CN116822803B - Carbon emission data graph construction method, device and equipment based on intelligent algorithm - Google Patents
Carbon emission data graph construction method, device and equipment based on intelligent algorithm Download PDFInfo
- Publication number
- CN116822803B CN116822803B CN202311091979.3A CN202311091979A CN116822803B CN 116822803 B CN116822803 B CN 116822803B CN 202311091979 A CN202311091979 A CN 202311091979A CN 116822803 B CN116822803 B CN 116822803B
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- time
- data
- prediction
- series
- 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.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 483
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 483
- 238000010276 construction Methods 0.000 title claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000002159 abnormal effect Effects 0.000 claims description 60
- 238000012937 correction Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims 1
- 238000003379 elimination reaction Methods 0.000 claims 1
- 238000012549 training Methods 0.000 description 25
- 239000011159 matrix material Substances 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 108010014173 Factor X Proteins 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The embodiment of the invention discloses a carbon emission data graph construction method, device and equipment based on an intelligent algorithm. One embodiment of the method comprises the following steps: extracting time-series carbon emission data corresponding to a last layer from layered time-series carbon emission data corresponding to a target carbon emission node as last-layer time-series carbon emission data; time-series carbon emission data of each layer which is different from the last time-series carbon emission data in the layered time-series carbon emission data; acquiring a carbon emission prediction result set corresponding to a front-layer time sequence carbon emission data set; generating a carbon emission prediction result according to the final-layer time sequence carbon emission data and the carbon emission prediction model; correcting the carbon emission prediction result according to the carbon emission prediction constraint information to obtain a carbon emission prediction output result; and constructing a carbon emission trend data graph according to the carbon emission prediction output result. This embodiment improves the accuracy of the stratified time-series of predicted carbon emissions.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a carbon emission data graph construction method, device and equipment based on an intelligent algorithm.
Background
Layered time series prediction is a technology in the field of time series prediction, and layered time series refers to a plurality of time series which can be related through a certain hierarchical relationship, and time series of different levels can be decomposed or aggregated according to a certain attribute (such as carbon emission node, carbon emission level and the like) to realize interconversion. Currently, in conducting stratified time-series prediction of carbon emissions, the following methods are generally adopted: the time series of each hierarchy is predicted in a single time sequence without considering the hierarchy relationship.
However, the following technical problems generally exist in the above manner:
firstly, the prediction results of different levels cannot automatically meet consistency, cannot be suitable for collaborative decision-making processes of all levels, so that the accuracy of a layering time sequence of the predicted carbon emission is poor, and partial carbon emission points are difficult to shut down in time, so that carbon emission exceeds standard;
secondly, the abnormal data in each carbon emission data are not analyzed in advance, so that the analysis time of the carbon data is longer;
Thirdly, each carbon emission data is detected manually, the efficiency is low, and abnormal data are difficult to detect in time.
The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.
Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a carbon emission data map construction method, apparatus, electronic device, and computer readable medium based on intelligent algorithms to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a carbon emission data map construction method based on an intelligent algorithm, the method comprising: extracting time-series carbon emission data corresponding to a last layer from layered time-series carbon emission data corresponding to a target carbon emission node as last-layer time-series carbon emission data; determining time-series carbon emission data of each layer different from the last-layer time-series carbon emission data in the layered time-series carbon emission data as a previous-layer time-series carbon emission data set; acquiring a carbon emission prediction result set of the front-layer time series carbon emission data set corresponding to a preset future time period as carbon emission prediction constraint information, wherein each carbon emission prediction result in the carbon emission prediction result set meets a consistency condition; generating a carbon emission prediction result corresponding to the preset future time period according to the last-layer time sequence carbon emission data and the carbon emission prediction model; correcting the carbon emission prediction result according to the carbon emission prediction constraint information to obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model; and constructing a carbon emission trend data graph according to the carbon emission prediction output result, and sending the carbon emission trend data graph to an associated display terminal for display.
In a second aspect, some embodiments of the present disclosure provide a carbon emission data map construction apparatus based on an intelligent algorithm, the apparatus comprising: an extraction unit configured to extract time-series carbon emission data corresponding to an end layer from layered time-series carbon emission data corresponding to a target carbon emission node as end layer time-series carbon emission data; a determining unit configured to determine, as a preceding layer time-series carbon emission data set, time-series carbon emission data of each layer that is different from the last layer time-series carbon emission data among the layered time-series carbon emission data; an acquisition unit configured to acquire a carbon emission amount prediction result set of the preceding time-series carbon emission data set corresponding to a preset future period as carbon emission amount prediction constraint information, wherein each of the carbon emission amount prediction results in the carbon emission amount prediction result set satisfies a consistency condition; a generation unit configured to generate a carbon emission prediction result corresponding to the preset future period of time based on the last-layer time-series carbon emission data and a carbon emission prediction model; a correction unit configured to perform correction processing on the carbon emission prediction result according to the carbon emission prediction constraint information, and obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model; and a construction unit configured to construct a carbon emission trend data map according to the carbon emission prediction output result, and send the carbon emission trend data map to an associated display terminal for display.
In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.
