early warning mechanism planning is a planning for performing classification early warning on different types of abnormalities according to the abnormality classification ranking table. The anomaly hierarchical early warning mechanism plan may include the following: abnormality type definition, in which the definition and characteristics of various abnormality types are clarified according to an abnormality classification ranking table, for example, abnormality for sudden increase of power load may be defined as "overload early warning"; for the abnormality of the voltage abnormality fluctuation, it can be defined as "grid instability early warning"; early warning level division: according to the severity of the abnormal types and the influence possibly caused, each abnormal type is divided into different early warning levels, for example, the overload early warning can be divided into primary early warning, secondary early warning and the like, and the overload conditions of different degrees are respectively corresponding to each other.

Secondly, the planning of the abnormal grading early warning mechanism further comprises the steps of early warning triggering conditions: setting corresponding early warning triggering conditions for each abnormality type, wherein the conditions are generally based on historical data and the result of statistical analysis and are used for judging whether the abnormality is possible to occur currently, for example, triggering overload early warning when the power load exceeds a certain threshold value; early warning notification mode: determining early warning notification modes of each abnormal type, which can comprise various modes such as short messages, telephones, mails and the like, so as to ensure that related personnel can receive early warning information in time; the early warning processing flow comprises the following steps: and formulating an early warning processing flow of each abnormal type, wherein the early warning processing flow comprises the steps of confirming the authenticity of early warning, evaluating the influence degree, taking emergency measures and the like. Through the planning of the abnormal grading early warning mechanism, operators related to the power system can be helped to timely find and process various abnormal conditions, and the stability and safety of power supply are ensured.

According to the electric power energy monitoring method, the electric power energy data are classified into groups and evaluated and analyzed, so that the electric power quality problem can be effectively found out and the running condition of various electric power energy sources can be predicted timely, namely, various target electric power energy source data in the energy data group in a normal running state are subjected to time sequence analysis to obtain corresponding periodic trend characteristics, the corresponding electric power running prediction mode is analyzed according to the periodic trend characteristics, the abnormal electric power energy source data in the abnormal energy source data group are analyzed and graded early-warning is carried out, various electric power abnormal conditions can be timely dealt with, and then an electric power energy source system can be effectively regulated and optimized, and the power supply quality and the energy utilization efficiency are further improved. Because various electric power energy data are divided into groups, the electric power energy data under normal operation are subjected to time sequence analysis to obtain corresponding electric power operation modes, various abnormal energy data monitoring groups are subjected to marking analysis and sequencing, and corresponding grading early warning mechanisms are made, so that the electric power energy monitoring effect is improved.

In one implementation manner of the present embodiment, as shown in fig. 2, step S101 is to acquire electric power energy data, divide the electric power energy data according to a preset energy data classification monitoring policy, and form a corresponding energy data monitoring group, where the steps include:

s201, acquiring associated influence data corresponding to electric power energy data according to a preset energy data classification monitoring strategy;

s202, performing association attribute analysis on the electric power energy data and the association influence data to generate a corresponding association influence mode;

s203, acquiring operation characteristics corresponding to the electric power energy data in the association influence mode, and generating corresponding monitoring classification indexes according to the operation characteristics;

s204, dividing the electric power energy data according to the monitoring classification indexes to form corresponding energy data monitoring groups.

In step S201, the preset energy data classification monitoring policy is a policy for classifying the electric power energy data into different categories for monitoring and management according to the characteristics and purposes of the electric power energy data. These categories may include electrical loads, voltages, currents, frequencies, power factors, and the like.

Next, the associated influence data refers to data having a direct or indirect relationship with the electric power energy data, which may reflect the use condition of the electric power energy, factors affecting the electric power supply, and the like. For example, if the electrical load increases, voltage stabilization may be affected; if the frequency of the power grid fluctuates, normal operation of the device may be affected.

Furthermore, according to the preset energy data classification monitoring strategy, associated influence data corresponding to the electric energy data can be obtained. The use condition of the electric power energy source is more comprehensively known through the related influence data, and the influence of different factors on the electric power supply is evaluated, so that decision support is provided for the operation and management of the electric power system. For example, by analyzing the associated influence data, it can be found which devices or areas have a larger power load and need to be preferentially protected for power supply; or which factors may cause instability in the grid, measures need to be taken for prevention and control.

