CN112257923B - Heavy overload warning method, device and electronic equipment - Google Patents

Abstract

In the heavy overload early warning method provided in the embodiment of the present application, since the heavy overload early warning model is based on weights corresponding to multiple electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of the first set The joint influence degree corresponding to the set, the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors, and the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set After screening, the multiple electric quantity influencing factor vectors in the third data feature set obtained after screening are all electric quantity influencing factor vectors that have a greater influence on the heavy overload in the first area, so the first electric quantity influencing factor vector obtained based on the third data feature set The prediction result of heavy overload in one area is more accurate, so as to realize the early warning of heavy overload in the station area.

Description

Heavy overload warning method, device and electronic equipment

technical field

This application relates to the field of power distribution systems, and more specifically, relates to a heavy overload early warning method, device and electronic equipment.

Background technique

In the power system, a station area refers to the power supply area of a power supply equipment. A station area includes multiple loads and power supply equipment that supplies power to multiple loads. The operating status of the power supply equipment directly affects the power supply quality of the station area to multiple loads. . Heavy-load operation or overload operation of power supply equipment is one of the main reasons for power outages in station areas, which not only affects the safety of power consumption, but also accelerates the loss of power supply equipment and reduces the service life of power supply equipment.

At present, the processing of heavy-load operation or overload operation in the station area is still in the post-processing stage, that is, data collection and analysis are carried out on the station area where the heavy-load operation or overload operation has occurred, and it is determined that the heavy-load operation or overload operation has occurred in the station area Due to the reasons, it is impossible to realize the early warning of heavy overload in the station area.

Contents of the invention

In view of this, the present application provides a heavy overload early warning method, device and electronic equipment, so as to realize the heavy overload early warning for the station area.

This application provides the following technical solutions:

A heavy overload early warning method, comprising:

Obtain the first data feature set corresponding to the first time period of the first area, and the second data feature set corresponding to the second time period, the first time period is earlier than the current time, and the current time is the end time time period, the second time period is a time period later than the current time and starting from the current time, and both the first data feature set and the second data feature set include multiple A vector of power influencing factors;

Acquiring weights corresponding to multiple electric quantity influencing factor vectors;

determining a plurality of first attributes respectively corresponding to the electric quantity influencing factor vectors to obtain a plurality of first attributes, the first attributes representing attribute information corresponding to the electric quantity influencing factor vectors;

Obtain at least one set of correlation coefficients corresponding to a first set, the first set includes any two different first attributes among the plurality of first attributes, and the two first attributes included in different first sets are incomplete same;

Obtaining at least one set of joint influence degrees corresponding to the first set, where one joint influence degree corresponding to the first set indicates that when two different first attributes contained in the first set act on the first area at the same time, a change in the power output of the power supply equipment that supplies power to each load located in the first area;

Obtaining first probability distributions respectively corresponding to the plurality of electric quantity influencing factor vectors for the plurality of electric quantity influencing factor vectors belonging to the same first attribute;

The weights corresponding to the multiple electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influencing factor vectors respectively The corresponding first probability distribution, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model;

Obtaining a first prediction result output by the heavy overload early warning model, the first prediction result including the operating state of the power supply equipment within the second time period, the operating state including normal operation and/or overload operation and/or or run with heavy load;

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

Preferably, if the operation status includes overload operation, the first prediction result further includes a time period when the power supply equipment is in overload operation;

And/or, if the operating state includes heavy-load operation, the first prediction result further includes that the power supply equipment is in a period of heavy-load operation;

And/or, if the operation status includes normal operation, the first prediction result further includes a time period during which the power supply equipment is in normal operation.

Preferably, if the operation status includes overload operation, the first prediction result further includes a first probability that the power supply equipment is in overload operation;

And/or, if the operating state includes heavy-load operation, the first prediction result further includes a second probability that the power supply equipment is in heavy-load operation;

And/or, if the operation status includes normal operation, the first prediction result further includes a third probability that the power supply equipment is in normal operation.

Preferably, it also includes:

If the first probability is greater than or equal to the first threshold, set the icon representing the first region in the running state signature map as the first mark, the running state mark map includes marks corresponding to at least one region respectively, the at least one region includes said first region;

If the first probability is greater than or equal to a second threshold and less than the first threshold, setting the icon representing the first region in the running state marker map as a second identifier;

If the first probability is less than the second threshold, the icon representing the first area in the running status marker map is set as a third identifier.

Preferably, said obtaining the first data feature set corresponding to the first time period in the first area, and the second data feature set corresponding to the second time period include:

Obtain weather information and time information corresponding to each day in the first time period in the first area, the weather information corresponding to a day includes: at least one of the temperature of the day, the air pressure of the day, humidity and precipitation The time information corresponding to a day includes: at least one of the date the day belongs to, the month the day belongs to, the week corresponding to the day, whether the day is a holiday, and the season the day belongs to;

Obtain the number of loads corresponding to each day of at least one load type and the power consumption ratio corresponding to each day of the at least one load type within the first time period, and the loads belonging to the at least one load type are all located in the first time period. an area;

Obtaining the operating parameters of the power supply equipment corresponding to each day in the first time period, the operating parameters corresponding to a day include the number of overloads, the number of heavy loads, the duration of overloading, the duration of heavy loads, the average load rate, and the maximum load rate at least one of;

The temperature, humidity, air pressure, precipitation, date, month, week, holiday, season corresponding to each day in the first time period, the number of loads corresponding to each day of the at least one load type, and the at least one load type The proportion of power consumption corresponding to each day of the type, the number of overloads, the number of overloads, the duration of overloading, the duration of overloading, the average load rate, and the maximum load rate of the power supply equipment corresponding to each day are respectively included in the first data feature set A vector of electric power influencing factors to obtain the first data feature set;

Acquiring weather information and date information respectively corresponding to each day in the second time period in the first area;

Using the temperature, humidity, air pressure, precipitation, date, month, week, holiday, and season corresponding to each day in the second time period as the electric quantity influencing factor vector in the second data feature set, to obtain The second data feature set.

Preferably, it also includes:

Obtain multiple historical data feature sets corresponding to the first area, one historical data feature set includes the sixth data feature set corresponding to the third time period of the first area, and the fourth data feature set corresponding to the fourth time period , the third time period is a time period that is earlier than the preset historical time and takes the preset historical time as the end time, the earliest time of the fourth time period is later than the historical time, and the latest time is earlier than The current time, the sixth data feature set and the fourth data feature set each include a plurality of sample power influencing factor vectors;

Perform the following operations for each set of historical data features:

Acquiring weights corresponding to multiple vectors of the sample electric quantity influencing factors;

Determining a plurality of second attributes corresponding to the sample electric quantity influencing factor vectors respectively to obtain a plurality of second attributes, the second attributes representing attribute information corresponding to the sample electric quantity influencing factor vectors;

Obtain at least one set of correlation coefficients corresponding to a second set, the second set includes any two different second attributes among the plurality of second attributes, and the two second attributes contained in different second sets are incomplete same;

Obtaining at least one set of joint influence degrees corresponding to the second set, and one joint influence degree corresponding to the first set indicates that when two different second attributes contained in the first set act on the first area at the same time, a change in the power output of the power supply equipment that supplies power to each load located in the first area;

Obtaining second probability distributions respectively corresponding to the plurality of electric quantity influencing factor vectors for the plurality of electric quantity influencing factor vectors belonging to the same first attribute;

The weights corresponding to the multiple sample electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the second set, the joint influence degree corresponding to at least one set of the second set, and the multiple electric quantity influencing factor vectors The corresponding second probability distribution and the feature set of historical data are input to the machine learning model;

Obtaining a second prediction result corresponding to the historical data feature set output by the machine learning model, so as to obtain a plurality of second prediction results respectively corresponding to the historical data feature set, one of the second prediction results includes a fourth time The operation state of the power supply equipment mentioned in the paragraph, the operation state includes normal operation and/or overload operation and/or heavy load operation;

The second prediction result is the machine learning model based on the weights corresponding to the multiple sample electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the second set, at least one set of correlation coefficients corresponding to the second set Combine the degree of influence and the second probability distributions respectively corresponding to the plurality of power influence factor vectors, filter the historical data feature set to obtain the fifth data feature set, and output the fourth data feature set based on the fifth data feature set A prediction result of the operating state of the power supply equipment within the time period.

For each of the second prediction results, compare the second prediction results with the actual operating status of the power supply equipment in the corresponding fourth time period, and obtain a comparison result, so as to obtain a plurality of the second prediction results respectively the corresponding comparison result;

The machine learning model is trained based on multiple comparison results to obtain the heavy overload warning model.

preferred,

If the operation state in the second prediction result is overload operation, the second prediction result also includes the first prediction time period during which the power supply equipment is in overload operation; the actual operation state also includes the power supply equipment During the first real time period of overload operation during the fourth time period;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

comparing the first predicted time period with the first real time period to obtain the comparison result;

and / or,

If the operation state in the second prediction result is heavy-load operation, the second prediction result also includes a second prediction time period during which the power supply equipment is in heavy-load operation; the actual operation state also includes the The power supply equipment is in the second real time period of heavy load operation during the fourth time period;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

comparing the second predicted time period with the second actual time period to obtain the comparison result;

and / or,

If the operation state in the second prediction result is normal operation, the second prediction result also includes a third prediction time period during which the power supply equipment is in normal operation; the actual operation state also includes the power supply equipment a third real time period during normal operation during said fourth time period;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

and comparing the third predicted time period with the third real time period to obtain the comparison result.