The above embodiments of the present disclosure have the following advantageous effects: by the intelligent algorithm-based carbon emission data graph construction method, accuracy of a layered time sequence of predicted carbon emission is improved, so that carbon emission points with partial carbon emission exceeding standard can be shut down in time to avoid carbon emission exceeding standard. Specifically, the reason why the carbon emissions are out of standard is that: the prediction results of different levels cannot automatically meet consistency, cannot be suitable for the collaborative decision process of each level, and the accuracy of the layering time sequence of the predicted carbon emission is poor, so that the partial carbon emission points are difficult to shut down in time. Based on this, the carbon emission data map construction method based on the intelligent algorithm of some embodiments of the present disclosure first extracts time-series carbon emission data corresponding to the last layer from layered time-series carbon emission data corresponding to the target carbon emission node as the last-layer time-series carbon emission data. Thus, the extracted last layer time series data may characterize the last layer time series data in the original layered time series data. Next, the time-series carbon emission data of each layer, which is different from the last-layer time-series carbon emission data, of the layered time-series carbon emission data is determined as a preceding-layer time-series carbon emission data set. Thus, time-series data of each layer preceding the last layer can be extracted. Next, a carbon emission prediction result set of the preceding time-series carbon emission data set corresponding to a preset future time period is acquired as carbon emission prediction constraint information. Wherein each of the carbon emission prediction results in the set of carbon emission prediction results satisfies a consistency condition. Thus, the obtained carbon emission amount prediction result set can characterize the externally input prediction result of the time series data of each layer before the last layer, so that the externally input prediction result of the time series of the higher layer can be used as the consistency constraint of the time series of the lower layer. And then, generating a carbon emission prediction result corresponding to the preset future time period according to the last-layer time series carbon emission data and the carbon emission prediction model. Thus, the original prediction result of the time-series data of the last layer can be generated by the carbon emission amount prediction model. And then, according to the carbon emission prediction constraint information, carrying out correction processing on the carbon emission prediction result to obtain a corrected carbon emission prediction result serving as a carbon emission prediction output result of the carbon emission prediction model. Thus, the original predicted result of the time-series data of the last layer can be corrected with the externally input carbon emission prediction result set as a constraint, and the corrected result can be used as the output result of the carbon emission generation model. And finally, constructing a carbon emission trend data graph according to the carbon emission prediction output result, and sending the carbon emission trend data graph to an associated display terminal for display. Thus, it is possible to realize a consistency constraint of the time series of the lower layer by using the prediction result of the time series of the higher layer inputted from the outside. And furthermore, the time series data of the carbon emission of different levels can meet the consistency, so that the method is suitable for the collaborative decision process of each level, and the accuracy of the layered time series data of the predicted carbon emission is improved. Therefore, the carbon emission point with partial carbon emission exceeding standard can be stopped in time, so that the carbon emission exceeding standard is avoided.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow chart of some embodiments of a smart algorithm-based carbon emission data map construction method according to the present disclosure;
FIG. 2 is a schematic diagram of a hierarchical time series carbon emission data comprising 2 levels according to some embodiments of the smart algorithm-based carbon emission data map construction method of the present disclosure;
FIG. 3 is a flow chart of some embodiments of a smart algorithm-based carbon emission data map construction apparatus according to the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 is a flow chart of some embodiments of a smart algorithm-based carbon emission data map construction method according to the present disclosure. A flow 100 of some embodiments of a smart algorithm-based carbon emission data map construction method according to the present disclosure is shown. The carbon emission data graph construction method based on the intelligent algorithm comprises the following steps:
Step 101, extracting time-series carbon emission data corresponding to the last layer from the layered time-series carbon emission data corresponding to the target carbon emission node as the last-layer time-series carbon emission data.
In some embodiments, an execution body (e.g., a computing device) of the smart algorithm-based carbon emission data map construction method may extract time-series carbon emission data corresponding to an end layer from layered time-series carbon emission data corresponding to a target carbon emission node as end layer time-series carbon emission data. The target carbon emission node may be a monitoring equipment node of the carbon emission region. The stratified time-series carbon emission data corresponding to the target carbon emission node may be data of carbon emission amounts of the above-described target carbon emission nodes organized in the form of stratified time-series. Here, the carbon emission amount in the stratified time-series carbon emission data may be the carbon emission amount of the above-described target carbon emission node in the history period. The last layer may be the last layer of the stratified time-series carbon emission data. The end layer time series carbon emission data may include a carbon emission time series for each end layer. The carbon emission time series may include individual carbon emissions over a historical period of time. Each carbon emission time series may correspond to one node of the last layer.
As an example, the structure of the layered time series carbon emission data of 2 layers may refer to fig. 2. In FIG. 2, the time-series carbon emission data of the first layer may includey 1 . The time-series carbon emission data of the second layer may includey 2 Andy 3 。
and 102, determining time series carbon emission data of each layer which is different from the last layer time series carbon emission data in the layered time series carbon emission data as a previous layer time series carbon emission data set.
In some embodiments, the execution body may determine the time-series carbon emission data of each layer, which is different from the last-layer time-series carbon emission data, of the layered time-series carbon emission data as the previous-layer time-series carbon emission data set. The time-series carbon emission data of each layer preceding the last-layer time-series carbon emission data may be determined as a previous-layer time-series carbon emission data set.
And step 103, acquiring a carbon emission prediction result set of the previous layer time series carbon emission data set corresponding to a preset future time period as carbon emission prediction constraint information.
In some embodiments, the execution body may acquire a carbon emission prediction result set of the preceding time-series carbon emission data set corresponding to a preset future period of time as the carbon emission prediction constraint information. Wherein each of the carbon emission prediction results in the set of carbon emission prediction results satisfies a consistency condition. The carbon emission amount prediction result set may be a prediction result of predicting time-series carbon emission data of each layer before the last layer, which is input externally. Here, the carbon emission amount prediction result of each layer may be the respective carbon emission amounts of the respective nodes of the layer predicted from expert empirical knowledge within a preset future period of time. Each of the carbon emission prediction results in the above-described carbon emission prediction result set satisfies a consistency condition. The consistency condition may be that a sum of the carbon emissions corresponding to the same point in time and the same branch in the carbon emission prediction result of the current layer is equal to a sum of the carbon emissions corresponding to the node of the branch and the point in time in the upper layer.