In step S202, the correlation attribute analysis is to perform statistical analysis on the electric power energy data and the correlation influence data to find the correlation and pattern between them. Specifically, the correlation between the electric power energy data and the correlation influence data can be evaluated by calculating indexes such as correlation coefficients, covariances, and the like between them.

And secondly, according to the result of the correlation analysis, the correlation mode between the electric power energy data and the correlation influence data can be further identified. These modes may be linear, non-linear, time-sequential, spatial, etc. For example, it may be found that there is a negative correlation between the power load and the voltage, i.e. the voltage drops as the load increases; or the fluctuation of the power grid frequency is found to be related to the running state of the equipment, namely the fluctuation of the frequency is large when the equipment is overloaded.

In steps S203 to S204, the operation characteristics of the corresponding electric power energy data in the association influence mode refer to some important indexes or attributes related to the electric power energy data, which may reflect the operation state and performance of the electric power system. For example, as for the electric load data, load size, load type (such as industrial load, residential load, etc.), load variation tendency, etc. may be included; for voltage data, voltage amplitude, voltage fluctuation range, voltage stability, etc. may be included.

And secondly, according to the operation characteristics, corresponding monitoring classification indexes can be generated. These metrics may be used to divide and categorize the electrical energy data for more refined monitoring and management. For example, the power load can be divided into different grades according to the load size, and then corresponding early warning threshold values and processing measures are set for each grade; or dividing the voltage data into different categories according to the voltage stability, and then formulating corresponding monitoring frequencies and analysis methods for each category.

Further, the electric power energy data are divided according to the monitoring classification indexes to form corresponding energy data monitoring groups. The energy data monitoring group can better know the running condition of the power system, discover and process various abnormal conditions in time, and ensure the stability and safety of power supply.

According to the method, the device and the system for monitoring the electric power energy data, the associated attribute analysis is carried out on the electric power energy data and the associated influence data, corresponding monitoring classification indexes are generated according to the operation characteristics of the electric power energy data and the associated influence data, and the electric power energy data can be subjected to classified clustering monitoring according to the various monitoring classification indexes, so that the electric power energy monitoring effect is improved.

In one implementation manner of this embodiment, as shown in fig. 3, in step S204, after obtaining the associated influence data corresponding to the electric power energy data according to the preset energy data classification monitoring policy, the method further includes the following steps:

s301, acquiring a data type of associated influence data;

s302, if the data type is electric power energy data, calibrating corresponding independent variable electric power energy data and dependent variable electric power energy data according to the association relation between the electric power energy data and the associated influence data;

s303, acquiring a corresponding association influence mode between the independent variable power energy data and the dependent variable power energy data, and acquiring a corresponding safety monitoring index according to the association influence mode;

s304, combining the associated influence mode and the safety monitoring index to generate a first electric power energy monitoring strategy corresponding to the electric power energy data.

In steps S301 to S302, the data type identifying the associated influence data is acquired, which can be determined by looking at the specific content and format of the data. For example, if the associated influence data is contact resistance becomes large, its data type is dynamic resistance data.

And if the data type of the associated influence data is the electric power energy data, calibrating the corresponding independent variable electric power energy data and dependent variable electric power energy data according to the association relation between the electric power energy data and the associated influence data. For example, an increase in contact resistance may cause an operational overload of the power system due to an excessive contact resistance, resulting in an increase in the total line resistance, which in turn may result in a decrease in the total line current, such that the power system is operational overload, which may be calibrated to be independent variable power energy data.

In steps S303 to S304, in the power system, the independent variable and the dependent variable are mutually affected. For example, a low supply voltage may cause the load to be too heavy, thereby overloading the power system; excessive contact resistance may lead to a drop in the total line current, which in turn may overload the power system operation. Therefore, in order to improve the monitoring effect of the electric power energy, a corresponding association influence mode between the independent variable electric power energy data and the dependent variable electric power energy data can be obtained, and a corresponding safety monitoring index can be obtained according to the association influence mode.

For example, the independent variable power energy data is voltage, the dependent variable power energy data is current, and the association influence mode between the voltage and the current can be obtained through statistical analysis. For example, voltage and current data may be collected over a period of time and then analyzed for relationships using correlation analysis, regression analysis, and the like. If the analysis shows a strong positive correlation between voltage and current (i.e. when the voltage increases, the current increases accordingly), then it is possible to obtain a voltage that is the main factor affecting the current.