Preferably, if the operation state in the second prediction result is overload operation, the second prediction result further includes the first prediction probability that the power supply equipment is in overload operation, and the actual operation state includes the power supply a first true probability that the device is operating at overload during the fourth time period;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

comparing the first predicted probability with the first true probability to obtain the comparison result;

and / or,

If the operation state in the second prediction result is heavy-load operation, the second prediction result further includes a second prediction probability that the power supply equipment is in heavy-load operation, and the actual operation state includes the power supply equipment a second true probability of being in heavy duty operation during said fourth time period;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

comparing the second predicted probability with the second actual probability to obtain the comparison result;

and / or,

If the operation state in the second prediction result is normal operation, the second prediction result further includes a third prediction probability that the power supply equipment is in normal operation, and the actual operation state includes that the power supply equipment is in normal operation. The third true probability of being in heavy duty operation for the fourth period of time;

The comparing the second predicted result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result includes:

and comparing the third predicted probability with the third actual probability to obtain the comparison result.

A heavy overload early warning device, comprising:

The first acquisition module is configured to acquire the first data feature set corresponding to the first time period in the first area, and the second data feature set corresponding to the second time period;

Wherein, the first time period is earlier than the current time and takes the current time as the end time, and the second time period is later than the current time and starts with the current time For a period of time, both the first data feature set and the second data feature set include a plurality of electric quantity influencing factor vectors;

The second obtaining module is used to obtain weights respectively corresponding to multiple electric quantity influencing factor vectors;

The first determining module is configured to determine a plurality of first attributes respectively corresponding to the electric quantity influencing factor vectors, so as to obtain a plurality of first attributes, and the first attributes represent the attribute information corresponding to the electric quantity influencing factor vectors;

The third acquisition module is used to acquire at least one set of correlation coefficients corresponding to the first set, the first set includes any two different first attributes among the plurality of first attributes, and the different first attributes included in the first set The two first attributes are not exactly the same;

The fourth acquisition module is configured to acquire at least one set of joint influence degrees corresponding to the first set, and one joint influence degree corresponding to the first set indicates that two different first attributes included in the first set act on the In the first area, the power output of the power supply equipment that supplies power to each load located in the first area changes;

The fifth acquisition module is configured to acquire the first probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors for the multiple electric quantity influencing factor vectors belonging to the same first attribute;

The first input module is configured to use the weights corresponding to the plurality of power influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and multiple The first probability distribution, the first data feature set, and the second data feature set respectively corresponding to the power influence factor vectors are input to a pre-built heavy overload early warning model;

A sixth obtaining module, configured to obtain a first prediction result output by the heavy overload early warning model, the first prediction result includes the operating state of the power supply equipment within the first time period, and the operating state includes normal operation and/or overload operation and/or heavy duty operation;

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

An electronic device comprising:

memory for storing programs;

a processor, configured to execute the program, and the program is specifically used for:

Obtain the first data feature set corresponding to the first time period of the first area, and the second data feature set corresponding to the second time period, the first time period is earlier than the current time, and the current time is the end time time period, the second time period is a time period later than the current time and starting from the current time, and both the first data feature set and the second data feature set include multiple A vector of power influencing factors;

Acquiring weights corresponding to multiple electric quantity influencing factor vectors;

determining a plurality of first attributes respectively corresponding to the electric quantity influencing factor vectors to obtain a plurality of first attributes, the first attributes representing attribute information corresponding to the electric quantity influencing factor vectors;

Obtain at least one set of correlation coefficients corresponding to a first set, the first set includes any two different first attributes among the plurality of first attributes, and the two first attributes included in different first sets are incomplete same;

Obtaining at least one set of joint influence degrees corresponding to the first set, where one joint influence degree corresponding to the first set indicates that when two different first attributes contained in the first set act on the first area at the same time, a change in the power output of the power supply equipment that supplies power to each load located in the first area;

Obtaining first probability distributions respectively corresponding to the plurality of electric quantity influencing factor vectors for the plurality of electric quantity influencing factor vectors belonging to the same first attribute;

The weights corresponding to the multiple electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influencing factor vectors respectively The corresponding first probability distribution, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model;

Obtaining a first prediction result output by the heavy overload early warning model, the first prediction result including the operating state of the power supply equipment within the second time period, the operating state including normal operation and/or overload operation and/or or run with heavy load;

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

It can be seen from the above technical solutions that in the heavy overload warning method, device and electronic equipment provided by the present application, the first data feature set corresponding to the first time period in the first area and the second data feature set corresponding to the second time period are acquired , wherein the first time period is the historical time period, the second time period is the time period to be predicted, and both the first data feature set and the second data feature set include a plurality of electric quantity influencing factor vectors. Each electric quantity influencing factor vector is analyzed to determine the weight corresponding to each electric quantity influencing factor vector, and the weight characterizes the degree of influence of the electric quantity influencing factor vector on the heavy overload of the first area. Determine first attributes respectively corresponding to the plurality of electric quantity influencing factor vectors, where the first attributes represent attribute information corresponding to the electric quantity influencing factor vectors. Obtain the correlation coefficient between two different first attributes. If the correlation coefficient is greater than the preset threshold, it is considered that there is a linear correlation between the two first attributes, that is, the power influencing factor vector in one of the first attributes can be used to replace the other. A vector of power impact factors in the first attribute. Obtain the joint influence degree corresponding to any two first attributes, where the joint influence degree represents the change in the power output of the power supply equipment that supplies power to each load located in the first area when two different first attributes act on the first area at the same time . In practical applications, it may appear that the weights corresponding to the two power influence factor vectors are relatively small, but because the two belong to different first attributes, the joint influence of the two on the heavy overload of the first area is relatively large, so When screening, it is necessary to consider the joint influence of different first attributes on heavy overload. For the multiple electric quantity influencing factor vectors belonging to the same first attribute, the first probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors are acquired, and the probability distribution of one electric quantity influencing factor vector characterizes the discreteness of the electric quantity influencing factor vector If the vector of the electric quantity influencing factor is too concentrated in a certain threshold range, it means that the vector of the electric quantity influencing factor changes little, and the reference significance for predicting heavy overload in the first area is small.

The weights corresponding to the multiple electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influencing factor vectors respectively The corresponding first probability distribution, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model to obtain the output of the heavy overload early warning model for the power supply equipment at the first The first prediction result of the running status in the second time period.

In the heavy overload early warning method provided in the embodiment of the present application, since the heavy overload early warning model is based on weights corresponding to multiple electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of the first set The joint influence degree corresponding to the set, the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors, and the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set After screening, the multiple electric quantity influencing factor vectors in the third data feature set obtained after screening are all electric quantity influencing factor vectors that have a greater influence on the heavy overload in the first area, so the first electric quantity influencing factor vector obtained based on the third data feature set The prediction result of heavy overload in one area is more accurate, so as to realize the early warning of heavy overload in the station area.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present application, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

FIG. 1 is a schematic flow diagram of a heavy overload early warning method provided in an embodiment of the present application;

FIG. 2 is a flow chart of an implementation of a first data feature set and a second data feature set provided in an embodiment of the present application;

Fig. 3 is a flow chart of the construction process of a heavy overload early warning model provided by the embodiment of the present application;

FIG. 4 is a structural diagram of a heavy overload early warning device provided in an embodiment of the present application;

FIG. 5 is a structural diagram of an implementation manner of an electronic device provided in an embodiment of the present application.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Embodiments of the present application provide a heavy overload early warning method, device and electronic equipment. Before introducing the technical solutions provided by the embodiments of the present application in detail, here is a brief introduction to the application scenarios involved in the embodiments of the present application.

In the power system, a station area refers to the power supply area of a power supply equipment, and a station area includes multiple loads and power supply equipment that supplies power to multiple loads. In the embodiment of the present application, any station area is referred to as the first area to introduce the technical solution.

The operating state of the power supply equipment located in the first area directly affects the power supply quality of the power supply equipment to the multiple loads located in the first area. The operating states of the power supply equipment can be divided into: heavy load operation, overload operation and normal operation based on the current power supply power of the power supply equipment and the rated power supply power of the power supply equipment.

The following examples illustrate heavy-load operation, overload operation and normal operation.

Exemplarily, in the embodiment of the present application, if the load rate of the power supply equipment reaches 80% for 2 consecutive hours or more, it is determined that the power supply equipment is in heavy-load operation; if the load rate of the power supply equipment reaches 100% for 2 consecutive hours or more, then It is determined that the power supply equipment is in overload operation; if the power supply equipment is in a state other than heavy load operation and overload operation, it is determined that the power supply equipment is in normal operation.

It is understandable that the power supply equipment in the first area is in heavy-load operation or overload operation for a long time, which not only affects the safety of power consumption, but also accelerates the loss of power supply equipment and reduces the service life of power supply equipment. The heavy and overload warning in the station area has become an urgent problem to be solved in the power system.

Based on the above reasons, embodiments of the present application provide a heavy overload early warning method, device, electronic equipment, and storage medium. In this method, based on the weights corresponding to the plurality of electric quantity influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influences The probability distributions corresponding to the factor vectors are used to screen the multiple power influencing factor vectors in the first data feature set and the second data feature set, and the obtained multiple power influencing factor vectors in the third data feature set are all for the first data feature set. An electric quantity influence factor vector with a greater degree of influence of heavy overload in a region, so the heavy overload prediction result of the first region obtained based on the third data feature set is more accurate, thereby realizing heavy overload early warning for the station region.

A heavy overload early warning method provided in the embodiment of the present application will be described in detail below.

As shown in FIG. 1 , it is a schematic flowchart of a heavy overload early warning method provided by the embodiment of the present application. The method includes the following steps S101 to S108 during implementation.

Step S101: Obtain the first data feature set corresponding to the first time period in the first area, and the second data feature set corresponding to the second time period.