And 104, generating a carbon emission prediction result corresponding to the preset future time period according to the last-layer time series carbon emission data and the carbon emission prediction model.
In some embodiments, the execution body may generate the carbon emission prediction result corresponding to the preset future period according to the last time series carbon emission data and the carbon emission prediction model. The carbon emission prediction model may be a model for predicting each carbon emission for a future period of time. Here, the carbon emission prediction model may be an algorithm model or a neural network model. For example, the above carbon emission prediction model may be, but is not limited to: ARIMA, ETS, xgboost, lightgbm, deepar.
In practice, the execution subject may generate the carbon emission amount prediction result corresponding to the preset future period of time by:
and a first step of performing a culling process on the abnormal value in the last time-series carbon emission data in response to determining that the abnormal value exists in the last time-series carbon emission data. Outliers in the end time series carbon emission data may be culled.
And secondly, performing missing value filling processing on the removed last-layer time-series carbon emission data so as to update the last-layer time-series carbon emission data. First, in response to determining that there is a missing value in the last-layer time-series data, a carbon emission amount time-series corresponding to the missing value may be extracted from the layered time-series carbon emission data. Then, a filling value corresponding to the missing value may be generated using the carbon emission time series. As an example, interpolation may be employed to generate a filling value corresponding to the missing value from the above-described carbon emission amount time series.
And thirdly, generating a carbon emission prediction result corresponding to the preset future time period according to the updated last-layer time series carbon emission data and the carbon emission prediction model. The updated last time series carbon emission data may be input into the carbon emission prediction model to obtain a carbon emission prediction result corresponding to the preset future time period. Here, the carbon emission amount prediction result may be a predicted amount of each carbon emission of each node of the last layer for a preset future period of time.
And 105, carrying out correction processing on the carbon emission prediction result according to the carbon emission prediction constraint information to obtain a corrected carbon emission prediction result serving as a carbon emission prediction output result of the carbon emission prediction model.
In some embodiments, the execution body may perform correction processing on the carbon emission prediction result according to the carbon emission prediction constraint information, to obtain the corrected carbon emission prediction result as the carbon emission prediction output result of the carbon emission prediction model. For example, the preset optimization target may be solved based on the carbon emission constraint information to obtain the corrected carbon emission prediction result. Here, the preset optimization target may be that the absolute value of the difference between the carbon emission amount prediction result and the corrected carbon emission amount prediction result is minimum.
In practice, the execution subject may perform correction processing on the carbon emission amount prediction result by:
and a first step of generating residual information according to each history fitting value and each actual value of the carbon emission data of the last layer time sequence and the corresponding history time period of the carbon emission prediction model. A residual error between each of the actual values and a history-fitted value corresponding to the actual value may be determined, and a residual error set may be obtained as residual error information. The historical time period may be a time period prior to the preset future time period described above.
And a second step of generating a covariance matrix according to the residual information. The variance-covariance matrix of the above residual information may be determined as a covariance matrix.
And thirdly, determining a constraint matrix corresponding to the layered time series carbon emission data. A predetermined sum matrix that sums the lowest-level timings of the above-described layered time-series carbon emission data to the high-level timings may be determined as the constraint matrix.
And a fourth step of generating carbon emission constraint information according to the constraint matrix and the carbon emission prediction constraint information. The constraint equation may be determined as carbon emission amount constraint information. Constraint formulas may be expressed as . Wherein (1)>The result of the carbon emission amount prediction after the correction process is shown. />Representing the above-described carbon emission prediction constraint information. Here, a->And->Are all in the form of a matrix.
The constraint matrix C may be:。
and fifthly, constructing a carbon emission prediction optimization target according to the carbon emission prediction result and the covariance matrix.
The following formula may be determined as the carbon emission prediction optimization target:。
wherein,the result of the carbon emission amount prediction after the correction process is shown. />The result of the above-described carbon emission prediction is shown. />Representing the covariance matrix. />The adjustment term of the modified bottom-most prediction result may be represented. The above formula may characterize that the sum of squares of the adjustment terms weighted by the residual covariance matrix is minimal. It will be appreciated that for sequences with greater standard deviation of the residuals (less accurate predictions), a greater adjustment term can be tolerated at the same penalty function value.
And a sixth step of generating a corrected carbon emission prediction result according to the carbon emission constraint information and the carbon emission prediction optimization target. The carbon emission prediction optimization target can be solved by taking the carbon emission constraint information as a constraint condition to obtain the corrected carbon emission And predicting the carbon emission amount. As an example, the solution may be solved by a lagrangian method. Specifically, it can be solved by the following formula:。
wherein,representing the matrix transpose.
And 106, constructing a carbon emission trend data graph according to the carbon emission prediction output result, and sending the carbon emission trend data graph to an associated display terminal for display.
In some embodiments, the executing body may construct a carbon emission trend data map according to the carbon emission prediction output result, and send the carbon emission trend data map to an associated display terminal for display. For example, the executing entity may construct the data trend graph of each carbon emission prediction amount corresponding to the output result of the carbon emission prediction as the carbon emission trend data graph through an excel table (for example, each carbon emission prediction amount may be input into the excel table, and then fit the carbon emission trend data graph through a linear regression method). The display terminal may be a computing terminal having a display function, which is communicatively connected to the execution body. For example, the display terminal may be a display.