According to the above-mentioned association influence mode, a corresponding safety monitoring index, which is an important parameter for evaluating the safety of the power system, may be further set. For example, a threshold may be set, and when the current exceeds this threshold, the system is considered to be potentially at risk of overload.

Secondly, the step of generating a first electric power energy monitoring strategy by specifically combining the association influence mode and the safety monitoring index is as follows: and according to the set safety monitoring index, monitoring the electric power energy data in real time, comparing the electric power energy data with a threshold value, and if the data exceeds the threshold value, namely, the potential overload risk exists, taking corresponding measures to treat the problem. For example, the overload problem can be solved by adjusting the supply voltage, increasing the capacity of the transmission line, etc. The first power energy monitoring strategy is to monitor and analyze power energy data in real time to find potential problems and risks and take corresponding measures to ensure the stable operation of the power system.

According to the electric power energy monitoring method provided by the embodiment, the independent variable electric power energy data and the dependent variable electric power energy data can be calibrated according to the association relation between the electric power energy data and the associated influence data. Therefore, the relation between the electric power energy data and the associated influence data can be better understood, a more accurate electric power energy monitoring strategy is generated, the electric power energy monitoring effect can be improved, and the stability and safety of the electric power energy are ensured.

In one implementation manner of this embodiment, as shown in fig. 4, after step S301, that is, after acquiring the data type of the association influence data, the following steps are further included:

s401, if the data type is non-electric power energy data, acquiring associated influence characteristics of the associated influence data relative to the electric power energy data;

s402, if the associated influence features are multiple, establishing a multi-source associated influence model corresponding to the electric power energy data according to each associated influence feature, and outputting a corresponding abnormal trend prediction instruction;

s403, according to the abnormal trend prediction indication, formulating an abnormal monitoring index corresponding to the electric power energy data as a second electric power energy monitoring strategy.

In step S401, the associated influence feature refers to a mutual influence relationship between the non-electric power energy data and the electric power energy data. For example, if an increase in the price of non-electrical energy causes an increase in the demand for electrical power, thereby overloading the operation of the electrical power system, the price of non-electrical energy can be said to be an associated influencing feature that influences the operation of the electrical power system.

Wherein statistical analysis, machine learning, etc. methods may be used to analyze the relationship between the non-electrical energy data and the electrical energy data. For example, a correlation analysis may be used to determine a degree of correlation between a non-electrical energy price and an electrical system operating load; regression analysis may also be used to build a mathematical model between non-electric energy prices and electric system operating loads.

And secondly, extracting the relevant influence characteristics of the non-electric power energy data relative to the electric power energy data according to the data analysis result. For example, if the analysis result shows that there is a strong positive correlation between the non-electric energy price and the electric power system operation load, then the "non-electric energy price increase will cause the electric power system operation load to increase" is a correlation influencing feature.

Furthermore, if the non-electric power energy data is weather environment data affecting the electric power energy data, the relevant affecting feature of the weather environment data relative to the electric power energy data may be extracted according to the result of the regression data analysis. For example, if the analysis results show that high temperature weather may cause an increase in the operating load of the power system, then it is an associated influencing feature that "high temperature weather may cause an increase in the operating load of the power system" is available.

In steps S402 to S403, if the associated influence features are plural, a multi-source associated influence model may be built to describe the influence of these features on the electrical energy data. The multi-source correlation influence model can be a statistical model, a machine learning model or a deep learning model, and the specific selection of which model depends on the characteristics of the data and the purpose of the study.

The method for establishing the multi-source association influence model comprises the following steps of: firstly, extracting characteristic variables related to electric power energy data according to a plurality of associated influence characteristics, wherein the characteristic variables can be original data or new characteristic variables obtained through certain conversion or combination; and then using the collected data as a training set to train the multi-source association influence model, wherein in the training process, the performance of the model can be evaluated by using methods such as cross-validation and the like, and proper model parameters are selected.

And secondly, predicting new electric power energy data by using the trained multi-source association influence model. By comparing the difference between the predicted result and the actual observed value, an abnormal trend prediction indication can be obtained. For example, if the prediction results show that there will be a substantial increase in power demand in a region where the power supply capacity is limited, then an abnormal trend prediction indication of the potential overload risk may be considered.