Exemplarily, the first time period is a time period that is earlier than the current time and takes the current time as the end time, the second time period is later than the current time and takes the current time as The time period for the start time.

Exemplarily, both the first data feature set and the second data feature set include a plurality of electric quantity influencing factor vectors

Exemplarily, one of the electric quantity influencing factor vectors is an influencing factor affecting power supply of multiple loads by the power supply equipment located in the first area.

Exemplarily, the dimensions of different power influence factor vectors may be the same, for example, elements 0 may be used to fill the lower-dimensional power influence shadow vector, so that the dimension of the lower-dimensional power influence shadow vector can reach a higher dimension.

Exemplarily, the dimensions of the vectors of different power influence factors may be different.

The following will introduce the first time end, the second time period, and the electric quantity influencing factor vector with specific examples.

The first time period is the historical time period, and the second time period is the forecast time period. For example, the first time period may be a time period 7 days earlier than the current time, and the second time period may be a time period 3 days later than the current time.

The multiple power influence factor vectors contained in the first data feature set corresponding to the first time period can be the power influence factor vectors corresponding to each of the above 7 days, and the multiple power influence factor vectors contained in the second data feature set corresponding to the second time period The influence factor vector may be the electric power influence factor vector corresponding to each day in the above-mentioned next 3 days. The plurality of power influence factor vectors contained in the second data feature set corresponding to the second time period may be weather information corresponding to each day in the next 3 days, such as one or more of temperature, air pressure, precipitation, humidity, and Time information, such as one or more of date, month, and whether it is a holiday.

Exemplarily, the first time period may include the current time. For example, if the current time is T day, the first time period may be (T day, T-1 day, T-2 day, T-3 day, T-4 day, T-5 day and T-6 day), The second time period may be (T+1 day, T+2 day, T+3 day). Correspondingly, the first data feature set is a plurality of power influences corresponding to T-day, T-1 day, T-2 day, T-3 day, T-4 day, T-5 day and T-6 day A collection of factor vectors, the second data feature collection is a collection of multiple electric quantity influencing factor vectors corresponding to T+1 day, T+2 day, and T+3 day respectively.

Step S102: Obtain the weights corresponding to the plurality of electric quantity influencing factor vectors respectively.

Exemplarily, different power influence factor vectors have different influence degrees on the power supply equipment supplying power to multiple loads. The weight corresponding to one electric quantity influencing factor vector represents the degree of influence of the electric quantity influencing factor vector on the power supply of the power supply equipment to multiple loads.

Exemplarily, a randomforest (random forest) algorithm may be used to calculate the respective weights corresponding to the multiple electric quantity influencing factor vectors.

Exemplarily, the greater the degree of influence of one quantity influencing factor vector on the power supply of the power supply equipment to multiple loads, the greater its corresponding weight.

Exemplarily, the weights corresponding to the plurality of electric quantity influencing factor vectors are all arbitrary values greater than or equal to 0 and less than or equal to 1.

Exemplarily, the sum of the respective weights corresponding to multiple electric quantity influencing factor vectors is equal to 1.

Step S103: Determine the first attributes respectively corresponding to the plurality of electric quantity influencing factor vectors.

Wherein, the first attribute represents the attribute information corresponding to the electric quantity influencing factor vector.

For example, for the electric quantity influence factor vector T-day overload times, T-1 day overload times, and T-2 day overload times, the first attribute is "overload times"; for the electric quantity influence factor vector T-day temperature, T-1 day temperature , T+1 daily temperature, the first attribute of which is "temperature"

Step S104: Obtain at least one set of correlation coefficients corresponding to the first set.

Wherein, the first set includes any two different first attributes among the first attributes, and the two first attributes included in different first sets are not completely the same.

Exemplarily, if the plurality of electric quantity influencing factor vectors respectively correspond to four first attributes, including: first attribute 1, first attribute 2, first attribute 3, and first attribute 4.

The first set includes: {first attribute 1, first attribute 2}, {first attribute 2, first attribute 3}, {first attribute 3, first attribute 4}, {first attribute 1, first attribute One attribute 3} {first attribute 1, first attribute 4} and {first attribute 2, first attribute 4}.

Exemplarily, the correlation coefficient characterizes the degree of correlation between two electric quantity influencing factor vectors in the first set.

计算第一集合中两个电量影响因子向量的相关系数。Exemplarily, it can be based on a preset formula:

Compute the correlation coefficient of the two electricity influence factor vectors in the first set.

Among them, ρ _{X, Y} represents the correlation coefficient between the vector X of the power influence factor and the vector Y of the power influence factor, COV(X, Y) represents the covariance of the vector X of the power influence factor and the vector Y of the power influence factor, and σ _X represents the power influence factor The average value of the vector X, σ _Y represents the average value of the electric quantity influencing factor vector Y.

Exemplarily, the value of the correlation coefficient ρ _XY is between -1 and 1. When ρ _XY =0, it is said that X and Y are not correlated; when |ρ _XY |=1, it is said that X and Y are completely correlated. At this time , there is a linear functional relationship between X and Y; when |ρ _XY |<1, the change of X will cause a partial change of Y, the larger the absolute value of ρ _XY , the greater the change of Y caused by the change of X, |ρ _XY When |> the first value, it is called high correlation, when |ρ _XY |< second value, it is called low correlation, and at other times it is moderate correlation.

The first value is greater than the second value. Exemplarily, the first value=0.8 and the second value=0.3 are just examples, and 0.8 and 0.3 are just examples, which are not limited in this embodiment of the present application.

Exemplarily, in the embodiment of the present application, if the correlation coefficient ρ _XY represents that X and Y are completely correlated or highly correlated, the power influence factor vector X is used to replace the power influence factor vector Y, or the power influence factor vector Y is used to replace the power influence Factor vector X, to reduce the operation process.

The above operation process includes a training process for obtaining a heavy overload early warning model; and a calculation process for the heavy overload early warning model to obtain a first prediction result based on the second data feature set.

Step S105: Obtain at least one joint influence degree corresponding to the first set.

The joint influence degree corresponding to one of the first sets represents the power supply for each load located in the first area when the two different first attributes included in the first set act on the first area at the same time. The power output of the power supply device changes.

Exemplarily, in an actual application, there may be a situation where the weights corresponding to the two electric power influencing factor vectors of different first attributes are relatively large, but the combined influence of the two on the heavy overload of the first region is small.

Exemplarily, in an actual application, there may be a situation where the weights corresponding to the electric power influencing factor vectors of two different first attributes are very different, but the joint influence of the two on the heavy overload of the first region is relatively small or relatively large.

Exemplarily, in practical applications, it may appear that the weights corresponding to the electric power influencing factor vectors of two different first attributes are relatively small, but the two belong to different first attributes, so the joint influence on the heavy overload of the first area larger case.

Therefore, it is necessary to consider the joint influence of different first attributes on heavy overload when performing screening.

In the following, two different first attributes are humidity and air pressure as an example to introduce the joint influence degree. It is assumed that if the weight of the power influencing factor vector is smaller than the third value, it means that the influence of the power influencing factor vector on the power supply device supplying power to multiple loads is relatively small. In the following, the joint influence degree takes a value between 0 and 1, and the humidity and air pressure are both 1×1 dimensional vectors, and the third value is 0.5 as an example for illustration.

For example, if the weight corresponding to the humidity on T day is 0.2, the weight corresponding to the air pressure on T day is 0.3, and the humidity on T day and the air pressure on T day are both less than 0.5, it can be seen that the humidity on T day and the humidity on T day have great influence on the power supply equipment’s ability to supply power to multiple loads. The degree of influence is small. If the calculated joint influence degree of humidity and air pressure on the power supply equipment supplying power to multiple loads is greater than or equal to 0.5, it means that the first attribute with different humidity and air pressure has a greater joint influence on the power supply equipment supplying power to multiple loads. Therefore, it is necessary to filter the humidity on day T and the humidity on day T into the third data feature set when screening the electric quantity influencing factor vector.

Step S106: For the multiple electric quantity influencing factor vectors belonging to the same first attribute, obtain first probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors.

Exemplarily, if the dimension of the electric quantity influencing factor vector is a 1×1 dimensional vector, then the first probability distribution corresponding to the electric quantity influencing factor vector is a 0-1 distribution.

Exemplarily, if the dimension of the electric quantity influencing factor vector is a multi-dimensional vector, then the first probability distribution of an electric quantity influencing factor vector represents the dispersion of all elements contained in the electric quantity influencing factor vector, if the electric quantity influencing factor vector contains If all the elements are too concentrated in a certain threshold range, it means that the electric quantity influence factor vector changes little, and has little reference significance for predicting the operating state of the power supply equipment located in the first area.

In the following, the probability distribution corresponding to the electric quantity influencing factor vector is introduced by taking the electric quantity influencing factor vector as a temperature vector as an example.

Exemplarily, the temperature is an important factor affecting the power supply of the power supply equipment to the load, that is, when the temperature is used as a power factor vector, the corresponding weight is relatively large.

In summer, when the temperature is higher, the operating time of the air conditioner (a type of load) located in the first area will be greatly increased, and the power supply of the power supply equipment may be greatly increased. In spring, due to the suitable temperature, the operating time of the air conditioner located in the first area is greatly reduced, or even does not operate, so that the power supply of the power supply equipment is greatly reduced.

However, in a short period of time, the change in temperature may not be large, for example, the temperature is maintained at 20 degrees to 22 degrees within a week, so the temperature has little reference significance for predicting heavy overload in the first area. , for example, in the next three days, the temperature vector may not be considered, that is, the temperature vector may not be filtered into the third data feature set.

Exemplarily, for long-term forecasting, such as the next month, the temperature vector needs to be considered, that is, the temperature vector is filtered into the third data feature set.