Alternatively, the carbon emission prediction output result is input into a pre-trained abnormal data detection model, and the node position of each carbon emission prediction in each binary tree in the carbon emission prediction output result is obtained.
In some embodiments, the execution body may input the carbon emission prediction output result into a pre-trained abnormal data detection model, to obtain a node position of each carbon emission prediction in the carbon emission prediction output result in each binary tree. The abnormal data detection model comprises at least two binary trees, and the randomly selected attributes in the at least two binary trees are different. The anomaly data detection model may be a pre-trained isolated forest model.
The carbon emission prediction output result may be input to an isolated Forest (iferst, isolation Forest) model created in advance. Wherein at least two binary trees are typically included in the isolated forest model. And the randomly selected attributes differ between these binary trees in the isolated forest model. Thus, by the isolated forest model, the node position of each carbon emission prediction amount in each binary tree in the obtained carbon emission prediction output result can be output. The node position here may be position data representing the node to which the carbon emission prediction belongs in the binary tree, for example, may be a node identifier such as a node number or a node height (or layer number), or a node path length, etc.
It should be noted that ifest generally belongs to Non-parametric and un-optimized methods, i.e., neither a mathematical model is defined nor labeled training is required. The iferst uses a very efficient set of strategies for how to find which points are easily isolated (isolated). Assuming we cut (split) the data space (data space) with one random hyperplane, the two subspaces can be generated at a time. We then continue to cut each subspace with a random hyperplane. The loop continues until there is only one data point within each subspace. Intuitively, we can find that clusters with very high densities are cut many times to stop cutting, but points with very low densities easily stop into a subspace very early.
The ifest algorithm benefits from the idea of a random forest, which, like a random forest is composed of a large number of decision trees, is also composed of a large number of binary trees. The tree in ifeast is called as an isolation tree, abbreviated as an iTree, i.e., a binary tree. The construction process of the iTree is simpler than that of the decision tree, and the iTree is a completely random process.
Assuming that the data set has N pieces of data, when an iTree is constructed, N samples can be evenly sampled from the N pieces of data to be used as training samples of the tree. Typically no-put-back sampling. A feature is randomly selected from the sample, and a value is randomly selected from all value ranges (between the minimum value and the maximum value) of the feature, so as to binary divide the sample. The sample is divided into nodes with the value smaller than the sample to the left and the sample is divided into nodes with the value larger than the sample to the right. Thus, a split condition and data sets on both the left and right sides can be obtained. The above process is then repeated on the left and right data sets, respectively, until the data set has only one record or the defined height of the tree is reached.
Alternatively, the target node position of each carbon emission prediction amount is determined according to the node positions of each carbon emission prediction amount included in the carbon emission prediction output result in each binary tree.
In some embodiments, the executing entity may determine the target node position of each carbon emission prediction amount according to the node positions of each carbon emission prediction amount included in the carbon emission prediction output result in each binary tree. For each of the carbon emission prediction output results, an average value of node positions in each binary tree in the isolated forest model of the carbon emission prediction amount may be determined as a target node position of the carbon emission prediction amount. The execution subject may determine an average value of the node positions of the carbon emission pre-measurement in each binary tree in the isolated forest model, i.e., a height average value (PathLength), as a target node position of the carbon emission pre-measurement. A weighted average of the node locations may also be determined as the target node location for the carbon emission prediction.
Optionally, at least one abnormal carbon emission prediction amount in the above carbon emission prediction output result is determined according to the target node position of each carbon emission prediction amount.
In some embodiments, the executing entity may determine at least one abnormal carbon emission prediction amount in the carbon emission prediction output result according to a target node position of each carbon emission prediction amount.
In practice, the execution body may determine, as the abnormal carbon emission prediction amount, the carbon emission prediction amount in which the target node position is smaller than the preset position threshold value in order of low to high for each target node position, and obtain at least one abnormal carbon emission prediction amount. The first few of the target node locations may be the lowest as candidate node locations. It may then be determined whether the candidate node locations are less than a location threshold. And determining carbon emission information corresponding to the candidate node position smaller than the position threshold, namely, the carbon emission predicted amount close to the root node, as the abnormal carbon emission predicted amount.
Optionally, a plurality of index parameters related to the at least one abnormal carbon emission prediction amount are determined.
In some embodiments, the executive may determine a plurality of index parameters associated with the at least one abnormal carbon emission prediction. A plurality of index parameters associated with the at least one abnormal carbon emission information is determined. The plurality is typically at least two. The index parameter obtained by correlation may be a directly-correlated index parameter or an indirectly-correlated index parameter. For example, for carbon emissions, these index parameters are typically directly related to the carbon emission rate, the carbon emission time.
Optionally, analyzing an impact index parameter of the plurality of index parameters on the at least one abnormal carbon emission prediction.
In some embodiments, the execution body may analyze the impact index parameters of the plurality of index parameters on the at least one abnormal carbon emission prediction.
The impact index parameters of the plurality of index parameters on the at least one abnormal carbon emission prediction amount may be analyzed using attribution theory (LMDI, logarithmic Mean Index Method). For a certain abnormal carbon emission prediction amount, the data change can be disassembled to a specific certain index parameter factor through attribution theoretical analysis, so that the main reason is further positioned.