Further, according to the abnormal trend prediction indication, a corresponding abnormal monitoring index is formulated as a second electric power energy monitoring strategy. These indicators may be thresholds or guard lines regarding the power system operating load, voltage, current, etc. When the actual observed values exceed the thresholds, abnormal conditions are considered to exist, and corresponding measures are needed to be taken for processing.

According to the electric power energy monitoring method provided by the embodiment, a multi-source association influence model corresponding to electric power energy data is established according to each association influence characteristic. The model can consider a plurality of influence factors at the same time, so that the change condition of the electric power energy source can be more comprehensively and deeply understood, and the monitoring efficiency is improved.

In one implementation manner of the present embodiment, as shown in fig. 5, step S104 of introducing the periodic trend feature into a preset regression model for training, and generating the power operation prediction mode corresponding to the energy data monitoring group as the power energy monitoring result includes the following steps:

s501, importing periodic trend characteristics into a preset regression model for training, and generating corresponding power energy prediction values;

s502, acquiring a numerical value difference between an electric power energy predicted value and an electric power energy observed value corresponding to electric power energy data, and judging whether the numerical value difference is in a preset difference threshold value interval;

S503, if the numerical value difference is in a preset difference threshold value interval, extracting power operation related features corresponding to the power energy prediction value, and generating a power operation prediction mode corresponding to the energy data monitoring group according to the power operation related features to serve as a power energy monitoring result.

In step S501, according to the purpose of the study and the actual situation, the periodic trend characteristics in the electric power energy data to be analyzed are determined. For example, features such as seasonal and weekly periodicity in the time series data may be considered. Then, according to the periodic trend characteristics, a proper regression model is selected for training, wherein the regression model comprises linear regression, polynomial regression, ARIMA (autoregressive moving average) model and the like. Which model is selected depends on the nature of the data and the purpose of the study.

Secondly, training a preset regression model by using the preprocessed electric power energy data as a training set. During training, cross-validation or the like may be used to evaluate the performance of the model and select appropriate model parameters. And then generating a corresponding electric power energy prediction value, namely predicting new electric power energy data by using a trained preset regression model. By inputting corresponding periodic trend characteristics, a corresponding electric power energy prediction value can be obtained. These predictions may be used in future power demand planning, resource allocation, etc.

In steps S502 to S503, the electric power energy prediction value is compared with the electric power energy observation value corresponding to the electric power energy data, and the numerical difference between the two is calculated. The magnitude of the numerical difference may be measured using an absolute error, a relative error, or the like. Judging whether the calculated numerical value difference is in a preset difference threshold value interval or not, and if so, considering that the predicted result is relatively close to the actual observed value; otherwise, the predicted result is considered to have larger deviation from the actual observed value. The preset difference threshold interval is a statistical concept and is mainly used for measuring the error range between the electric power energy predicted value and the corresponding sample statistical value of the electric power energy observed value and the overall parameter.

And secondly, if the numerical value difference is in a preset difference threshold value interval, the prediction result is proved to have certain reliability. At this time, the electric power operation related characteristics such as the load variation trend, peak-to-valley period distribution, and the like, which correspond to the electric power energy prediction value, may be extracted. These features help to better understand the operation of the power system.

Further, according to the extracted power operation related characteristics, a power operation prediction mode corresponding to the energy data monitoring group is generated. This mode can be used in future power demand planning, resource allocation, etc. For example, future electricity demand can be predicted according to the load change trend, so that corresponding preparations are made in advance.

According to the electric power energy monitoring method, the electric power operation prediction mode can be updated in real time to reflect the latest change condition of the electric power energy, so that abnormal conditions of the electric power energy can be found in time, the internal rule and trend of the electric power energy are further predicted, and the monitoring effect of the electric power energy is improved.

In one implementation manner of the embodiment, as shown in fig. 6, step S106 is to perform anomaly characteristic analysis on the anomaly data analysis group to generate a corresponding anomaly analysis type, and perform security level ranking on the anomaly analysis type according to a preset power operation security standard, so as to form a corresponding anomaly classification ranking table, where the steps include:

s601, if the number of the abnormal analysis types is multiple, obtaining abnormal attributes corresponding to the abnormal analysis types, and setting an abnormal label corresponding to the abnormal analysis type according to the abnormal attributes;

s602, classifying the plurality of abnormal analysis types according to the abnormal labels, generating corresponding abnormal feature sets, and constructing a corresponding abnormal power energy source mode library according to the abnormal feature sets.

In step S601 to step S602, if the current exception resolution type is plural, a corresponding exception attribute may be extracted for each exception resolution type. These properties may be numerical characteristics such as voltage, current, power, etc.; but may also be a generic type of feature such as fault type, status of the device, etc. And setting corresponding exception labels for each exception analysis type according to the extracted exception attributes. These labels may better understand the nature and source of the anomalies.

And classifying different abnormality analysis types according to the set abnormality labels. For example, voltage anomalies may be categorized into different types of overvoltage, undervoltage, etc.; the abnormal current is classified into overcurrent, undercurrent and other types. And then generating a corresponding abnormal characteristic set according to the classified abnormal analysis type. These feature sets may include information about the time, duration, frequency, etc. that the anomaly occurred, as well as other features associated with the anomaly.

Further, according to the obtained abnormal characteristic set, a corresponding abnormal electric power energy source mode library is constructed. The library can be used for future power demand planning, resource allocation and the like, and helps to predict and cope with possible abnormal situations.

According to the electric power energy monitoring method, various abnormal analysis types are subjected to feature analysis, so that the abnormal conditions of the electric power energy can be more accurately identified, a corresponding abnormal electric power energy mode library is further classified and constructed, the abnormal conditions and the processing method of the electric power energy can be accumulated and summarized, the monitoring effect of the electric power energy is improved, and the electric power energy operation risk is reduced.

In one implementation manner of the present embodiment, as shown in fig. 7, in step S601, if the number of the exception analysis types is plural, the method further includes the following steps of:

S701, if abnormal correlation exists among the abnormal analysis types, acquiring a corresponding target abnormal analysis type, and generating a corresponding abnormal correlation group according to the target abnormal analysis type;

s702, establishing a corresponding abnormal superposition prediction model according to an abnormal association instruction corresponding to the abnormal association group, and outputting a power energy abnormality prediction result corresponding to the abnormal association group.

In steps S701 to S702, it is determined whether or not there is a correlation with the other abnormality analysis type for each abnormality analysis type. If there is an association, it is taken as the target exception resolution type. The exception resolution types with the same association features are then combined into an exception association group.

For example, when a voltage abnormality occurs, it is often accompanied by the occurrence of a current abnormality. Therefore, it is possible to take the voltage abnormality as the target abnormality analysis type and combine the current abnormality related to the voltage abnormality into one abnormality related group.

And secondly, establishing corresponding abnormal association indication according to the characteristics of the abnormal association group. These indications may indicate the likelihood and severity of the occurrence of the anomaly. Then, according to the established abnormality association indication, a corresponding abnormality superposition prediction model is established, and the model can be used for predicting possible abnormal conditions in the future and giving corresponding early warning information. The abnormal superposition prediction model is a fitting method based on time sequence decomposition and machine learning, and is used for predicting possible abnormal conditions in the future and giving corresponding early warning information. And predicting the electric power energy data according to the established abnormal superposition prediction model, and outputting a corresponding abnormal prediction result.

In practical application, prophet is a data prediction tool based on Python and R language of Facebook open source, which can predict according to time sequence decomposition combined with variable values and fitting of machine learning, and can also be used for abnormal value detection and missing value filling of time sequence data. For example, when Prophet is used to predict voltage anomalies in a power system, historical voltage data is first required as input, then the model is learned and fitted from this data, and finally a predictive model is generated. When future voltage data is predicted using this model, if the prediction results show that the future voltage value is outside the normal range, then the outside range value may be considered an outlier requiring further analysis and processing.

Moreover, the abnormal superposition prediction model can perform abnormal superposition on the abnormal correlation indication conditions corresponding to the abnormal correlation group one by one, so as to analyze and predict the power operation conditions corresponding to the power energy system under various abnormal conditions.

According to the electric power energy monitoring method provided by the embodiment, the corresponding abnormality association group is generated according to the target abnormality analysis type, the corresponding abnormality superposition prediction model is further established, and the influence of a plurality of abnormality analysis types can be simultaneously considered through the abnormality superposition prediction model, so that the change condition of the electric power energy is more comprehensively and deeply understood, and the monitoring efficiency is improved.

The embodiment of the application discloses an electric power energy monitoring system, as shown in fig. 8, includes:

the monitoring classification module 1 is used for acquiring electric power energy data, and dividing the electric power energy data according to a preset energy data classification monitoring strategy to form a corresponding energy data monitoring group;

the quality evaluation module 2 is used for performing evaluation analysis on the energy data monitoring group according to a preset energy data evaluation index to generate a power quality evaluation coefficient corresponding to the energy data monitoring group;

the time sequence feature analysis module 3 is used for performing time sequence analysis on target electric power energy data in the energy data monitoring group and generating periodic trend features corresponding to the energy data monitoring group if the electric power quality evaluation coefficient accords with a preset electric power energy monitoring standard;

the first monitoring module 4 is used for guiding the periodic trend characteristics into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result;

the abnormal marking module 5 is used for acquiring a corresponding abnormal energy data monitoring group and marking the abnormal power energy data in the abnormal energy data monitoring group to generate a corresponding abnormal data analysis group if the power quality evaluation coefficient does not accord with the preset power energy monitoring standard;

The anomaly analysis module 6 is used for carrying out anomaly characteristic analysis on the anomaly data analysis group, generating a corresponding anomaly analysis type, and carrying out security level sequencing on the anomaly analysis type according to a preset power operation security standard to form a corresponding anomaly classification sequencing table;

and the second monitoring module 7 is used for generating a corresponding abnormality grading early warning mechanism plan as an electric power energy monitoring result according to the abnormality classification ranking table.

By adopting the technical scheme, the electric power energy data are classified into groups and evaluated and analyzed according to the monitoring classification module 1 and the quality evaluation module 2, so that the electric power quality problem can be timely and effectively found and the running condition of various electric power energy sources can be predicted, namely, various target electric power energy source data in the energy data group in a normal running state can be timely analyzed through the time sequence feature analysis module 3 to obtain corresponding periodic trend features, the corresponding electric power running prediction mode can be analyzed through the first monitoring module 4 according to the periodic trend features, and the abnormal electric power energy source data in the abnormal energy source data group can be analyzed and graded early-warned through the abnormal marking module 5 and the abnormal analysis module 6, namely, the corresponding abnormal grading early-warning mechanism planning can be established through the second monitoring module 7, various electric power abnormal conditions can be timely dealt with, the electric power energy system can be effectively regulated and optimized, and the power supply quality and the energy source utilization efficiency can be further improved. Because various electric power energy data are divided into groups, the electric power energy data under normal operation are subjected to time sequence analysis to obtain corresponding electric power operation modes, various abnormal energy data monitoring groups are subjected to marking analysis and sequencing, and corresponding grading early warning mechanisms are made, so that the electric power energy monitoring effect is improved.

It should be noted that, the electric power energy monitoring system provided in the embodiment of the present application further includes each module and/or the corresponding sub-module corresponding to the logic function or the logic step of any one of the above-mentioned electric power energy monitoring methods, so that the same effects as each logic function or logic step are achieved, and detailed descriptions thereof are omitted herein.

The embodiment of the application also discloses a terminal device, which comprises a memory, a processor and computer instructions stored in the memory and capable of running on the processor, wherein when the processor executes the computer instructions, any one of the electric power energy monitoring methods in the embodiment is adopted.

The terminal device may be a computer device such as a desktop computer, a notebook computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory, for example, the terminal device may further include an input/output device, a network access device, a bus, and the like.

The processor may be a Central Processing Unit (CPU), or of course, according to actual use, other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), ready-made programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and the general purpose processor may be a microprocessor or any conventional processor, etc., which is not limited in this application.

The memory may be an internal storage unit of the terminal device, for example, a hard disk or a memory of the terminal device, or may be an external storage device of the terminal device, for example, a plug-in hard disk, a Smart Memory Card (SMC), a secure digital card (SD), or a flash memory card (FC) provided on the terminal device, or the like, and may be a combination of the internal storage unit of the terminal device and the external storage device, where the memory is used to store computer instructions and other instructions and data required by the terminal device, and the memory may be used to temporarily store data that has been output or is to be output, which is not limited in this application.

Any one of the electric power energy monitoring methods in the embodiments is stored in the memory of the terminal device through the terminal device, and is loaded and executed on the processor of the terminal device, so that the terminal device is convenient to use.

The embodiment of the application also discloses a computer readable storage medium, and the computer readable storage medium stores computer instructions, wherein when the computer instructions are executed by a processor, any one of the electric power energy monitoring methods in the embodiment is adopted.

The computer instructions may be stored in a computer readable medium, where the computer instructions include computer instruction codes, where the computer instruction codes may be in a source code form, an object code form, an executable file form, or some middleware form, etc., and the computer readable medium includes any entity or device capable of carrying the computer instruction codes, a recording medium, a usb disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, etc., where the computer readable medium includes but is not limited to the above components.

Any one of the electric power energy monitoring methods in the above embodiments is stored in the computer readable storage medium through the present computer readable storage medium, and is loaded and executed on a processor, so as to facilitate the storage and application of the method.

The foregoing are all preferred embodiments of the present application, and are not intended to limit the scope of the present application in any way, therefore: all equivalent changes in structure, shape and principle of this application should be covered in the protection scope of this application.

Claims

1. The electric power energy monitoring method is characterized by comprising the following steps of:

2. The method for monitoring electric power energy according to claim 1, wherein the steps of obtaining electric power energy data, dividing the electric power energy data according to a preset energy data classification monitoring policy, and forming a corresponding energy data monitoring group include the following steps:

3. The method for monitoring electric power energy according to claim 2, further comprising the steps of, after obtaining the associated influence data corresponding to the electric power energy data according to the preset energy data classification monitoring policy:

acquiring the data type of the associated influence data;

4. A method of monitoring electrical energy according to claim 3, further comprising the steps of, after obtaining the data type of the associated impact data:

5. The method for monitoring electric power energy according to claim 1, wherein the step of introducing the periodic trend feature into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result comprises the steps of:

6. The method for monitoring electric power energy according to claim 1, wherein the step of performing an anomaly characteristic analysis on the anomaly data analysis group to generate a corresponding anomaly analysis type, and performing a security level ranking on the anomaly analysis type according to a preset electric power operation security standard to form a corresponding anomaly classification ranking table comprises the steps of:

7. The method according to claim 6, wherein if the number of the abnormality analysis types is plural, obtaining the abnormality attribute corresponding to each abnormality analysis type, and setting the abnormality label corresponding to the abnormality analysis type according to the abnormality attribute, further comprising the steps of:

8. An electrical energy monitoring system, comprising:

the monitoring classification module (1) is used for acquiring electric power energy data, and dividing the electric power energy data according to a preset energy data classification monitoring strategy to form a corresponding energy data monitoring group;

the quality evaluation module (2) is used for performing evaluation analysis on the energy data monitoring group according to a preset energy data evaluation index to generate an electric power quality evaluation coefficient corresponding to the energy data monitoring group;

the time sequence feature analysis module (3) is used for carrying out time sequence analysis on target electric power energy data in the energy data monitoring group and generating periodic trend features corresponding to the energy data monitoring group if the electric power quality evaluation coefficient accords with a preset electric power energy monitoring standard;

the first monitoring module (4) is used for guiding the periodic trend characteristics into a preset regression model for training, and generating an electric power operation prediction mode corresponding to the energy data monitoring group as an electric power energy monitoring result;

The abnormal marking module (5) is used for acquiring a corresponding abnormal energy data monitoring group and marking the abnormal power energy data in the abnormal energy data monitoring group to generate a corresponding abnormal data analysis group if the power quality evaluation coefficient does not accord with the preset power energy monitoring standard;

the abnormal analysis module (6) is used for carrying out abnormal characteristic analysis on the abnormal data analysis group, generating a corresponding abnormal analysis type, and carrying out security level sequencing on the abnormal analysis type according to a preset power operation security standard to form a corresponding abnormal classification sequencing table;

and the second monitoring module (7) is used for generating a corresponding abnormality grading early warning mechanism plan as the electric power energy monitoring result according to the abnormality classification ranking table.

9. A terminal device comprising a memory and a processor, wherein the memory has stored therein computer instructions executable on the processor, the processor employing a method of power energy monitoring as claimed in any one of claims 1 to 7 when the computer instructions are loaded and executed by the processor.

10. A computer readable storage medium having stored therein computer instructions which, when loaded and executed by a processor, employ a method of monitoring electrical energy according to any one of claims 1 to 7.