Exemplarily, the weights corresponding to the power influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric power influences Different thresholds are set for the probability distributions corresponding to the factor vectors, so as to determine the second data feature set from the first data feature set.

For example, the first threshold value corresponding to the weight is 0.5, the second threshold value corresponding to the related system is 0.8, the third threshold value corresponding to the joint influence degree is 0.5, and the fourth threshold value corresponding to the first probability distribution is 0.9.

Step S107: The weights corresponding to the plurality of electric quantity influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, the multiple electric quantity influences The probability distributions corresponding to the factor vectors, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model.

Step S108: Obtain the first prediction result output by the heavy overload warning model.

Wherein, the first prediction result is the operation state of the power supply equipment within the first time period within the second time period, and the operation state includes: normal operation and/or overload operation and/or heavy load operation.

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

Exemplarily, if the current power supply of the power supply equipment is greater than or equal to 80% of the rated power supply power of the power supply equipment and less than or equal to the rated power supply power of the power supply equipment, it is determined that the power supply equipment is in heavy-duty operation. If the power supply power of the power supply equipment is greater than the rated power supply power of the power supply equipment, it is determined that the power supply equipment is in overload operation; if the current power supply power of the power supply equipment is less than 80% of the rated power supply power of the power supply equipment, it is determined that the power supply equipment is in normal operation .

Exemplarily, the heavy overload early warning model can focus on the weights corresponding to the power influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, Different thresholds are set for the probability distributions corresponding to the plurality of power influencing factor vectors, so as to determine a third data feature set from the first data feature set and the second data feature set.

For example, the first threshold value corresponding to the weight is 0.5, the second threshold value corresponding to the related system is 0.8, the third threshold value corresponding to the joint influence degree is 0.5, and the fourth threshold value corresponding to the first probability distribution is 0.9.

It can be known from the above technical solutions that in the heavy overload early warning method provided by the present application, the first data feature set corresponding to the first time period of the first area and the second data feature set corresponding to the second time period are obtained, wherein the first time The period is a historical time period, the second time period is a time period to be predicted, and both the first data feature set and the second data feature set include multiple electric quantity influencing factor vectors. Each electric quantity influencing factor vector is analyzed to determine the weight corresponding to each electric quantity influencing factor vector, and the weight characterizes the degree of influence of the electric quantity influencing factor vector on the heavy overload of the first area. Determine first attributes respectively corresponding to the plurality of electric quantity influencing factor vectors, where the first attributes represent attribute information corresponding to the electric quantity influencing factor vectors. Obtain the correlation coefficient between two different first attributes. If the correlation coefficient is greater than the preset threshold, it is considered that there is a linear correlation between the two first attributes, that is, the power influencing factor vector in one of the first attributes can be used to replace the other. A vector of power impact factors in the first attribute. Obtain the joint influence degree corresponding to any two first attributes, where the joint influence degree represents the change in the power output of the power supply equipment that supplies power to each load located in the first area when two different first attributes act on the first area at the same time . In practical applications, it may appear that the weights corresponding to the two power influence factor vectors are relatively small, but because the two belong to different first attributes, the joint influence of the two on the heavy overload of the first area is relatively large, so When screening, it is necessary to consider the joint influence of different first attributes on heavy overload. For the multiple electric quantity influencing factor vectors belonging to the same first attribute, the first probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors are acquired, and the probability distribution of one electric quantity influencing factor vector characterizes the discreteness of the electric quantity influencing factor vector If the vector of the electric quantity influencing factor is too concentrated in a certain threshold range, it means that the vector of the electric quantity influencing factor changes little, and the reference significance for predicting heavy overload in the first area is small.

The weights corresponding to the multiple electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influencing factor vectors respectively The corresponding first probability distribution, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model to obtain the output of the heavy overload early warning model for the power supply equipment at the first The first prediction result of the running status in the second time period.

To sum up, in the heavy overload early warning method provided by the embodiment of the present application, since the heavy overload early warning model is based on weights corresponding to a plurality of electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of The joint influence degree corresponding to the first set, the first probability distribution corresponding to the plurality of electric quantity influence factor vectors respectively, for the plurality of electric quantities contained in the first data feature set and the second data feature set The influence factor vectors are screened, so after screening, the multiple power influence factor vectors in the third data feature set are all power influence factor vectors that have a greater impact on the heavy overload in the first area, so based on the third data feature set The heavy overload prediction result of the first area obtained is more accurate, so as to realize the heavy overload early warning of the station area.

In an optional embodiment, in order to know the specific operating status of the power supply equipment in the first time period in each time period in the first area, so as to subsequently adjust the power supply equipment in the first area in a targeted manner. The embodiment of the present application provides an implementation manner of obtaining the first prediction result output by the heavy overload early warning model.

This implementation includes: Step A1 to Step A3.

Step A1: If the first prediction result indicates that the power supply equipment is in overload operation during the second time period, the first prediction result further includes a time period in which the power supply equipment is in overload operation.

and / or,

Step A2 If the first prediction result indicates that the power supply equipment is in heavy-load operation during the second time period, the first prediction result also includes the time period when the power supply equipment is in heavy-load operation;

and / or,

Step A3: If the first prediction result indicates that the power supply equipment operates normally within the second time period, the first prediction result further includes a time period during which the power supply equipment is in normal operation.

The following takes a specific example as an example, the first prediction result.

The following is the operating status of the power supply equipment in each time period of the day in the first prediction result, for example, from 0:00 to 6:00, the operating status of the power supply equipment is normal operation; from 6:00 to 12: 00, the operating state of the power supply equipment is heavy load operation; from 12:00 to 22:00, the operating state of the power supply equipment is overload operation; from 22:00 to 24:00, the operating state of the power supply equipment is normal run. Then the first prediction result includes the time periods corresponding to each operating state, that is, the normal operation time of the power supply equipment is 0:00 to 6:00, and 22:00 to 24:00, and the normal operation time is 8 hours; The time of heavy load operation of power supply equipment is from 6:00 to 12:00, and the duration of heavy load operation is 6 hours; the time of overload operation of power supply equipment is from 12:00 to 22:00, and the duration of overload operation is 10 hours.

In the embodiment of the present application, the specific operating status of the power supply equipment in the first area in the second time period can be grasped based on the prediction results, so that the power supply equipment in the first area can be adjusted in each time period.

In an optional embodiment, in order to realize accurate early warning of heavy overload in each station area in the first area, the embodiment of the present application provides another implementation manner of obtaining the prediction result output by the heavy overload early warning model.

This implementation includes:

Step B1: If the first prediction result indicates that the power supply equipment is overloaded within a second time period, the first prediction result further includes a second probability that the power supply equipment is in heavy load operation.

and / or,

Step B2: If the prediction result indicates that the power supply equipment is in heavy-load operation within the second time period, the first prediction result further includes a second probability that the power supply equipment is in a heavy-load state;

and / or,

Step B3: If the prediction result indicates that the power supply equipment operates normally within the second time period, the first prediction result further includes a third probability that the power supply equipment is in a normal state.

In this embodiment of the present application, the first probability represents the probability that the power supply equipment is allowed to overload within the second time period, the second probability represents the probability that the power supply equipment is in heavy-load operation within the second time period, and the third probability Characterizes the probability that the power supply equipment is in normal operation within the second time period. If the first probability is higher, it means that the first region has a higher probability of being overloaded within the first time period, so as to realize accurate early warning of heavy overload in each station area in the first region.

In an optional embodiment, because the overload state exceeds the rated power supply power of the power supply equipment, it is more necessary to monitor the power supply equipment in the overload state. For this reason, the embodiment of the present application provides a method for marking the power supply equipment in the overload state, so as to monitor the power supply equipment in the overload state subsequently. The method includes:

Step C1: If the first probability is greater than or equal to the first threshold, set the icon representing the first region in the running state marker map as the first identifier.

Step C2: If the first probability is greater than or equal to the second threshold and less than the first threshold, set the icon representing the first area in the running state marker map as a second identifier.

Step C3: If the first probability is less than the second threshold, set the icon representing the first area in the running state marker map as a third identifier.

Exemplarily, the running state sign map includes at least one area corresponding to the identification, and the at least one area includes the first area.

Exemplarily, the first threshold is greater than the second threshold, for example, the first threshold is 80%, and the second threshold is 60%.

That is, if the first probability is greater than or equal to 80%, the first area is a high-risk area; if the first probability is greater than or equal to 60% and less than 80%, the first area is a medium-risk area; if the first probability is less than 60% %, the first area is a low-risk area.

Exemplarily, different identifications may be given to devices in the first area based on the risk level of the first area. For example, if the first area is a high-risk area, set the first mark for the first area, if the first area is a medium-risk area, set the second mark for the first area, and if the first area is a low-risk area, then Set the third flag for the first area.

Exemplarily, the first logo, the second logo and the third logo may be logos of different shapes or colors.

For example, the first mark is red, the second mark is yellow, and the third mark is green.

Exemplarily, the first logo, the second logo and the third logo may be displayed in a blinking manner.

In this embodiment of the present application, the colors and shapes of the first logo, the second logo and the third logo are not limited, and the first logo, the second logo and the third logo can be A combination of different shapes and different colors.

In an optional embodiment, the embodiment of the present application discloses an implementation manner of acquiring the first data feature set and the second data feature set.

As shown in FIG. 2 , it is a flow chart of an implementation manner of acquiring a first data feature set and a second data feature set provided by the embodiment of the present application. This implementation manner includes: step S201 to step S206.

Step S201: Obtain weather information and time information respectively corresponding to each day in the first time period in the first area.

The weather information corresponding to a day includes: at least one of the temperature of the day, the air pressure of the day, humidity and precipitation, and the time information corresponding to a day includes: the date of the day, the month of the day, the month of the day At least one of the corresponding week, whether the day is a holiday, and the season to which the day belongs.