As an example, if the index is assumed: y=x+z. At this time, when the indices Y1 and Y0 of two different periods are compared, the change in the index is expressed as: Y1-Y0. And because the change of the index is caused by the change of two factors of X and Z, the change of the index can be further divided into the change of two factors of X and Z: y1-y0= (x1+z1) - (x0+z0) = (X1-X0) + (Z1-Z0). The absolute value of the contribution of factor X to the index is: X1-X0; the relative contribution values are: (X1-X0)/(Y1-Y0). The absolute value of the contribution of factor Z to the index is: Z1-Z0; the relative contribution values are: (Z1-Z0)/(Y1-Y0). It is understood that if the predicted amount of abnormal carbon emissions and the plurality of index parameters are in addition, a difference between the current value and the contrast value of each of the plurality of index parameters may be determined as an affecting index parameter affecting the predicted amount of abnormal carbon emissions.
In practice, the execution subject may analyze the influence index parameters of the plurality of index parameters on the at least one abnormal carbon emission prediction amount by:
in response to determining that the at least one abnormal carbon emission prediction amount and the plurality of index parameters are in an additive relationship, determining, for each of the plurality of index parameters, a difference between a current index value and a comparison index value of the index parameter as a contribution value affecting the at least one abnormal carbon emission prediction amount.
And a second step of, in response to determining that the at least one abnormal carbon emission prediction amount is in a multiplication relation with the plurality of index parameters, determining, for each of the plurality of index parameters, a natural logarithm of a ratio of a current index value to a comparison index value of the index parameter, and generating a contribution value of the index parameter affecting the at least one abnormal carbon emission prediction amount based on the natural logarithm, a difference between the current index value of the index parameter and the comparison index value.
And thirdly, generating an influence index parameter which influences the maximum predicted amount of the at least one abnormal carbon emission according to the contribution values corresponding to the index parameters.
Optionally, the at least one abnormal carbon emission prediction amount and the impact index parameter are transmitted to the display terminal.
In some embodiments, the execution body may transmit the at least one abnormal carbon emission prediction amount and the impact index parameter to the display terminal.
The above related matters are taken as an invention point of the present disclosure, and solve the second technical problem mentioned in the background art, which results in longer analysis time of carbon data. ". Factors that lead to longer analysis times for carbon data tend to be as follows: abnormal data in each carbon emission data is not resolved in advance, resulting in longer carbon data resolving time. If the above factors are solved, the effect of shortening the analysis time of the carbon data can be achieved. To achieve this, first, the above-described carbon emission amount prediction output results are input into a pre-trained abnormal data detection model, and the node positions of each carbon emission prediction amount in the above-described carbon emission amount prediction output results in the respective binary trees are obtained. The abnormal data detection model comprises at least two binary trees, and the randomly selected attributes in the at least two binary trees are different. Next, a target node position of each carbon emission prediction amount is determined according to the node positions of each carbon emission prediction amount included in the carbon emission prediction output result in each binary tree. Next, at least one abnormal carbon emission prediction amount in the above-described carbon emission prediction output results is determined according to the target node position of each carbon emission prediction amount. Then, determining a plurality of index parameters related to the at least one abnormal carbon emission prediction amount; analyzing the influence index parameters of the plurality of index parameters on the at least one abnormal carbon emission prediction amount. And finally, transmitting the at least one abnormal carbon emission predicted amount and the influence index parameter to the display terminal. Thus, by analyzing the respective carbon emission predictions, anomalies can be identified in combination with the time-series trend characteristics of the data. Thereby reducing the possibility that the change is identified as an abnormality and improving the accuracy of the abnormality analysis result. Further, the carbon data analysis time is shortened.
Optionally, before inputting the predicted output result of the carbon emission amount into a pre-trained abnormal data detection model, to obtain a node position of each predicted amount of carbon emission in the predicted output result of the carbon emission amount in each binary tree, the method further includes:
first, a training sample dataset is obtained. Here, the training sample data set may refer to sample data for training the abnormal data detection model. The training sample data may be a sample carbon emission sequence.
And secondly, selecting a preset number of training sample data from the training sample data set for each binary tree in the abnormal data detection model, and placing the training sample data into a root node of the binary tree.
And thirdly, selecting an attribute dimension different from other binary trees from a plurality of attribute dimensions of the preset number of training sample data.
In practice, the execution body may select an attribute dimension different from other binary trees by:
a first sub-step of selecting at least two candidate attribute dimensions from the plurality of attribute dimensions of the preset number of sample data by using the kurtosis coefficient.
And a second sub-step of selecting an attribute dimension different from the other binary tree from the at least two candidate attribute dimensions.
And fourthly, determining the dividing value of the attribute dimension according to the value range of the preset number of training sample data in the selected attribute dimension, dividing the training sample data of the current node into two child nodes, and recording the dividing value of the attribute dimension in the current node until the training sample data is divided into leaf nodes or the height of the binary tree reaches a height threshold.
It should be noted that, for the two sub-nodes obtained by dividing, the value range of the training sample data on the sub-node in the attribute dimension may be determined, so as to determine the dividing value of the attribute dimension again, so as to divide the training sample data on the sub-node into the two sub-nodes again.
As an example, the construction of an isolated forest first requires the construction of an iTree (tree). The itere is a random binary tree with either two daughter or leaf nodes per node and one child is not. Given a stack of data sets D, where all attributes of D are variables that are continuous, the iTree composition process is as follows: 1, randomly selecting an attribute Attr;2, randomly selecting a Value of the attribute; 3, classifying each record according to Attr, placing records with Attr smaller than Value on the left daughter, and placing records with Value larger than or equal to Value on the right child; 4, then recursing steps 2 and 3, continuing to construct the left and right parades until the following condition is satisfied: the incoming training sample data set has only one record or a plurality of identical records; alternatively, the height of the tree reaches a defined height.
It will be appreciated that the maximum height is set for each iTree, typically because at least one abnormal carbon emission prediction record is relatively small and the path length is relatively low. And we only need to distinguish between normal and abnormal recordings. So that only the portions below the average height need be of interest. This may allow for a higher analysis efficiency of the isolated forest model. As an example, the maximum height may be determined according to the number of samples (sub-sampling size) in each tree, such as. The number of samples per tree may be the same or different. In addition, sampling typically has less of a negative impact on the isolated forest model algorithm. And experiments show that after the sampling size exceeds 256, the effect on the isolated forest model is not greatly improved.
Thus, after t iTrees are obtained, iForest training generally ends. We can then use the generated ifest to perform test data analysis. It should be noted that, in order to ensure the accuracy of the prediction result of the isolated forest model, after each itrene is obtained, the itrene may be tested by using test data. Alternatively, the entire isolated forest model may be tested using the test data.
Here, the test procedure typically walks the test data over each of the constructed itrees to see at which leaf node the test data is at. It will be appreciated that the assumption that the iTree can effectively detect anomalies is: outliers are generally very rare and are quickly partitioned into leaf nodes in the iTree. In this case, the accuracy of the iTree analysis result may be determined according to the abnormality index of the test data. Wherein the anomaly index is generally determined based on the natural logarithm of the current analysis data (i.e., the data input to the itrate), the data quantity of the time series data (i.e., the data set).
The above related matters are taken as an invention point of the present disclosure, and solve the third technical problem mentioned in the background art that abnormal data is difficult to detect in time. ". Factors that make it difficult to detect abnormal data in time are often as follows: each carbon emission data is detected manually, the efficiency is low, and abnormal data is difficult to detect in time. If the above factors are solved, the effect of timely detecting abnormal data can be achieved. To achieve this, first, a training sample dataset is acquired. And secondly, selecting a preset number of training sample data from the training sample data set for each binary tree in the abnormal data detection model, and putting the training sample data into a root node of the binary tree. Then, selecting one attribute dimension which is different from other binary trees from a plurality of attribute dimensions of the preset number of training sample data. Then, determining the dividing value of the attribute dimension according to the value range of the preset number of training sample data in the selected attribute dimension, dividing the training sample data of the current node into two child nodes, and recording the dividing value of the attribute dimension in the current node until the training sample data is divided into leaf nodes or the height of the binary tree reaches a height threshold. Thus, the abnormal data can be detected by the trained abnormal data detection model. Therefore, abnormal carbon emission prediction in the carbon emission prediction output result can be detected rapidly through the model, and the detection efficiency is improved.
With further reference to FIG. 3, as an implementation of the method illustrated in the above-described figures, the present disclosure provides some embodiments of an intelligent algorithm-based carbon emission data map construction apparatus, which correspond to those method embodiments illustrated in FIG. 1, which is particularly applicable to various electronic devices.
As shown in fig. 3, the smart algorithm-based carbon emission data map construction apparatus 300 of some embodiments includes: an extraction unit 301, a determination unit 302, an acquisition unit 303, a generation unit 304, a correction unit 305, and a construction unit 306. Wherein the extraction unit 301 is configured to extract, from the layered time-series carbon emission data corresponding to the target carbon emission node, time-series carbon emission data corresponding to the last layer as the last-layer time-series carbon emission data; a determining unit 302 configured to determine, as a preceding layer time-series carbon emission data set, time-series carbon emission data of each layer that is different from the last layer time-series carbon emission data among the layered time-series carbon emission data; an acquisition unit 303 configured to acquire, as carbon emission prediction constraint information, a carbon emission prediction result set of the preceding time-series carbon emission data set corresponding to a preset future time period, wherein each of the carbon emission prediction results in the carbon emission prediction result set satisfies a consistency condition; a generation unit 304 configured to generate a carbon emission prediction result corresponding to the preset future period according to the last-layer time-series carbon emission data and the carbon emission prediction model; a correction unit 305 configured to perform correction processing on the carbon emission prediction result based on the carbon emission prediction constraint information, to obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model; and a construction unit 306 configured to construct a carbon emission trend data map according to the carbon emission prediction output result, and send the carbon emission trend data map to an associated display terminal for display.
It will be appreciated that the elements described in the intelligent algorithm-based carbon emission data map construction device 300 correspond to the individual steps in the method described with reference to fig. 1. Thus, the operations, features, and advantages described above with respect to the method are equally applicable to the smart algorithm-based carbon emission data map construction apparatus 300 and the units contained therein, and are not described herein.
Referring now to fig. 4, a schematic diagram of an electronic device (e.g., computing device) 400 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 4, the electronic device 400 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 401, which may perform various suitable actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing device 401, the ROM402, and the RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 400 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 4 may represent one device or a plurality of devices as needed.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing device 401.
It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: extracting time-series carbon emission data corresponding to a last layer from layered time-series carbon emission data corresponding to a target carbon emission node as last-layer time-series carbon emission data; determining time-series carbon emission data of each layer different from the last-layer time-series carbon emission data in the layered time-series carbon emission data as a previous-layer time-series carbon emission data set; acquiring a carbon emission prediction result set of the front-layer time series carbon emission data set corresponding to a preset future time period as carbon emission prediction constraint information, wherein each carbon emission prediction result in the carbon emission prediction result set meets a consistency condition; generating a carbon emission prediction result corresponding to the preset future time period according to the last-layer time sequence carbon emission data and the carbon emission prediction model; correcting the carbon emission prediction result according to the carbon emission prediction constraint information to obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model; and constructing a carbon emission trend data graph according to the carbon emission prediction output result, and sending the carbon emission trend data graph to an associated display terminal for display.
Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor comprising: the device comprises an extraction unit, a determination unit, an acquisition unit, a generation unit, a correction unit and a construction unit. The names of these units do not constitute a limitation of the unit itself in some cases, and for example, the extraction unit may also be described as "a unit that extracts time-series carbon emission data corresponding to the last layer from among layered time-series carbon emission data corresponding to the target carbon emission node as the last-layer time-series carbon emission data".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (7)
1. A carbon emission data graph construction method based on an intelligent algorithm comprises the following steps:
extracting time-series carbon emission data corresponding to a last layer from layered time-series carbon emission data corresponding to a target carbon emission node as last-layer time-series carbon emission data;
determining the time-series carbon emission data of each layer different from the last-layer time-series carbon emission data in the layered time-series carbon emission data as a previous-layer time-series carbon emission data set;
acquiring a carbon emission prediction result set of the front-layer time sequence carbon emission data set corresponding to a preset future time period as carbon emission prediction constraint information, wherein each carbon emission prediction result in the carbon emission prediction result set meets a consistency condition, and the consistency condition is that the sum of each carbon emission corresponding to the same time point and the same branch in the carbon emission prediction result of the current layer is equal to the sum of the node corresponding to the branch in the previous layer and each carbon emission corresponding to the time point;
generating a carbon emission prediction result corresponding to the preset future time period according to the final time sequence carbon emission data and a carbon emission prediction model;
according to the carbon emission prediction constraint information, carrying out correction processing on the carbon emission prediction result to obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model;
And constructing a carbon emission trend data graph according to the carbon emission prediction output result, and sending the carbon emission trend data graph to an associated display terminal for display.
2. The method of claim 1, wherein the generating a carbon emission prediction result corresponding to the preset future time period from the last time series carbon emission data and a carbon emission prediction model comprises:
in response to determining that abnormal values exist in the last-layer time-series carbon emission data, performing elimination processing on the abnormal values in the last-layer time-series carbon emission data;
performing missing value filling processing on the removed last-layer time-series carbon emission data so as to update the last-layer time-series carbon emission data;
and generating a carbon emission prediction result corresponding to the preset future time period according to the updated last-layer time series carbon emission data and the carbon emission prediction model.
3. The method of claim 1, wherein the method further comprises:
inputting the carbon emission prediction output result into a pre-trained abnormal data detection model to obtain the node position of each carbon emission prediction in each binary tree in the carbon emission prediction output result, wherein the abnormal data detection model comprises at least two binary trees, and the at least two binary trees have different randomly selected attributes;
Determining a target node position of each carbon emission prediction amount according to the node position of each carbon emission prediction amount in each binary tree included in the carbon emission prediction output result;
determining at least one abnormal carbon emission prediction amount in the carbon emission prediction output result according to the target node position of each carbon emission prediction amount;
determining a plurality of index parameters related to the at least one abnormal carbon emission prediction amount;
analyzing the influence index parameters of the plurality of index parameters on the at least one abnormal carbon emission predicted amount;
and sending the at least one abnormal carbon emission predicted amount and the influence index parameter to the display terminal.
4. The method of claim 3, wherein the determining at least one abnormal carbon emission prediction amount of the carbon emission prediction output results according to the target node position of each carbon emission prediction amount comprises:
and determining the carbon emission predicted quantity of which the target node position is smaller than a preset position threshold value as an abnormal carbon emission predicted quantity according to the sequence from low to high of each target node position, and obtaining at least one abnormal carbon emission predicted quantity.
5. An intelligent algorithm-based carbon emission data map construction device, comprising:
An extraction unit configured to extract time-series carbon emission data corresponding to an end layer from layered time-series carbon emission data corresponding to a target carbon emission node as end layer time-series carbon emission data;
a determining unit configured to determine, as a preceding layer time-series carbon emission data set, time-series carbon emission data of each layer of the layered time-series carbon emission data that is different from the last layer time-series carbon emission data;
an acquisition unit configured to acquire a carbon emission amount prediction result set of the preceding layer time-series carbon emission data set corresponding to a preset future period of time as carbon emission amount prediction constraint information, wherein each carbon emission amount prediction result in the carbon emission amount prediction result set satisfies a consistency condition that a sum of each carbon emission amount corresponding to the same time point and the same branch in the carbon emission amount prediction result of the current layer is equal to a sum of a node corresponding to the branch in the previous layer and each carbon emission amount of the time point;
a generation unit configured to generate a carbon emission prediction result corresponding to the preset future period of time according to the last-layer time-series carbon emission data and a carbon emission prediction model;
A correction unit configured to perform correction processing on the carbon emission prediction result according to the carbon emission prediction constraint information, and obtain a corrected carbon emission prediction result as a carbon emission prediction output result of the carbon emission prediction model;
and the construction unit is configured to construct a carbon emission trend data graph according to the carbon emission prediction output result and send the carbon emission trend data graph to an associated display terminal for display.
6. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.
7. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311091979.3A CN116822803B (en) | 2023-08-29 | 2023-08-29 | Carbon emission data graph construction method, device and equipment based on intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311091979.3A CN116822803B (en) | 2023-08-29 | 2023-08-29 | Carbon emission data graph construction method, device and equipment based on intelligent algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116822803A CN116822803A (en) | 2023-09-29 |
| CN116822803B true CN116822803B (en) | 2023-11-24 |
Family
ID=88118785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311091979.3A Active CN116822803B (en) | 2023-08-29 | 2023-08-29 | Carbon emission data graph construction method, device and equipment based on intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822803B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437105A (en) * | 2023-11-14 | 2024-01-23 | 国网宁夏电力有限公司电力科学研究院 | Carbon emission development trend prediction and early warning system based on carbon emission data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103762589A (en) * | 2014-01-08 | 2014-04-30 | 河海大学 | Method for optimizing new energy capacity ratio in layers in power grid |
| CN114240005A (en) * | 2022-02-24 | 2022-03-25 | 国网浙江省电力有限公司信息通信分公司 | Carbon emission prediction method and device based on multidimensional reference quantity and time series |
| CN114742294A (en) * | 2022-04-09 | 2022-07-12 | 广州网文三维数字技术有限公司 | Neural network algorithm for carbon emission prediction |
| CN115343958A (en) * | 2022-09-16 | 2022-11-15 | 中邮科通信技术股份有限公司 | Carbon analysis method based on intelligent building VMD-LSTM-GRU |
| CN115632392A (en) * | 2022-09-15 | 2023-01-20 | 平湖市通用电气安装有限公司 | Machine learning-based hierarchical and partitioned accurate load response system |
| CN116094068A (en) * | 2023-03-21 | 2023-05-09 | 国网福建省电力有限公司 | Power grid dispatching method, equipment and medium based on carbon emission prediction mechanism |
| WO2023154408A1 (en) * | 2022-02-10 | 2023-08-17 | Johnson Controls Tyco IP Holdings LLP | Control system with multi-factor and adaptive carbon emissions optimization |
-
2023
- 2023-08-29 CN CN202311091979.3A patent/CN116822803B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103762589A (en) * | 2014-01-08 | 2014-04-30 | 河海大学 | Method for optimizing new energy capacity ratio in layers in power grid |
| WO2023154408A1 (en) * | 2022-02-10 | 2023-08-17 | Johnson Controls Tyco IP Holdings LLP | Control system with multi-factor and adaptive carbon emissions optimization |
| CN114240005A (en) * | 2022-02-24 | 2022-03-25 | 国网浙江省电力有限公司信息通信分公司 | Carbon emission prediction method and device based on multidimensional reference quantity and time series |
| CN114742294A (en) * | 2022-04-09 | 2022-07-12 | 广州网文三维数字技术有限公司 | Neural network algorithm for carbon emission prediction |
| CN115632392A (en) * | 2022-09-15 | 2023-01-20 | 平湖市通用电气安装有限公司 | Machine learning-based hierarchical and partitioned accurate load response system |
| CN115343958A (en) * | 2022-09-16 | 2022-11-15 | 中邮科通信技术股份有限公司 | Carbon analysis method based on intelligent building VMD-LSTM-GRU |
| CN116094068A (en) * | 2023-03-21 | 2023-05-09 | 国网福建省电力有限公司 | Power grid dispatching method, equipment and medium based on carbon emission prediction mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 吉林省交通运输碳排放灰色关联与预测分析;卢晓玲;高标;;综合运输(第12期);5-10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116822803A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2021343372A1 (en) | Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models | |
| CN114422267B (en) | Flow detection method, device, equipment and medium | |
| CN116822803B (en) | Carbon emission data graph construction method, device and equipment based on intelligent algorithm | |
| CN115085196B (en) | Power load predicted value determination method, device, equipment and computer readable medium | |
| CN114580263A (en) | Knowledge graph-based information system fault prediction method and related equipment | |
| CN113807926A (en) | Recommendation information generation method and device, electronic equipment and computer readable medium | |
| CN116827971B (en) | Block chain-based carbon emission data storage and transmission method, device and equipment | |
| CN112199252A (en) | Abnormity monitoring method and device and electronic equipment | |
| CN115599650A (en) | Health degree evaluation method and device of IT system, electronic equipment and storage medium | |
| CN117236805B (en) | Power equipment control method, device, electronic equipment and computer readable medium | |
| CN113891342A (en) | Base station inspection method and device, electronic equipment and storage medium | |
| CN115860147A (en) | Customs sheet pre-judging model training method and device based on unbalanced ensemble learning | |
| CN115186738A (en) | Model training method, device and storage medium | |
| CN111582456B (en) | Method, apparatus, device and medium for generating network model information | |
| CN111027680B (en) | Monitoring quantity uncertainty prediction method and system based on variational self-encoder | |
| CN108491440B (en) | GNSS non-real-time data tracing visualization method and system | |
| CN113779335A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN113052509A (en) | Model evaluation method, model evaluation apparatus, electronic device, and storage medium | |
| CN116596585B (en) | User satisfaction obtaining method and device, electronic equipment and storage medium | |
| CN116319386A (en) | Availability and fault prediction method and device, electronic equipment and medium | |
| CN117235535B (en) | Abnormal supply end power-off method and device, electronic equipment and medium | |
| CN117593096B (en) | Intelligent pushing method and device for product information, electronic equipment and computer medium | |
| EP4134834A1 (en) | Method and apparatus of processing feature information, electronic device, and storage medium | |
| CN113901206A (en) | Word embedding-based equipment loss prediction method and device and electronic equipment | |
| CN117857388A (en) | Switch operation information detection method and device, electronic equipment and computer medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |