CN115906668A - Power transmission line forest fire trip prediction method, device, equipment and storage medium - Google Patents
Power transmission line forest fire trip prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115906668A CN115906668A CN202211717404.3A CN202211717404A CN115906668A CN 115906668 A CN115906668 A CN 115906668A CN 202211717404 A CN202211717404 A CN 202211717404A CN 115906668 A CN115906668 A CN 115906668A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- characteristic data
- transmission line
- power transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 157
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000003860 storage Methods 0.000 title claims description 16
- 238000012549 training Methods 0.000 claims abstract description 115
- 238000010801 machine learning Methods 0.000 claims abstract description 83
- 230000008569 process Effects 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000012360 testing method Methods 0.000 claims description 25
- 230000000694 effects Effects 0.000 claims description 19
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000002265 prevention Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting mountain fire trip of a power transmission line, which comprises the following steps: extracting fire point characteristic data of a sample site, and performing standardization processing on the fire point characteristic data to determine standard characteristic data; determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process; and performing the iterative training of the model by adopting the characteristic data of the current round on the machine learning model, performing the iterative training of the new round on the machine learning model by adopting the characteristic data of the new round after the iterative training of the model is completed, and taking the machine learning model after the iterative training as the forest fire trip prediction model of the power transmission line. Can effectively assist the staff to carry out mountain fire prevention and cure work, ensured transmission line's safety.
Description
Technical Field
The embodiment of the invention relates to the field of computers, in particular to a method, a device, equipment and a storage medium for predicting mountain fire tripping of a power transmission line.
Background
Most overhead transmission lines pass through mountains and mountains, and partial sections are close to villages and are influenced by human activities to a certain extent. Under the influence of customs such as burning fields, ancestor worship and the like, overhead transmission lines in the areas are easy to have large-scale fire disasters, multiple transmission lines are caused to trip at the same time, even important cross spanning, dense channels and main channels for sending western electricity to the east are influenced in severe cases, and great risks are generated on safe and stable operation of a power grid. When the existing section predicts the mountain fire trip of the power transmission line, workers are often required to participate in the prediction process, influence factors of the mountain fire trip phenomenon of the power transmission line are not comprehensively considered, and the road mountain fire trip risk of the power transmission line is difficult to comprehensively and objectively predict. Therefore, how to improve the accuracy of predicting the mountain fire trip of the power transmission line and save the labor cost for predicting the mountain fire trip risk of the power transmission line is a problem to be solved.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for predicting mountain fire tripping of a power transmission line, which can effectively assist workers to carry out mountain fire prevention and control work while improving the accuracy of predicting mountain fire tripping risks of the power transmission line, and ensure the safety of the power transmission line.
According to one aspect of the invention, a method for predicting mountain fire tripping of a power transmission line is provided, which comprises the following steps:
extracting fire point characteristic data of a sample site, and carrying out standardization processing on the fire point characteristic data to determine standard characteristic data; the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location;
determining the feature weight of standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round of feature data in the subsequent round of iteration process;
performing the iterative training of the model of the current round on the machine learning model by adopting the characteristic data of the current round, performing the iterative training of the new round on the machine learning model by adopting the characteristic data of the new round after the iterative training of the model of the current round is finished, and taking the machine learning model after the iterative training as a forest fire trip prediction model of the power transmission line; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
According to another aspect of the present invention, there is provided a power transmission line mountain fire trip prediction apparatus, comprising:
the standard characteristic data determining module is used for extracting fire point characteristic data of a sample site, standardizing the fire point characteristic data and determining standard characteristic data; the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to a sample place;
the local round characteristic data determining module is used for determining the characteristic weight of standard characteristic data, determining local round characteristic data in the local round iteration process from the standard characteristic data according to the characteristic weight and a preset weight condition, and taking other characteristic data except the local round characteristic data as candidate characteristic data to be selected as new round characteristic data in the subsequent round iteration process;
the model iterative training module is used for carrying out model iterative training on the machine learning model by adopting the current round of characteristic data, carrying out new round of model iterative training on the machine learning model by adopting the new round of characteristic data after the current round of model iterative training is finished, and taking the machine learning model after the iterative training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method for predicting the forest fire trip of the power transmission line according to any embodiment of the invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for predicting forest fire trip of a power transmission line according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme of the embodiment of the invention, the fire point characteristic data of a sample place is extracted and subjected to standardization processing, and standard characteristic data are determined; determining the feature weight of the standard feature data, determining the feature data of the current round in the iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process; performing model