Step S202: Obtain the number of loads corresponding to each day of at least one load type and the proportion of power consumption corresponding to each day of the at least one load type within the first time period.

One of the load types corresponds to at least one load located in the first area.

Exemplarily, the load types can be divided based on different angles. For example, if the load type is electricity consumption type, the load type can be divided into high power consumption load, medium power consumption load and low power consumption load; if the load type is industry type, the load type can be divided into production type Electric load, household electric load, and service electric load; if the load type is city type, the load type can be divided into first-level urban electric load, second-level urban electric load, and third-level urban user load.

Step S203: Obtain the operating parameters of the power supply equipment corresponding to each day in the first time period.

The operating parameters corresponding to one day include at least one of overload times, reload times, overload duration, reload duration, average load rate, and maximum load rate.

Step S204: The temperature, humidity, air pressure, precipitation, date, month, week, holiday, season corresponding to each day in the first time period, the load quantity corresponding to each day of the at least one load type, the The proportion of power consumption corresponding to at least one load type in each day, the number of overloads, the number of overloads, the duration of overloading, the duration of overloading, the average load rate, and the maximum load rate of the power supply equipment in each day are respectively used as the first data A vector of electric power influencing factors in the feature set to obtain the first data feature set.

Step S205: Obtain weather information and date information respectively corresponding to each day in the second time period in the first area.

The weather information includes at least one of temperature, air pressure, humidity and precipitation, and the date information includes at least one of month, week, holiday and season.

Step S206: Use the temperature, humidity, air pressure, precipitation, date, month, week, holiday, and season corresponding to each day in the second time period as the electric quantity influencing factor vector in the second data feature set , to obtain the second data feature set

In an optional embodiment, the embodiment of the present application also provides a method for constructing a heavy overload early warning model.

As shown in FIG. 3 , it is a flowchart of a construction process of a heavy overload early warning model provided by the embodiment of the present application. The process includes: step S301 to step S310.

Step S301: Obtain multiple feature sets of historical data corresponding to the first area.

One set of historical data features includes a sixth data feature set corresponding to a third time period in the first area, and a fourth data feature set corresponding to a fourth time period, the third time period being earlier than a preset historical time, And the time period with the preset historical time as the end time, the earliest time of the fourth time period is later than the historical time, and the latest time is earlier than the current time, the sixth data feature set and the Each of the fourth data feature sets includes a plurality of sample power influencing factor vectors.

Exemplarily, in the embodiment of the present application, the elements included in the historical data feature sets corresponding to the multiple historical times are the same as the elements included in the first data feature feature vector set corresponding to the current time.

Exemplarily, the element values corresponding to the elements in the historical data feature sets corresponding to different historical times may be different.

Exemplarily, for a historical time, the third data feature corresponding to the historical time includes:

The weather information and date information corresponding to each day in the third time period, the weather information at least includes: temperature, air pressure, humidity and precipitation, and the date information at least includes: month, week, holiday and season

The number of loads and power consumption ratios corresponding to at least one load type corresponding to the first area within the third time period, one load type corresponding to at least one load located in the first area.

The times of overloading, times of reloading, duration of overloading, duration of reloading, average load rate, and maximum load rate of the power supply equipment corresponding to each day in the third time period.

The historical time corresponds to the fourth data feature set including:

The weather information and date information corresponding to each day in the fourth time period, the weather information at least includes: temperature, air pressure, humidity and precipitation, and the date information at least includes: month, week, holiday and season.

The operation step S302 of step S302 to step S307 is executed for each of the historical data feature sets: obtaining weights respectively corresponding to a plurality of the sample electric quantity influencing factor vectors.

Step S303: Determine the second attributes respectively corresponding to the plurality of sample power influencing factor vectors.

Step S304: Obtain at least one set of correlation coefficients corresponding to the second set.

The second set includes any two different second attributes among the plurality of second attributes, and the two second attributes included in different second sets are not completely the same.

Step S305: Obtain at least one joint influence degree corresponding to the second set.

The joint influence degree corresponding to one of the first sets represents the power supply equipment that supplies power to each load located in the first area when two different second attributes included in the first set act on the first area at the same time power output changes.

Step S306: For the multiple electric quantity influencing factor vectors belonging to the same first attribute, obtain second probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors.

Step S307: The weights corresponding to the plurality of sample electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the second set, the joint influence degree corresponding to at least one set of the second set, the multiple electric quantities The second probability distributions respectively corresponding to the impact factor vectors, and the feature set of the historical data are input to the machine learning model.

Exemplarily, the machine learning model can be any one of neural network model, logistic regression model, linear regression model, LIGHTGBM model, support vector machine (SVM), Adaboost, XGboost, Transformer-Encoder model.

Exemplarily, the neural network model may be any one of a model based on a recurrent neural network, a model based on a convolutional neural network, and a classification model based on a Transformer-encoder.

Exemplarily, the machine learning model may be a deep hybrid model of a model based on a recurrent neural network, a model based on a convolutional neural network, and a classification model based on a Transformer-encoder.

Exemplarily, the machine learning model may be any one of an attention-based deep model, a memory network-based deep model, and a deep learning-based short text classification model.

The short text classification model based on deep learning is a recurrent neural network (RNN) or a convolutional neural network (CNN) or a variant based on a recurrent neural network or a convolutional neural network.

Exemplarily, some simple domain adaptation can be done on the pre-trained model to obtain a machine learning model.

Exemplarily, "simple domain adaptation" includes, but is not limited to, using large-scale unsupervised domain corpus to perform secondary pre-training on the pre-trained model, and/or, through model distillation The pre-trained model performs model compression.

Exemplarily, supervised learning and semi-supervised learning can be performed on the machine learning model. Semi-supervised learning is a learning method that combines supervised learning and unsupervised learning. Semi-supervised learning uses large amounts of unlabeled data, as well as labeled data, for pattern recognition.

Step S308: Obtain a second prediction result corresponding to the historical data feature set output by the machine learning model, so as to obtain a plurality of second prediction results corresponding to each of the historical data feature sets.

The second prediction result is the machine learning model based on the weights corresponding to the multiple sample electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the second set, at least one set of correlation coefficients corresponding to the second set Combine the degree of influence and the second probability distributions respectively corresponding to the plurality of power influence factor vectors, filter the historical data feature set to obtain the fifth data feature set, and output the fourth data feature set based on the fifth data feature set A prediction result of the operating state of the power supply equipment within the time period.

One of the second prediction results includes the operation state of the power supply equipment within a fourth time period, and the operation state includes normal operation and/or overload operation and/or heavy load operation.

Exemplarily, the specific implementation process of step S301 to step S308 may refer to step S101 to step S108 in FIG. 1 , which will not be repeated here.

Step S309: For each second prediction result, compare the second prediction result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtain a comparison result, so as to obtain a plurality of the second prediction results. The prediction results correspond to the comparison results respectively.

Step S310: Train the machine learning model based on multiple comparison results to obtain the heavy overload warning model.

It can be understood that the embodiment of the present application is not limited to the heavy overload early warning model training method, and those skilled in the art can select an appropriate training method based on the current working conditions to train the heavy overload early warning model.

Exemplarily, the heavy overload early warning model is trained and optimized in a manner of gradually iterating multiple electric quantity influencing factor vectors.

In an optional embodiment, in step S309, comparing the second prediction result with the actual operating state of the power supply equipment in the corresponding fourth time period, obtaining the comparison result includes:

Step D1: If the operation state in the second prediction result is overload operation, the second prediction result also includes the first prediction probability that the power supply equipment is in overload operation, and the actual operation state includes the power supply equipment A first real probability that the plant is operating at overload during the fourth time period.

Step D2: Comparing the first predicted probability and the first real probability to obtain the comparison result.

Exemplarily, if it is determined that the power supply equipment is in the overload state within the fourth time period, the first true probability is 1; if it is determined that the power supply equipment is in the non-overload state within the fourth time period, the The first true probability is 0.

and / or,

Step D3: If the operation state in the second prediction result is heavy-load operation, the second prediction result also includes a second predicted probability that the power supply equipment is in heavy-load operation, and the actual operation state includes the The second true probability that the power supply equipment is in heavy-duty operation during the fourth time period.

Step D4: Comparing the second predicted probability and the second real probability to obtain the comparison result.

Exemplarily, if it is determined that the power supply equipment is in the overload state within the fourth time period, the second true probability is 1; if it is determined that the power supply equipment is in the non-overload state within the fourth time period, then The second true probability is 0.

and / or,

Step D5: If the operation state in the second prediction result is normal operation, the second prediction result further includes a third prediction probability that the power supply equipment is in normal operation, and the actual operation state includes the power supply equipment A third true probability that the plant is in heavy duty operation during said fourth time period.

Step D6: Comparing the third predicted probability and the third real probability to obtain the comparison result.

Exemplarily, if it is determined that the power supply equipment is in a normal state within the fourth time period, the third true probability is 1; if it is determined that the power supply equipment is in an abnormal state within the fourth time period, then the The third true probability is 0.

In an optional embodiment, the step S309 of comparing the second prediction result with the actual operating state of the power supply equipment within a corresponding fourth time period, and obtaining the comparison result further includes:

Step E1: If the operation state in the second prediction result is overload operation, the second prediction result also includes the first prediction time period during which the power supply equipment is in overload operation; the actual operation state also includes the The power supply equipment is in the first real time period of overload operation during the fourth time period.

Step E2: Comparing the first predicted time period and the first real time period to obtain the comparison result.

Exemplarily, the real time and real time duration when the power supply equipment is in overload operation within the fourth time period may be obtained based on historical data of the power system.

and / or,

Step E3: If the operation state in the second prediction result is heavy-load operation, the second prediction result also includes a second prediction time period during which the power supply equipment is in heavy-load operation; the actual operation state is also It includes a second real time period during which the power supply equipment is in heavy-load operation during the fourth time period.

Step E4: Comparing the second predicted time period and the second real time period to obtain the comparison result.

and / or,

Step E5: If the operation state in the second prediction result is normal operation, the second prediction result also includes a third prediction time period during which the power supply equipment is in normal operation; the actual operation state also includes the The power supply equipment is in a third real time period of normal operation during the fourth time period.

Step E6: Comparing the third predicted time period and the third real time period to obtain the comparison result.

The method is described in detail in the above-mentioned embodiments provided by this application. The method of this application can be realized by various devices. Therefore, this application also provides a heavy overload early warning device. The following specific examples are given for detailed description .

In an optional embodiment, the embodiment of the present application provides a heavy overload warning device. As shown in FIG. 4 , it is a structural diagram of a heavy overload early warning device provided in the embodiment of the present application.

The device includes: a first acquisition module 401, a second acquisition module 402, a first determination module 403, a third acquisition module 404, a fourth acquisition module 405, a fifth acquisition module 406, a first input module 407 and a sixth acquisition module 408.

The first acquiring module 401 is configured to acquire a first data feature set corresponding to a first time period in the first area, and a second data feature set corresponding to a second time period.

Wherein, the first time period is earlier than the current time and takes the current time as the end time, and the second time period is later than the current time and starts with the current time For a period of time, both the first data feature set and the second data feature set include a plurality of electric quantity influencing factor vectors.

The second obtaining module 402 is configured to obtain weights corresponding to the plurality of electric quantity influencing factor vectors respectively.

The first determining module 403 is configured to determine the first attributes corresponding to the plurality of electric quantity influencing factor vectors respectively, so as to obtain a plurality of first attributes, and the first attributes represent the attribute information corresponding to the electric quantity influencing factor vectors.

The third acquisition module 404 is configured to acquire at least one set of correlation coefficients corresponding to the first set, the first set includes any two different first attributes among the plurality of first attributes, and the different first sets include The two first properties of are not identical.

The fourth acquisition module 405 is configured to acquire at least one set of joint influence degrees corresponding to the first set, and a joint influence degree corresponding to the first set indicates that two different first attributes included in the first set act simultaneously When in the first area, the power output of the power supply equipment that supplies power to each load located in the first area changes.

The fifth acquiring module 406 is configured to acquire the first probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors for the multiple electric quantity influencing factor vectors belonging to the same first attribute.

The first input module 407 is configured to use the weights corresponding to the plurality of power influence factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple The first probability distribution, the first data feature set, and the second data feature set respectively corresponding to each of the power influence factor vectors are input to the pre-built heavy overload early warning model.

The sixth obtaining module 408 is configured to obtain a first prediction result output by the heavy overload early warning model, the first prediction result includes the operating state of the power supply equipment within the first time period, and the operating state includes normal run and/or run on overload and/or run on heavy load.

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

It can be understood that the embodiment of the heavy overload early warning device provided in the embodiment of the present application is compatible with the embodiment of the heavy overload early warning method provided in Figure 1, and the specific implementation process of the device embodiment can be found in the method embodiment in Figure 1 The implementation process will not be repeated here.

Exemplarily, the sixth acquisition module includes:

A first obtaining unit, configured to obtain a time period during which the power supply equipment is in overload operation if the operation state of the first prediction result includes overload operation.

and / or,

A second obtaining unit, configured to obtain a time period during which the power supply equipment is in heavy-duty operation if the operation state of the first prediction result includes heavy-duty operation.

and / or,

A third obtaining unit, configured to obtain the time and duration when the power supply equipment is in a normal state if the operation state of the first prediction result includes normal operation.

Exemplarily, the sixth acquisition module also includes:

A fourth obtaining unit, configured to obtain a first probability that the power supply equipment is in an overload state if the operation state of the first prediction result includes heavy load operation.

and / or,

A fifth obtaining unit, configured to obtain a second probability that the power supply equipment is in a heavy-load state if the operation state of the first prediction result includes heavy-load operation.

and / or,

A sixth obtaining unit, configured to obtain a third probability that the power supply equipment is in a normal state if the operation state of the first prediction result includes normal operation.

Exemplarily, the first acquisition module includes:

The seventh obtaining unit is used to obtain weather information and time information corresponding to each day in the first time period in the first area, and the weather information corresponding to one day includes: the temperature of the day, the air pressure of the day, and the humidity And at least one of precipitation, the time information corresponding to a day includes: at least one of the date the day belongs to, the month the day belongs to, the week corresponding to the day, whether the day is a holiday, and the season the day belongs to.

The eighth acquisition unit is configured to acquire the quantity of loads corresponding to each day of at least one load type and the proportion of power consumption corresponding to each day of the at least one load type within the first time period, and one load type corresponds to at least a load located in the first zone.

The ninth acquisition subunit is configured to acquire the operating parameters of the power supply equipment corresponding to each day in the first time period, and the operating parameters corresponding to one day include the number of overloads, the number of overloads, the duration of overloading, and the duration of overloading , at least one of the average load rate and the maximum load rate.

The first determination unit is configured to calculate the temperature, humidity, air pressure, precipitation, date, month, week, holiday, season, and load corresponding to each day of the at least one load type in the first time period. Quantity, the proportion of power consumption corresponding to each day of the at least one load type, the number of times of overload, the number of times of heavy load, the duration of overload, the length of heavy load, the average load rate, and the maximum load rate of the power supply equipment are respectively used as the The electric quantity influencing factor vector in the first data feature set is obtained to obtain the first data feature set.

The tenth acquiring subunit is configured to acquire weather information and date information respectively corresponding to each day in the second time period in the first area.

The second determining unit is configured to use the temperature, humidity, air pressure, precipitation, date, month, week, holiday, and season corresponding to each day in the second time period as the data in the second data feature set. A vector of power influencing factors to obtain the second data feature set.

Exemplarily, the heavy overload early warning device further includes: a first building module, configured to build the heavy overload early warning model.

Exemplarily, the first building block includes:

The first construction unit is configured to obtain a first region and obtain a plurality of feature sets of historical data corresponding to the first region.

One set of historical data features includes a sixth data feature set corresponding to a third time period in the first area, and a fourth data feature set corresponding to a fourth time period, the third time period being earlier than a preset historical time, And the time period with the preset historical time as the end time, the earliest time of the fourth time period is later than the historical time, and the latest time is earlier than the current time, the sixth data feature set and the Each of the fourth data feature sets includes a plurality of sample power influencing factor vectors.

The second construction unit is configured to obtain the weights corresponding to the plurality of sample power influencing factor vectors respectively.

The third construction unit is configured to determine the second attributes respectively corresponding to the plurality of sample power influencing factor vectors.

The fourth construction unit obtains at least one set of correlation coefficients corresponding to the second set, the second set includes any two different second attributes among the plurality of second attributes, and the two second attributes included in the second set are different from each other. The two properties are not exactly the same.

The fifth construction unit is configured to obtain at least one set of joint influence degrees corresponding to the second set, and one joint influence degree corresponding to the first set indicates that two different second attributes included in the first set act on the In the first area, the power output of the power supply equipment that supplies power to each load located in the first area changes.

The sixth construction unit is configured to obtain the second probability distributions respectively corresponding to the multiple electric quantity influencing factor vectors for the multiple electric quantity influencing factor vectors belonging to the same first attribute.

The seventh construction unit is used to combine the weights corresponding to the plurality of sample power influencing factor vectors, the correlation coefficients corresponding to at least one set of the second set, the joint influence degree corresponding to at least one set of the second set, and the multiple The second probability distribution corresponding to each of the electric quantity influencing factor vectors, and the historical data feature set are input to the machine learning model. .

An eighth construction unit, configured to obtain a second prediction result corresponding to the historical data feature set output by the machine learning model, one of the second prediction results includes the operating status of the power supply equipment within a fourth time period, and the The above operating states include normal operation and/or overload operation and/or heavy load operation.

The second prediction result is the machine learning model based on the weights corresponding to the multiple sample electric quantity influencing factor vectors, at least one set of correlation coefficients corresponding to the second set, at least one set of correlation coefficients corresponding to the second set Combine the degree of influence and the second probability distributions respectively corresponding to the plurality of power influence factor vectors, filter the historical data feature set to obtain the fifth data feature set, and output the fourth data feature set based on the fifth data feature set A prediction result of the operating state of the power supply equipment within the time period.

The first comparison unit, for each second prediction result, compares the second prediction result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtains a comparison result, so as to obtain a plurality of the The comparison results corresponding to the second prediction results respectively.

A first training unit, configured to train the machine learning model based on a plurality of comparison results, so as to obtain the heavy overload warning model.

Exemplarily, the first comparison unit includes:

The first acquisition subunit, if the operation state in the second prediction result is overload operation, the second prediction result also includes the first prediction time period when the power supply equipment is in overload operation; the actual operation state It also includes the first real time period when the power supply equipment is in overload operation during the fourth time period:

and comparing the first predicted time period with the first real time period to obtain the comparison result.

and / or;

The second acquiring subunit is configured to if the operation state in the second prediction result is heavy-load operation, the second prediction result also includes a second prediction time period during which the power supply equipment is in heavy-load operation; The actual running state further includes a second real time period in which the power supply equipment is in heavy-load operation during the fourth time period;

and comparing the second predicted time period with the second real time period to obtain the comparison result.

and / or,

A third acquiring subunit, configured to if the operation state in the second prediction result is normal operation, the second prediction result further includes a third prediction time period during which the power supply equipment is in normal operation; the actual The running state also includes a third real time period in which the power supply equipment is in normal operation during the fourth time period;

and comparing the third predicted time period with the third real time period to obtain the comparison result.

Exemplarily, the first comparison unit further includes:

The fourth acquisition subunit, the operation state in the second prediction result is overload operation, the second prediction result also includes the first prediction probability that the power supply equipment is in overload operation, and the actual operation state includes the The first real probability that the power supply equipment is in overload operation during the fourth time period;

and comparing the first predicted probability with the first real probability to obtain the comparison result.

and / or,

The fifth obtaining subunit is configured to: if the operation state in the second prediction result is heavy-load operation, the second prediction result further includes a second prediction probability that the power supply equipment is in heavy-load operation, the The actual operating state includes a second true probability that the power supply equipment is in heavy-duty operation during the fourth time period;

and comparing the second predicted probability with the second true probability to obtain the comparison result.

and / or,

The sixth acquisition subunit is configured to: if the operation state in the second prediction result is normal operation, the second prediction result further includes a third prediction probability that the power supply equipment is in normal operation, and the actual operation the state includes a third true probability that the power supply is in heavy duty operation during the fourth time period;

and comparing the third predicted probability with the third actual probability to obtain the comparison result.

Exemplarily, the heavy overload warning device further includes:

A first marking module, configured to determine that the first area is a high-risk area if the first probability is greater than or equal to a first threshold, and set the icon representing the first area in the running state marking map as the first logo.

A second marking module, configured to determine that the first area is a medium-risk area if the first probability is greater than or equal to a second threshold and less than the first threshold, and represent the first area in a running state marking map icon set as the first logo.

A third marking module, configured to determine that the first area is a low-risk area if the first probability is less than the second threshold, and set the icon representing the first area in the running state marking map as the first logo.

As shown in FIG. 5, it is a structural diagram of an implementation manner of an electronic device provided in the embodiment of the present application. The electronic device includes:

The memory 501 is used for storing programs.

The processor 502 is configured to execute the program, and the program is specifically used for:

Obtain the first data feature set corresponding to the first time period of the first area, and the second data feature set corresponding to the second time period, the first time period is earlier than the current time, and the current time is the end time time period, the second time period is a time period later than the current time and starting from the current time, and both the first data feature set and the second data feature set include multiple A vector of power influencing factors;

Acquiring weights corresponding to multiple electric quantity influencing factor vectors;

determining a plurality of first attributes respectively corresponding to the electric quantity influencing factor vectors to obtain a plurality of first attributes, the first attributes representing attribute information corresponding to the electric quantity influencing factor vectors;

Obtain at least one set of correlation coefficients corresponding to a first set, the first set includes any two different first attributes among the plurality of first attributes, and the two first attributes included in different first sets are incomplete same;

Obtaining at least one set of joint influence degrees corresponding to the first set, where one joint influence degree corresponding to the first set indicates that when two different first attributes contained in the first set act on the first area at the same time, a change in the power output of the power supply equipment that supplies power to each load located in the first area;

Obtaining first probability distributions respectively corresponding to the plurality of electric quantity influencing factor vectors for the plurality of electric quantity influencing factor vectors belonging to the same first attribute;

The weights corresponding to the multiple electric quantity influencing factor vectors, the correlation coefficients corresponding to at least one set of the first set, the joint influence degree corresponding to at least one set of the first set, and the multiple electric quantity influencing factor vectors respectively The corresponding first probability distribution, the first data feature set and the second data feature set are input to the pre-built heavy overload early warning model;

Obtaining a first prediction result output by the heavy overload early warning model, the first prediction result including the operating state of the power supply equipment within the second time period, the operating state including normal operation and/or overload operation and/or or run with heavy load;

The first prediction result is based on the heavy overload early warning model based on the weights corresponding to a plurality of the power influence factor vectors, at least one set of correlation coefficients corresponding to the first set, at least one set of correlation coefficients corresponding to the first set The joint influence degree and the first probability distribution respectively corresponding to the multiple electric quantity influencing factor vectors are obtained by filtering the multiple electric quantity influencing factor vectors included in the first data feature set and the second data feature set A third data feature set, and based on the third data feature set, output a prediction result of the operating state of the power supply equipment within the second time period.

The processor 502 may be a central processing unit CPU, or an ASIC (Application Specific Integrated Circuit).

The electronic device may further include a communication interface 503 and a communication bus 504 , wherein the memory 501 , the processor 502 and the communication interface 503 complete mutual communication through the communication bus 504 .

An embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the various steps included in any one of the above heavy overload warning method embodiments are implemented.

It should be noted that the features described in the various embodiments in this specification can be replaced or combined with each other. For the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiments.

It should also be noted that in this article, relational terms such as first and second etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations Any such actual relationship or order exists between. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be directly implemented by hardware, software modules executed by a processor, or a combination of both. Software modules can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other Any other known storage medium.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A heavy overload early warning method is characterized by comprising the following steps:

acquiring a first data feature set corresponding to a first time period of a first area and a second data feature set corresponding to a second time period, wherein the first time period is a time period which is earlier than the current time and takes the current time as a termination time, the second time period is a time period which is later than the current time and takes the current time as an initiation time, and the first data feature set and the second data feature set both comprise a plurality of electric quantity influence factor vectors;

acquiring weights corresponding to the electric quantity influence factor vectors respectively;

determining first attributes corresponding to the electric quantity influence factor vectors respectively to obtain a plurality of first attributes, wherein the first attributes represent attribute information corresponding to the electric quantity influence factor vectors;

obtaining correlation coefficients corresponding to at least one group of first sets, wherein the first sets comprise any two different first attributes in the first attributes, and the two first attributes contained in the different first sets are not completely the same;

acquiring joint influence degrees corresponding to at least one group of first sets, wherein the joint influence degree corresponding to one first set characterizes electric quantity output change of power supply equipment for supplying power to each load in the first area when two different first attributes contained in the first set simultaneously act on the first area;

acquiring first probability distributions corresponding to the electric quantity influence factor vectors aiming at the electric quantity influence factor vectors belonging to the same first attribute;

inputting weights corresponding to the electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first set, joint influence degrees corresponding to at least one group of the first set, first probability distribution corresponding to the electric quantity influence factor vectors, the first data feature set and the second data feature set into a pre-constructed overload warning model;

obtaining a first prediction result output by the heavy overload early warning model, wherein the first prediction result comprises the operation state of the power supply equipment in the second time period, and the operation state comprises normal operation and/or overload operation and/or heavy load operation;

the first prediction result is obtained by screening the multiple electric quantity influence factor vectors contained in the first data feature set and the second data feature set to obtain a third data feature set based on weights corresponding to the multiple electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first set, joint influence degrees corresponding to at least one group of the first set, and first probability distribution corresponding to the multiple electric quantity influence factor vectors, respectively, by the heavy overload early warning model, and outputting a prediction result of the operating state of the power supply device in the second time period based on the third data feature set.

2. The heavy overload early warning method according to claim 1, wherein if the operation state includes overload operation, the first prediction result further includes a time period during which the power supply device is in overload operation;

and/or if the operation state comprises heavy-load operation, the first prediction result further comprises that the power supply equipment is in a heavy-load operation time period;

and/or if the operation state comprises normal operation, the first prediction result further comprises a time period when the power supply equipment is in normal operation.

3. The overload warning method according to claim 1, wherein if the operation state includes overload operation, the first prediction result further includes a first probability that the power supply equipment is in overload operation;

and/or, if the operation state includes heavy-load operation, the first prediction result further includes a second probability that the power supply device is in heavy-load operation;

and/or if the operation state comprises normal operation, the first prediction result further comprises a third probability that the power supply equipment is in normal operation.

4. The heavy overload early warning method according to claim 3, further comprising:

if the first probability is greater than or equal to a first threshold value, setting icons representing the first areas in an operation state label graph as first identifications, wherein the operation state label graph comprises identifications respectively corresponding to at least one area, and the at least one area comprises the first areas;

if the first probability is larger than or equal to a second threshold value and smaller than a first threshold value, setting an icon representing the first area in the running state marker graph as a second identifier;

and if the first probability is smaller than the second threshold value, setting an icon representing the first area in the running state label graph as a third identifier.

5. The heavy overload early warning method according to any one of claims 1 to 4, wherein the obtaining a first data feature set corresponding to a first time period of a first area and a second data feature set corresponding to a second time period comprises:

acquiring weather information and time information respectively corresponding to each day in a first time period in the first area, wherein the weather information corresponding to one day comprises: at least one of the temperature of the day, the pressure of the day, the humidity and the precipitation, wherein the time information corresponding to the day includes: at least one of a date to which the day belongs, a month to which the day belongs, a week corresponding to the day, whether the day is a holiday and a season to which the day belongs;

acquiring the load quantity corresponding to each day of at least one load type and the power consumption ratio corresponding to each day of the at least one load type in the first time period, wherein the loads belonging to the at least one load type are all located in the first area;

acquiring operation parameters of the power supply equipment corresponding to each day in the first time period, wherein the operation parameters corresponding to each day comprise at least one of overload times, overload duration, average load rate and maximum load rate;

respectively taking the temperature, the humidity, the air pressure, the precipitation, the date, the month, the week, the holiday, the season, the load quantity respectively corresponding to each day of the at least one load type, the power consumption duty ratio respectively corresponding to each day of the at least one load type, the overload times, the overload duration, the average load rate and the maximum load rate respectively corresponding to each day of the power supply equipment as the electric quantity influence factor vector in the first data feature set so as to obtain the first data feature set;

acquiring weather information and date information respectively corresponding to each day in the second time period in the first area;

and respectively taking the temperature, the humidity, the air pressure, the precipitation, the date, the month, the week, the holiday and the season corresponding to each day in the second time period as the electric quantity influence factor vector in the second data feature set so as to obtain the second data feature set.

6. The heavy overload early warning method according to claim 1, further comprising:

acquiring a plurality of historical data feature sets corresponding to the first area, wherein one historical data feature set comprises a sixth data feature set corresponding to a third time period of the first area and a fourth data feature set corresponding to a fourth time period, the third time period is a time period which is earlier than a preset historical time and takes the preset historical time as a termination time, the fourth time period is earlier than the historical time at the earliest time and earlier than the current time at the latest time, and the sixth data feature set and the fourth data feature set both comprise a plurality of sample electric quantity influence factor vectors;

performing the following for each of the sets of historical data features:

obtaining weights corresponding to the sample electric quantity influence factor vectors respectively;

determining second attributes corresponding to the plurality of sample electric quantity influence factor vectors respectively to obtain a plurality of second attributes, wherein the second attributes represent attribute information corresponding to the sample electric quantity influence factor vectors;

obtaining correlation coefficients corresponding to at least one group of second sets, wherein the second sets comprise any two different second attributes in the second attributes, and the two second attributes contained in the different second sets are not completely the same;

acquiring joint influence degrees corresponding to at least one group of the second sets, wherein the joint influence degree corresponding to one first set characterizes the electric quantity output change of power supply equipment for supplying power to each load in the first area when two different second attributes contained in the first set simultaneously act on the first area;

acquiring second probability distributions corresponding to the electric quantity influence factor vectors aiming at the electric quantity influence factor vectors belonging to the same first attribute;

inputting weights corresponding to the sample electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of second sets, joint influence degrees corresponding to at least one group of second sets, second probability distributions corresponding to the electric quantity influence factor vectors and the historical data feature set into a machine learning model;

obtaining second prediction results corresponding to the historical data feature sets output by the machine learning model to obtain second prediction results corresponding to a plurality of historical data feature sets respectively, wherein one second prediction result comprises the operation state of the power supply equipment in a fourth time period, and the operation state comprises normal operation and/or overload operation;

the second prediction result is obtained by screening the historical data feature set to obtain a fifth data feature set based on weights corresponding to the plurality of sample electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the second sets, joint influence degrees corresponding to at least one group of the second sets, and second probability distributions corresponding to the plurality of electric quantity influence factor vectors by the machine learning model, and outputting a prediction result of the operation state of the power supply device in the fourth time period based on the fifth data feature set;

for each second prediction result, comparing the second prediction result with the actual operation state of the power supply equipment in a corresponding fourth time period to obtain a comparison result so as to obtain comparison results corresponding to a plurality of second prediction results respectively;

training the machine learning model based on a plurality of comparison results to obtain the heavy overload early warning model.

7. The heavy overload warning method according to claim 6,

if the operation state in the second prediction result is overload operation, the second prediction result further comprises a first prediction time period when the power supply equipment is in overload operation; the actual operating state further comprises a first real time period during which the power supply apparatus is in overload operation for the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply device in the corresponding fourth time period, and obtaining the comparison result comprises:

comparing the first predicted time period with the first real time period to obtain the comparison result;

and/or the presence of a gas in the gas,

if the operation state in the second prediction result is the heavy-load operation, the second prediction result further comprises a second prediction time period when the power supply equipment is in the heavy-load operation; the actual operating state further comprises a second real time period during which the power sourcing equipment is in heavy-duty operation during the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply device in the corresponding fourth time period, and obtaining the comparison result comprises:

comparing the second predicted time period with the second real time period to obtain the comparison result;

and/or the presence of a gas in the atmosphere,

if the operation state in the second prediction result is normal operation, the second prediction result further comprises a third prediction time period when the power supply equipment is in normal operation; the actual operating state further includes a third real time period during which the power supply apparatus is in normal operation during the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply device in the corresponding fourth time period, and obtaining the comparison result comprises:

comparing the third predicted time period with the third real time period to obtain the comparison result.

8. The heavy overload early warning method according to claim 6, wherein if the operation status in the second prediction result is overload operation, the second prediction result further comprises a first prediction probability that the power supply device is in overload operation, and the actual operation status comprises a first real probability that the power supply device is in overload operation for the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply device in the corresponding fourth time period, and obtaining the comparison result comprises:

comparing the first prediction probability and the first true probability to obtain a comparison result;

and/or the presence of a gas in the gas,

if the operation state in the second prediction result is the heavy-load operation, the second prediction result further includes a second prediction probability that the power supply equipment is in the heavy-load operation, and the actual operation state includes a second real probability that the power supply equipment is in the heavy-load operation in the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply equipment in the corresponding fourth time period, and obtaining the comparison result comprises:

comparing the second prediction probability with the second true probability to obtain a comparison result;

and/or the presence of a gas in the gas,

if the operation state in the second prediction result is normal operation, the second prediction result further includes a third prediction probability that the power supply equipment is in normal operation, and the actual operation state includes a third true probability that the power supply equipment is in heavy-load operation in the fourth time period;

the comparing the second prediction result with the actual operating state of the power supply device in the corresponding fourth time period, and obtaining the comparison result comprises:

and comparing the third prediction probability with the third true probability to obtain the comparison result.

9. A heavy overload early warning device, its characterized in that includes:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first data feature set corresponding to a first time period of a first region and a second data feature set corresponding to a second time period;

the first time period is a time period which is earlier than the current time and takes the current time as the termination time, the second time period is a time period which is later than the current time and takes the current time as the starting time, and the first data feature set and the second data feature set both comprise a plurality of electric quantity influence factor vectors;

the second obtaining module is used for obtaining weights corresponding to the electric quantity influence factor vectors respectively;

the first determining module is used for determining first attributes corresponding to the electric quantity influence factor vectors respectively to obtain a plurality of first attributes, and the first attributes represent attribute information corresponding to the electric quantity influence factor vectors;

a third obtaining module, configured to obtain correlation coefficients corresponding to at least one group of first sets, where each first set includes any two different first attributes of the multiple first attributes, and the two first attributes included in different first sets are not completely the same;

a fourth obtaining module, configured to obtain a joint influence degree corresponding to at least one group of the first sets, where the joint influence degree corresponding to one first set characterizes an electric quantity output change of a power supply device that supplies power to each load located in the first area when two different first attributes included in the first set simultaneously act on the first area;

a fifth obtaining module, configured to obtain, for multiple electric quantity influence factor vectors that belong to a same first attribute, first probability distributions corresponding to the multiple electric quantity influence factor vectors, respectively;

a first input module, configured to input weights corresponding to the multiple electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first sets, joint influence degrees corresponding to at least one group of the first sets, first probability distributions corresponding to the multiple electric quantity influence factor vectors, the first data feature set, and the second data feature set to a pre-constructed overload warning model;

a sixth obtaining module, configured to obtain a first prediction result output by the heavy overload early warning model, where the first prediction result includes an operation state of the power supply device in the first time period, and the operation state includes normal operation and/or overload operation and/or heavy load operation;

the first prediction result is obtained by screening the multiple electric quantity influence factor vectors contained in the first data feature set and the second data feature set to obtain a third data feature set based on weights corresponding to the multiple electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first set, joint influence degrees corresponding to at least one group of the first set, and first probability distribution corresponding to the multiple electric quantity influence factor vectors, respectively, by the heavy overload early warning model, and outputting a prediction result of the operating state of the power supply device in the second time period based on the third data feature set.

10. An electronic device, comprising:

a memory for storing a program;

a processor configured to execute the program, the program specifically configured to:

acquiring a first data feature set corresponding to a first time period of a first area and a second data feature set corresponding to a second time period, wherein the first time period is a time period which is earlier than the current time and takes the current time as a termination time, the second time period is a time period which is later than the current time and takes the current time as an initiation time, and the first data feature set and the second data feature set both comprise a plurality of electric quantity influence factor vectors;

acquiring weights corresponding to the electric quantity influence factor vectors respectively;

determining first attributes corresponding to the electric quantity influence factor vectors respectively to obtain a plurality of first attributes, wherein the first attributes represent attribute information corresponding to the electric quantity influence factor vectors;

obtaining correlation coefficients corresponding to at least one group of first sets, wherein the first sets comprise any two different first attributes in the first attributes, and the two first attributes contained in the different first sets are not completely the same;

acquiring joint influence degrees corresponding to at least one group of the first sets, wherein the joint influence degree corresponding to one first set characterizes the electric quantity output change of power supply equipment for supplying power to each load in the first area when two different first attributes contained in the first set act on the first area simultaneously;

aiming at a plurality of electric quantity influence factor vectors belonging to the same first attribute, acquiring first probability distributions corresponding to the electric quantity influence factor vectors respectively;

inputting weights corresponding to the electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first set, joint influence degrees corresponding to at least one group of the first set, first probability distribution corresponding to the electric quantity influence factor vectors, the first data feature set and the second data feature set into a pre-constructed overload warning model;

obtaining a first prediction result output by the heavy overload early warning model, wherein the first prediction result comprises the operation state of the power supply equipment in the second time period, and the operation state comprises normal operation and/or overload operation and/or heavy load operation;

the first prediction result is obtained by screening the multiple electric quantity influence factor vectors contained in the first data feature set and the second data feature set to obtain a third data feature set based on weights corresponding to the multiple electric quantity influence factor vectors, correlation coefficients corresponding to at least one group of the first set, joint influence degrees corresponding to at least one group of the first set, and first probability distribution corresponding to the multiple electric quantity influence factor vectors, respectively, by the heavy overload early warning model, and outputting a prediction result of the operating state of the power supply device in the second time period based on the third data feature set.

Images