iteration training on the machine learning model by using the characteristic data of the current round, performing new round model iteration training on the machine learning model by using the new round characteristic data after the model iteration training of the current round is finished, and taking the machine learning model after the iteration training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line. The problem that when the forest fire tripping phenomenon of the power transmission line is predicted, workers are required to participate in the prediction process, and influence factors of the forest fire tripping phenomenon of the power transmission line are not comprehensively considered is solved. According to the scheme, the forest fire trip prediction model of the power transmission line is constructed, the forest fire trip risk of the power transmission line is predicted through the forest fire trip prediction model of the power transmission line, and labor cost for predicting the forest fire trip risk of the power transmission line is saved. When the machine learning model is subjected to model iterative training to obtain the power transmission line forest fire tripping prediction model, the influence of human activity data, geographic information data and meteorological information data on the power transmission line forest fire tripping phenomenon is fully considered, the model accuracy of the power transmission line forest fire tripping prediction model is improved, workers are effectively assisted to carry out forest fire prevention and control work, and the safety of the power transmission line is guaranteed.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for predicting mountain fire trip of a power transmission line according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for predicting mountain fire trip of a power transmission line according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for predicting mountain fire trip of a power transmission line according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a power transmission line forest fire trip prediction device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "candidate" and "target" and the like in the description and claims of the present invention and the above drawings are used for distinguishing similar objects and are not necessarily used for describing a particular order or sequence. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a method for predicting a mountain fire trip of a power transmission line according to an embodiment of the present invention, which is applicable to a case of predicting a mountain fire trip phenomenon of the power transmission line, and is particularly applicable to performing model iterative training on a machine learning model according to fire point characteristic data, and predicting a mountain fire trip risk of the power transmission line according to the mountain fire trip prediction model by using the machine learning model after iterative training as the power transmission line mountain fire trip prediction model. The method can be executed by a power transmission line forest fire trip prediction device, the power transmission line forest fire trip prediction device can be realized in a hardware and/or software mode, and the power transmission line forest fire trip prediction device can be configured in electronic equipment. As shown in fig. 1, the method includes:
and S110, extracting fire point characteristic data of the sample site, standardizing the fire point characteristic data, and determining standard characteristic data.
The fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location. The sample sites comprise fire point samples in which the mountain fire tripping condition of the power transmission line occurs and fireless samples in which the mountain fire tripping condition of the power transmission line does not occur.
The fire sample refers to the occurrence place of the historical power transmission line mountain fire trip phenomenon collected in advance. The fireless sample refers to a place where a mountain fire trip phenomenon may occur, but the mountain fire trip phenomenon has not occurred. The human activity data comprises the distance from the sample location to the railway, the distance from the sample location to the highway, the distance from the sample location to the first-level highway, the distance from the sample location to the residential site, the population density of the area where the sample location is located and the national production total value. The geographic information data comprises vegetation characteristics, topographic and geomorphic characteristics and historical fire characteristics. Vegetation characteristics may include vegetation type risk rating and normalized vegetation index; the topographical features may include longitude, latitude, elevation, slope, and heading of the sample location; the historical fire characteristics may include a fire density, a combustible risk level, and a mountain fire risk level for the sample site.
Generally, the farther away from railways, roads and residences, the weaker the human activities and the higher the vegetation coverage, once a fire occurs, the fire source is difficult to find in an early stage, and the fire is easy to spread, so that a large-area mountain fire disaster is caused. The fire difficulty of different vegetation types is different, and mountain fire disasters are frequently generated in coniferous forests and coniferous and broad mixed forest areas with high vegetation coverage in the field. The landform not only affects the vegetation type, but also affects the flame burning and spreading speed, and the related characteristics mainly comprise longitude, latitude, elevation, gradient and slope. Not only do elevations introduce differences in temperature and humidity, but human activity also decreases as elevation increases. The slope is bigger, and the surface runoff is faster, can directly slow down mountain fire spreading speed. The slope direction can influence the radiation quantity of the earth surface, thereby influencing the growth of vegetation and further influencing the generation and the expansion of mountain fire.
Specifically, a sample place is randomly extracted from the occurrence places of the historical mountain fire trip phenomenon of the power transmission line, and human activity data, geographic information data and meteorological information data corresponding to the sample place are obtained. And taking the human activity data, the geographic information data and the meteorological information data corresponding to the sample location as fire point characteristic data. Due to the fact that dimensions of different fire point characteristic data are different, in order to guarantee reliability of the power transmission line forest fire tripping prediction model, the fire point characteristic data need to be processed in a standardized mode. For example, the fire point feature data may be normalized by a normalization method based on the mean and standard deviation of the raw data, and the normalized fire point feature data may be used as the standard feature data.
And S120, determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking the feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process.
The feature weight refers to a data contribution degree of the standard feature data. The characteristic data of the current wheel refers to model training data of the current wheel for performing model iterative training on the machine learning model. The new round of feature data refers to model training data for performing a new round of model iterative training on the machine learning model.
Specifically, the feature weight of the standard feature data can be determined by using a ReliefF algorithm. And determining standard characteristic data corresponding to the characteristic weight meeting the preset weight condition as the characteristic data of the current round in the current round of iteration process. Meanwhile, other feature data except the feature data of the current round are used as candidate feature data and used for selecting new round feature data in the subsequent round of iteration process.
S130, performing model iteration training on the machine learning model by using the current round of feature data, performing new round of model iteration training on the machine learning model by using the new round of feature data after the current round of model iteration training is completed, and taking the machine learning model after the iteration training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting the forest fire trip risk of the power transmission line.
Among other things, the machine learning model may be a machine learning model based on the Catboost learning framework. The Catboost learning framework may be implemented based on the GBDT algorithm. On the basis of GBDT, catboost improves the nominal attribute processing; and a sequencing promotion strategy is provided to optimize the prediction deviation, so that model overfitting can be effectively reduced. In the Catboost algorithm, the traditional gradient estimation is replaced by a sequencing promotion strategy, so that the gradient estimation deviation can be effectively reduced, and the generalization capability of the model is improved.
Specifically, if the feature data of the current round is model training data for performing first model iterative computation on the machine learning model, it may be determined that the standard feature data corresponding to the feature weights with the largest four values are the feature data of the current round in the iterative process of the current round, then the feature data of the current round is used to perform the iterative computation on the machine learning model of the current round, and after the iterative training of the current round is completed, the model accuracy of the machine learning model after the iterative training of the current round is determined. And if the model accuracy is smaller than a preset threshold value, selecting at least one candidate feature data to be added into the feature data of the current round, taking the feature data of the current round added with the candidate feature data as new round feature data, performing new round iterative training on the machine learning model by adopting the new round feature data, and determining the model accuracy of the machine learning model after the new round iterative training. Stopping model iterative computation of the machine learning model until the model accuracy is greater than or equal to a preset threshold value, and taking the machine learning model after iterative training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
Illustratively, model iterative training can be performed on the machine learning model through the following sub-steps to obtain a power transmission line mountain fire trip prediction model:
and S1301, performing model iteration training on the machine learning model by adopting the model iteration training, and determining target feature data from the candidate feature data according to the feature weight after the model iteration training is completed.
Specifically, the iterative calculation of the model is carried out on the machine learning model by adopting the characteristic data of the current round, and after the iterative training of the model of the current round is completed, the model accuracy of the machine learning model after the iterative training of the model of the current round is determined. And if the accuracy of the model does not meet the preset accuracy condition, selecting the candidate characteristic data corresponding to the characteristic weight with the maximum value as the target characteristic data.
And S1302, adding the target characteristic data into the characteristic data of the current round, determining the characteristic data of the new round, and performing new round model iterative training on the machine learning model by adopting the characteristic data of the new round.
Specifically, the target feature data is added to the feature data of the current round, and the feature data of the current round to which the target feature data is added is used as the feature data of the new round. And performing new round model iterative training on the machine learning model by using the new round characteristic data, and determining the model accuracy of the machine learning model after the new round model iterative training is completed.
And S1303, stopping model iterative training when the accuracy of the model reaches the accuracy peak value, and taking the machine learning model after iterative training as a power transmission line forest fire trip prediction model.
Specifically, when the machine learning model is subjected to model iterative training, the model accuracy of the machine learning model after each model iterative training is tested, and a model accuracy change curve of the machine learning model in the model iterative training process is drawn according to a test result. And determining whether the model accuracy of the machine learning model reaches an accuracy peak value or not according to the model accuracy change curve. And if the accuracy of the model reaches the accuracy peak value, stopping the iterative training of the model, and taking the machine learning model after the iterative training as a power transmission line forest fire trip prediction model.
After the iterative training of the model of the power transmission line is completed, the target characteristic data is determined from the candidate characteristic data according to the characteristic weight, the target characteristic data is added into the iterative training of the model, the new characteristic data for performing a new iterative training on the machine learning model is determined, the optimal training subset for performing the model training on the machine learning model can be obtained in the iterative training process, model training on the machine learning model is not required to be performed by adopting all standard characteristic data, and the model training efficiency of the machine learning model is improved while the model accuracy of the power transmission line forest fire trip prediction model is improved.
According to the technical scheme provided by the embodiment, the fire point characteristic data of a sample site is extracted, the fire point characteristic data is subjected to standardization processing, and standard characteristic data is determined; determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process; performing the iterative training of the model by adopting the characteristic data of the current round on the machine learning model, performing the iterative training of the new round on the machine learning model by adopting the characteristic data of the new round after the iterative training of the model is completed, and taking the machine learning model after the iterative training as a forest fire trip prediction model of the power transmission line; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line. The problem that when the forest fire tripping phenomenon of the power transmission line is predicted, workers are required to participate in the prediction process, and influence factors of the forest fire tripping phenomenon of the power transmission line are not comprehensively considered is solved. According to the scheme, the forest fire trip risk of the power transmission line is predicted through the power transmission line forest fire trip prediction model by constructing the power transmission line forest fire trip prediction model, and labor cost for predicting the forest fire trip risk of the power transmission line is saved. When the machine learning model is subjected to model iterative training to obtain the power transmission line forest fire tripping prediction model, the influence of human activity data, geographic information data and meteorological information data on the power transmission line forest fire tripping phenomenon is fully considered, the model accuracy of the power transmission line forest fire tripping prediction model is improved, workers are effectively assisted to carry out forest fire prevention and control work, and the safety of the power transmission line is guaranteed.
Example two
Fig. 2 is a flowchart of a power transmission line forest fire trip prediction method according to a second embodiment of the present invention, which is optimized based on the second embodiment, and provides a preferred implementation of model evaluation on a power transmission line forest fire trip prediction model according to a prediction accuracy, a model accuracy, and a model recall rate. Specifically, as shown in fig. 2, the method includes:
s210, extracting fire point characteristic data of a sample site, and performing standardization processing on the fire point characteristic data to determine standard characteristic data;
the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location.
S220, determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking the feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process.
S230, performing model iterative training on the machine learning model by using the current round of feature data, performing new round of model iterative training on the machine learning model by using the new round of feature data after the current round of model iterative training is finished, and taking the machine learning model after the iterative training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
S240, testing the power transmission line forest fire trip prediction model by adopting the test sample and the power transmission line forest fire trip prediction model, and determining a confusion matrix according to the test sample and the test result.
The test samples also comprise fire point samples under the condition of mountain fire tripping of the power transmission line and fireless samples under the condition of mountain fire tripping of the power transmission line.
Specifically, human activity data, geographic information data and meteorological information data corresponding to the test sample are extracted as test characteristic data. And determining a confusion matrix according to the model output result of the power transmission line mountain fire trip prediction model and the actual power transmission line mountain fire trip phenomenon occurrence condition corresponding to the test sample. For example, the confusion matrix is shown in table 1:
TABLE 1 confusion matrix
Wherein TP is a fire point sample in the test sample with correct prediction result; TN is a fire-free sample in the test samples with correct prediction results; FP is a fire point sample in a test sample with a wrong prediction result; FN are the fireless samples of the test samples with erroneous prediction results.
And S250, determining the prediction accuracy, the model accuracy and the model recall rate of the power transmission line forest fire trip prediction model according to the confusion matrix.
Specifically, a calculation formula of the prediction accuracy of the power transmission line forest fire trip prediction model is shown as a formula (1):
wherein, accuracy is the prediction accuracy.
The calculation formula of the model accuracy of the power transmission line forest fire trip prediction model is shown as the formula (2):
where precision is the model accuracy.
The calculation formula of the model recall rate of the power transmission line forest fire tripping prediction model is shown as formula (3):
wherein recall is the model recall rate.
And S260, performing model evaluation on the power transmission line forest fire trip prediction model according to the prediction accuracy, the model accuracy and the model recall rate.
Specifically, if the prediction accuracy is greater than a preset first accuracy threshold, the model accuracy is greater than a preset second accuracy threshold, and the model recall rate is greater than a preset recall rate threshold, the evaluation result of the model evaluation on the power transmission line forest fire trip prediction model is qualified; otherwise, determining that the evaluation result of the model evaluation on the power transmission line forest fire trip prediction model is unqualified, and performing iterative training on the machine learning model again to determine the power transmission line forest fire trip prediction model.
According to the technical scheme, after the power transmission line forest fire tripping prediction model is determined, a confusion matrix is adopted, the results of predicting whether forest fire occurs and the results of actually predicting whether forest fire occurs are visually compared, the prediction accuracy, the model accuracy and the model recall rate of the power transmission line forest fire tripping prediction model are calculated according to the confusion matrix, and the power transmission line forest fire tripping prediction model is evaluated according to the prediction accuracy, the model accuracy and the model recall rate. According to the scheme, the evaluation method of the optimized power transmission line forest fire trip prediction model is provided, quantitative evaluation of the power transmission line forest fire trip prediction model can be achieved, and a comprehensive model evaluation result is obtained.
EXAMPLE III
Fig. 3 is a flowchart of a method for predicting mountain fire trip of a power transmission line according to a third embodiment of the present invention, and this embodiment is optimized based on the foregoing embodiment, and provides a preferred implementation manner of extracting fire characteristic data of a sample location, and performing normalization processing on the fire characteristic data to determine standard characteristic data. Specifically, as shown in fig. 3, the method includes:
s310, extracting fire point characteristic data of a sample site, and constructing a feature set to be processed according to the fire point characteristic data;
the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location.
Specifically, after the sample locations are randomly selected, the fire point feature data of the sample locations are extracted from the monitoring data of the satellite on the sample locations, the fire point feature data of each sample location are recorded in a table, and the table in which the fire point feature data of each sample location are recorded is used as the feature set to be processed.
And S320, processing the abnormal values and the missing values in the feature set to be processed, and determining the target feature set.
Specifically, the abnormal values and the missing values in the feature set to be processed may be deleted, and the feature set to be processed after the abnormal values and the missing values are deleted is used as the target feature set.
For example, the method for processing the abnormal value and the missing value in the feature set to be processed may be: drawing a box type graph according to the feature set to be processed, determining an abnormal value of fire point feature data in the feature set to be processed according to the box type graph, and deleting the abnormal value; and positioning the missing values in the feature set to be processed, calculating the data mean value of the column family corresponding to the missing values in the feature set to be processed, and supplementing the missing values by adopting the data mean value.
It can be understood that the abnormal values of the fire point feature data in the feature set to be processed are determined according to the box type graph, the abnormal values in the feature set to be processed are deleted, meanwhile, the missing values in the feature set to be processed are supplemented by adopting the data mean value, and the reliability of the fire point feature data in the feature set to be processed can be improved.
S330, carrying out standardization processing on the characteristic data to be processed in the target characteristic set, and determining standard characteristic data.
The feature data to be processed refers to all data recorded in the target feature set.
Specifically, the feature data to be processed may be normalized by a normalization method based on the mean and standard deviation of the raw data, and the normalized feature data to be processed may be used as the standard feature data.
And S340, determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking the feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process.
S350, performing the iterative training of the model of the machine learning model by adopting the characteristic data of the current round, performing the iterative training of the model of the new round by adopting the characteristic data of the new round after the iterative training of the model of the current round is finished, and taking the machine learning model after the iterative training as a forest fire trip prediction model of the power transmission line; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
According to the technical scheme of the embodiment, when the standard characteristic data is determined, the characteristic set to be processed is constructed according to the fire point characteristic data, then the abnormal value and the missing value in the characteristic set to be processed are processed, the target characteristic set is determined, the characteristic data to be processed in the target characteristic set is subjected to standardization processing, and the standard characteristic data is determined. By the aid of the scheme, adverse effects of abnormal data and missing data in the fire point characteristic data on a subsequent training machine learning model can be avoided, and reliability and integrity of standard characteristic data are guaranteed.
Example four
Fig. 4 is a schematic structural diagram of a power transmission line forest fire trip prediction device according to a fourth embodiment of the present invention. The embodiment can be applied to the condition of predicting the mountain fire tripping phenomenon of the power transmission line. As shown in fig. 4, the power transmission line mountain fire trip prediction device includes: a standard feature data determination module 410, a present round feature data determination module 420, and a model iteration training module 430.
The standard characteristic data determining module 410 is configured to extract fire characteristic data of a sample location, and perform standardization processing on the fire characteristic data to determine standard characteristic data; the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location;
a feature data determination module 420 in the current round, configured to determine a feature weight of the standard feature data, determine, according to the feature weight and a preset weight condition, feature data in the current round in an iteration process from the standard feature data, and use feature data other than the feature data in the current round as candidate feature data for selecting new round feature data in a subsequent round of iteration process;
the model iterative training module 430 is used for performing the current round of model iterative training on the machine learning model by using the current round of feature data, performing the new round of model iterative training on the machine learning model by using the new round of feature data after the current round of model iterative training is completed, and taking the machine learning model after the iterative training as a power transmission line mountain fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
According to the technical scheme provided by the embodiment, the fire point characteristic data of a sample site is extracted, the fire point characteristic data is subjected to standardization processing, and standard characteristic data is determined; determining the feature weight of the standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round feature data in the subsequent round of iteration process; performing the iterative training of the model by adopting the characteristic data of the current round on the machine learning model, performing the iterative training of the new round on the machine learning model by adopting the characteristic data of the new round after the iterative training of the model is completed, and taking the machine learning model after the iterative training as a forest fire trip prediction model of the power transmission line; the power transmission line forest fire trip prediction model is used for predicting the forest fire trip risk of the power transmission line. The problem that when the forest fire tripping phenomenon of the power transmission line is predicted, workers are required to participate in the prediction process, and influence factors of the forest fire tripping phenomenon of the power transmission line are not comprehensively considered is solved. According to the scheme, the forest fire trip risk of the power transmission line is predicted through the power transmission line forest fire trip prediction model by constructing the power transmission line forest fire trip prediction model, and labor cost for predicting the forest fire trip risk of the power transmission line is saved. When the machine learning model is subjected to model iterative training to obtain the power transmission line forest fire tripping prediction model, the influence of human activity data, geographic information data and meteorological information data on the power transmission line forest fire tripping phenomenon is fully considered, the model accuracy of the power transmission line forest fire tripping prediction model is improved, workers are effectively assisted to carry out forest fire prevention and control work, and the safety of the power transmission line is guaranteed.
Illustratively, the model iterative training module 430 includes:
the target characteristic data determining unit is used for performing model iterative training on the machine learning model by adopting the current round of characteristic data, and determining target characteristic data from the candidate characteristic data according to the characteristic weight after the current round of model iterative training is finished;
the new round characteristic data determining unit is used for adding the target characteristic data into the current round characteristic data, determining new round characteristic data and performing new round model iterative training on the machine learning model by adopting the new round characteristic data;
and the prediction model determining unit is used for stopping model iterative training when the accuracy of the model reaches the accuracy peak value, and taking the machine learning model after iterative training as the power transmission line forest fire trip prediction model.
Exemplarily, the power transmission line mountain fire trip prediction device further includes:
the confusion matrix determining module is used for testing the power transmission line forest fire trip predicting model by adopting the test sample and the power transmission line forest fire trip predicting model and determining a confusion matrix according to the test sample and the test result;
the prediction accuracy determining module is used for determining the prediction accuracy, the model accuracy and the model recall rate of the power transmission line forest fire trip prediction model according to the confusion matrix;
and the model evaluation module is used for carrying out model evaluation on the power transmission line forest fire trip prediction model according to the prediction accuracy, the model accuracy and the model recall rate.
Illustratively, the standard feature data determination module includes:
the fire point characteristic data extraction unit is used for extracting fire point characteristic data of a sample site and constructing a feature set to be processed according to the fire point characteristic data;
the target feature set determining unit is used for processing the abnormal values and the missing values in the feature set to be processed and determining a target feature set;
and the standard characteristic data determining unit is used for carrying out standardization processing on the characteristic data to be processed in the target characteristic set and determining standard characteristic data.
Illustratively, the target feature set determining unit is specifically configured to:
drawing a box type graph according to the feature set to be processed, determining an abnormal value of fire point feature data in the feature set to be processed according to the box type graph, and deleting the abnormal value;
and positioning the missing values in the feature set to be processed, calculating the data mean value of the column group corresponding to the missing values in the feature set to be processed, and supplementing the missing values by adopting the data mean value.
The power transmission line forest fire trip prediction device provided by the embodiment can be applied to the power transmission line forest fire trip prediction method provided by any embodiment, and has corresponding functions and beneficial effects.
EXAMPLE five
FIG. 5 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 11 performs the various methods and processes described above, such as the transmission line mountain fire trip prediction method.
In some embodiments, the power line mountain fire trip prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the memory unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the power transmission line mountain fire trip prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the line mountain fire trip prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for predicting mountain fire trip of a power transmission line is characterized by comprising the following steps:
extracting fire point characteristic data of a sample site, and carrying out standardization processing on the fire point characteristic data to determine standard characteristic data; the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location;
determining the feature weight of standard feature data, determining the feature data of the current round in the current round of iteration process from the standard feature data according to the feature weight and a preset weight condition, and taking other feature data except the feature data of the current round as candidate feature data for selecting new round of feature data in the subsequent round of iteration process;
performing model iteration training on the machine learning model by using the characteristic data of the current round, performing new model iteration training on the machine learning model by using the new characteristic data of the current round after the model iteration training of the current round is finished, and taking the machine learning model after the iteration training as a power transmission line mountain fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
2. The method of claim 1, wherein the performing of the iterative training of the current round model on the machine learning model by using the current round of feature data, and performing the iterative training of the new round model on the machine learning model by using the new round of feature data after the iterative training of the current round model is completed, and the performing of the iterative training on the machine learning model as the power transmission line mountain fire trip prediction model comprises:
performing model iteration training on a machine learning model by using the feature data of the current round, and determining target feature data from the candidate feature data according to the feature weight after the model iteration training of the current round is completed;
adding the target characteristic data into the characteristic data of the current round, determining new round characteristic data, and performing new round model iterative training on the machine learning model by adopting the new round characteristic data;
and when the accuracy of the model reaches the accuracy peak value, stopping the iterative training of the model, and taking the machine learning model after the iterative training as a power transmission line forest fire trip prediction model.
3. The method of claim 1, further comprising:
testing the power transmission line forest fire trip prediction model by adopting a test sample and the power transmission line forest fire trip prediction model, and determining a confusion matrix according to the test sample and a test result;
determining the prediction accuracy, the model accuracy and the model recall rate of the power transmission line forest fire trip prediction model according to the confusion matrix;
and performing model evaluation on the power transmission line forest fire trip prediction model according to the prediction accuracy, the model accuracy and the model recall rate.
4. The method of claim 1, wherein extracting fire signature data for a sample site and normalizing the fire signature data to determine standard signature data comprises:
extracting fire point characteristic data of a sample site, and constructing a feature set to be processed according to the fire point characteristic data;
processing the abnormal values and the missing values in the feature set to be processed to determine a target feature set;
and carrying out standardization processing on the characteristic data to be processed in the target characteristic set to determine standard characteristic data.
5. The method according to claim 4, wherein processing the outliers and the missing values in the feature set to be processed to determine a target feature set comprises:
drawing a box type graph according to the feature set to be processed, determining an abnormal value of fire point feature data in the feature set to be processed according to the box type graph, and deleting the abnormal value;
and positioning the missing values in the feature set to be processed, calculating the data mean value of the column group corresponding to the missing values in the feature set to be processed, and supplementing the missing values by adopting the data mean value.
6. A power transmission line forest fire trip prediction device is characterized by comprising:
the standard characteristic data determining module is used for extracting fire point characteristic data of a sample site, carrying out standardization processing on the fire point characteristic data and determining standard characteristic data; the fire point characteristic data comprises human activity data, geographic information data and meteorological information data corresponding to the sample location;
the local round characteristic data determining module is used for determining the characteristic weight of standard characteristic data, determining local round characteristic data in the local round iteration process from the standard characteristic data according to the characteristic weight and a preset weight condition, and taking other characteristic data except the local round characteristic data as candidate characteristic data to be selected as new round characteristic data in the subsequent round iteration process;
the model iterative training module is used for carrying out model iterative training on the machine learning model by adopting the current round of characteristic data, carrying out new round of model iterative training on the machine learning model by adopting the new round of characteristic data after the current round of model iterative training is finished, and taking the machine learning model after the iterative training as a power transmission line forest fire trip prediction model; the power transmission line forest fire trip prediction model is used for predicting forest fire trip risks of the power transmission line.
7. The apparatus of claim 6, wherein the model iterative training module comprises:
the target characteristic data determining unit is used for performing model iterative training on the machine learning model by adopting the model iterative training unit, and determining target characteristic data from the candidate characteristic data according to the characteristic weight after the model iterative training is completed;
the new round characteristic data determining unit is used for adding the target characteristic data into the current round characteristic data, determining new round characteristic data and performing new round model iterative training on the machine learning model by adopting the new round characteristic data;
and the prediction model determining unit is used for stopping model iterative training when the model accuracy reaches the accuracy peak value, and taking the machine learning model after iterative training as the power transmission line forest fire trip prediction model.
8. The apparatus of claim 6, further comprising:
the confusion matrix determining module is used for testing the power transmission line forest fire trip predicting model by adopting a test sample and the power transmission line forest fire trip predicting model and determining a confusion matrix according to the test sample and a test result;
the prediction accuracy determining module is used for determining the prediction accuracy, the model accuracy and the model recall rate of the power transmission line forest fire tripping prediction model according to the confusion matrix;
and the model evaluation module is used for carrying out model evaluation on the power transmission line forest fire trip prediction model according to the prediction accuracy, the model accuracy and the model recall rate.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the method of predicting a power transmission line wildfire trip according to any one of claims 1 to 5 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211717404.3A CN115906668A (en) | 2022-12-29 | 2022-12-29 | Power transmission line forest fire trip prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211717404.3A CN115906668A (en) | 2022-12-29 | 2022-12-29 | Power transmission line forest fire trip prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115906668A true CN115906668A (en) | 2023-04-04 |
Family
ID=86482400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211717404.3A Pending CN115906668A (en) | 2022-12-29 | 2022-12-29 | Power transmission line forest fire trip prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115906668A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197680A (en) * | 2023-08-20 | 2023-12-08 | 国网湖北省电力有限公司神农架供电公司 | Power transmission and distribution forest fire monitoring method and monitoring device based on multi-source satellite data |
-
2022
- 2022-12-29 CN CN202211717404.3A patent/CN115906668A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197680A (en) * | 2023-08-20 | 2023-12-08 | 国网湖北省电力有限公司神农架供电公司 | Power transmission and distribution forest fire monitoring method and monitoring device based on multi-source satellite data |
| CN117197680B (en) * | 2023-08-20 | 2024-05-14 | 国网湖北省电力有限公司神农架供电公司 | Power transmission and distribution forest fire monitoring method and monitoring device based on multi-source satellite data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8880962B2 (en) | Maintenance planning and failure prediction from data observed within a time window | |
| US20210175715A1 (en) | System and method for congestion forecasting in electrical networks | |
| Barone et al. | Optimization of life-cycle maintenance of deteriorating bridges with respect to expected annual system failure rate and expected cumulative cost | |
| Wang et al. | A novel model of the ideal point method coupled with objective and subjective weighting method for evaluation of surrounding rock stability | |
| CN115116195B (en) | Foundation pit monitoring method and device based on artificial intelligence | |
| CN115906668A (en) | Power transmission line forest fire trip prediction method, device, equipment and storage medium | |
| Fogliatto et al. | Power distribution system interruption duration model using reliability analysis regression | |
| CN115792505B (en) | Rail transit power supply management method and system | |
| Li et al. | Prediction of power outage quantity of distribution network users under typhoon disaster based on random forest and important variables | |
| CN118171035B (en) | Method and device for early warning of people stream heating power, electronic equipment and storage medium | |
| CN117370914A (en) | Power grid attack detection model test method, device, equipment and storage medium | |
| CN117034149A (en) | Fault processing strategy determining method and device, electronic equipment and storage medium | |
| CN115760074A (en) | Power equipment operation and maintenance method and device, computer equipment and storage medium | |
| CN115509255A (en) | Substation patrol unmanned aerial vehicle airline risk management and control method, device, equipment and storage medium | |
| CN115774648A (en) | Abnormity positioning method, device, equipment and storage medium | |
| CN115453661A (en) | Weather forecasting method, weather forecasting device, weather forecasting equipment and storage medium | |
| Bani-Mustafa et al. | A framework for multi-hazards risk aggregation considering risk model maturity levels | |
| CN115392715A (en) | Power utilization data risk assessment method, device, equipment and storage medium | |
| Liu et al. | Global maximum flow based time-domain simulation method for evaluating power system resilience | |
| CN115907226A (en) | Characteristic data processing method, device, equipment and storage medium | |
| Sanz et al. | Statistical estimation of power system vulnerability | |
| Ghosh et al. | Functional uncertainty analysis of phasor measurement unit using fuzzy hidden markov model | |
| CN116186549B (en) | Model training method, device, equipment and medium | |
| CN116911477A (en) | Method, device, equipment and medium for managing unmanned aerial vehicle route of transformer substation | |
| Sohrabi | Data-Driven Approaches for Enhancing Power Grid Reliability |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |