CN115759658B - Enterprise energy consumption data management system suitable for smart city - Google Patents
Enterprise energy consumption data management system suitable for smart city Download PDFInfo
- Publication number
- CN115759658B CN115759658B CN202211480976.4A CN202211480976A CN115759658B CN 115759658 B CN115759658 B CN 115759658B CN 202211480976 A CN202211480976 A CN 202211480976A CN 115759658 B CN115759658 B CN 115759658B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- scale
- feature
- power
- enterprise
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 292
- 238000013523 data management Methods 0.000 title claims abstract description 59
- 238000000605 extraction Methods 0.000 claims abstract description 71
- 238000007726 management method Methods 0.000 claims abstract description 30
- 239000013598 vector Substances 0.000 claims description 140
- 239000011159 matrix material Substances 0.000 claims description 74
- 238000013527 convolutional neural network Methods 0.000 claims description 70
- 238000000034 method Methods 0.000 claims description 29
- 238000010586 diagram Methods 0.000 claims description 26
- 230000004927 fusion Effects 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 20
- 230000008859 change Effects 0.000 abstract description 13
- 238000013135 deep learning Methods 0.000 abstract description 10
- 238000004422 calculation algorithm Methods 0.000 abstract description 9
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 23
- 238000012545 processing Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000005065 mining Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The utility model discloses an enterprise energy consumption data management system suitable for smart city, it draws the multiscale dynamic correlation characteristic of the energy consumption power of each consumer in the enterprise in the time dimension through adopting the artificial intelligence detection algorithm based on deep learning to consider the energy consumption power between each consumer also has the correlation, consequently further utilize the network model that has different receptive fields to carry out the multiscale correlation characteristic extraction of the energy consumption change characteristic between each consumer to carry out the energy consumption detection of enterprise with this. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Description
Technical Field
The present application relates to the field of smart cities, and more particularly, to an enterprise energy consumption data management system suitable for smart cities.
Background
Smart city construction is an important trend of city development in the future, and is a necessary requirement for sustainable city development. The energy consumption data management of enterprises can improve the energy utilization efficiency of smart cities.
The existing enterprise energy consumption management system is usually simple energy consumption total value monitoring, for example, a preset threshold is set to judge whether the enterprise energy consumption is normal, and the enterprise energy consumption management mode is too simple and does not accord with the actual enterprise energy consumption use condition, because the enterprise energy consumption itself can change along with time and business conditions, and the enterprise energy consumption management requirement cannot be met by simple threshold reference.
Thus, an optimized enterprise energy consumption data management scheme suitable for smart cities is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides an enterprise energy consumption data management system suitable for smart cities, which extracts multi-scale dynamic association characteristics of energy consumption power of electric equipment in an enterprise in a time dimension by adopting an artificial intelligent detection algorithm based on deep learning, and considers that the energy consumption power of the electric equipment also has association relation, so that the multi-scale association characteristics of energy consumption change characteristics among the electric equipment are extracted by further utilizing a network model with different receptive fields, and the energy consumption detection of the enterprise is carried out. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
According to one aspect of the present application, there is provided an enterprise energy consumption data management system adapted for a smart city, comprising:
the energy consumption data acquisition module is used for acquiring energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period;
the device energy consumption feature extraction module is used for respectively arranging energy consumption power values of each electric device at a plurality of preset time points in a preset time period into power input vectors and then obtaining a plurality of power feature vectors through the multi-scale neighborhood feature extraction module;
the device-to-device correlation feature extraction module is used for performing two-dimensional arrangement on the plurality of power feature vectors to form a global power feature matrix, and then obtaining a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields;
the feature fusion module is used for fusing the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map to obtain a classification feature map; and
And the management result generation module is used for passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the energy consumption of the enterprise to be detected is normal or not.
In the above enterprise energy consumption data management system suitable for smart city, the device energy consumption feature extraction module includes: a first scale feature extraction unit, configured to input the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale feature extraction unit, configured to input the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale power feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the multiscale cascading unit is used for cascading the first neighborhood scale power eigenvector and the second neighborhood scale power eigenvector to obtain the multiple power eigenvectors.
In the above enterprise energy consumption data management system suitable for a smart city, the first scale feature extraction unit is further configured to: performing one-dimensional convolution encoding on the power input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale power feature vector; wherein, the formula is:
Wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated with a convolution kernel function, w is the size of the first convolution kernel, and X represents the power input vector. A second scale feature extraction unit, further configured to: performing one-dimensional convolution encoding on the power input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale power feature vector; wherein, the formula is:
wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated with a convolution kernel function, m is the size of the second convolution kernel, and X represents the power input vector.
In the enterprise energy consumption data management system applicable to the smart city, the first convolutional neural network uses a first convolutional kernel with a first scale, and the second convolutional neural network uses a second convolutional kernel with a second scale, wherein the first scale is different from the second scale.
In the enterprise energy consumption data management system applicable to the smart city, the first convolutional neural network uses a first hole convolutional kernel with a first hole rate, the second convolutional neural network uses a second hole convolutional kernel with a second hole rate, wherein the first hole rate is different from the second hole rate, and the first hole convolutional kernel and the second hole convolutional kernel have the same size.
In the above enterprise energy consumption data management system suitable for smart city, the feature fusion module is further configured to: fusing the first scale energy consumption correlation feature map and the second scale energy consumption correlation feature map by the following formula to obtain the classification feature map; wherein, the formula is:
wherein M is 1i And M 2i Diagonal matrix, M, obtained by linear transformation of the ith feature matrix of the first scale energy consumption associated feature map and the second scale energy consumption associated feature map respectively ci Is the ith feature matrix of the classification feature map, and ReLU (·) represents the ReLU activation function,the method is characterized in that the method comprises the steps of multiplying a matrix, dividing the matrix eigenvalues by the division between a numerator matrix and a denominator matrix, wherein exp (·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the calculation of a natural exponential function value with the eigenvalues of all positions in the matrix as powers.
In the above enterprise energy consumption data management system suitable for smart city, the management result generating module includes: a developing unit for developing the classification feature map into classification feature vectors based on row vectors or column vectors; the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a plurality of full-connection layers of the classifier so as to obtain coded classification characteristic vectors; and the classification result generating unit is used for enabling the coding classification feature vector to pass through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided an enterprise energy consumption data management method applicable to a smart city, including:
acquiring energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period;
the energy consumption power values of the electric equipment at a plurality of preset time points in a preset time period are respectively arranged into power input vectors, and then a plurality of power feature vectors are obtained through a multi-scale neighborhood feature extraction module;
two-dimensionally arranging the power feature vectors into a global power feature matrix, and then obtaining a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields;
fusing the first scale energy consumption associated feature map and the second scale energy consumption associated feature map to obtain a classification feature map; and
and the classification characteristic diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the energy consumption of the enterprise to be detected is normal or not.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory in which computer program instructions are stored which, when executed by the processor, cause the processor to perform the enterprise energy consumption data management method applicable to a smart city as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform an enterprise energy consumption data management method applicable to a smart city as described above.
Compared with the prior art, the enterprise energy consumption data management system suitable for the smart city extracts the multi-scale dynamic association characteristics of the energy consumption power of each electric equipment in the enterprise in the time dimension by adopting the artificial intelligent detection algorithm based on deep learning, and considers that the energy consumption power of each electric equipment also has association relation, so that the network model with different receptive fields is further utilized to extract the multi-scale association characteristics of the energy consumption change characteristics of each electric equipment, and the energy consumption detection of the enterprise is carried out. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is an application scenario diagram of an enterprise energy consumption data management system suitable for use in a smart city according to an embodiment of the present application;
FIG. 2 is a block diagram of an enterprise energy consumption data management system suitable for use in a smart city in accordance with an embodiment of the present application;
FIG. 3 is a system architecture diagram of an enterprise energy consumption data management system suitable for use in a smart city according to an embodiment of the present application;
FIG. 4 is a block diagram of a device energy consumption feature extraction module in an enterprise energy consumption data management system suitable for use in smart cities according to an embodiment of the present application;
FIG. 5 is a block diagram of a management result generation module in an enterprise energy consumption data management system suitable for use in a smart city according to an embodiment of the present application;
FIG. 6 is a flow chart of an enterprise energy consumption data management method applicable to a smart city according to an embodiment of the present application;
Fig. 7 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Scene overview
As described in the foregoing background, smart city construction is an important trend of city development in the future, and is a necessary requirement for sustainable city development. The energy consumption data management of enterprises can improve the energy utilization efficiency of smart cities.
The existing enterprise energy consumption management system is usually simple energy consumption total value monitoring, for example, a preset threshold is set to judge whether the enterprise energy consumption is normal, and the enterprise energy consumption management mode is too simple and does not accord with the actual enterprise energy consumption use condition, because the enterprise energy consumption itself can change along with time and business conditions, and the enterprise energy consumption management requirement cannot be met by simple threshold reference. Thus, an optimized enterprise energy consumption data management scheme suitable for smart cities is desired.
At present, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, speech signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
In recent years, deep learning and neural network development provide new solutions and schemes for enterprise energy consumption data management in smart cities.
Accordingly, since the existing enterprise energy consumption management system is generally simple to monitor the total energy consumption value to detect whether the enterprise energy consumption is normal, the detection mode for the enterprise energy consumption cannot meet the existing management requirement in consideration of the fact that the enterprise energy consumption usage itself changes with time and service conditions. Based on the above, in the technical scheme of the application, the multi-scale dynamic association characteristic of the energy consumption power of each electric equipment in the enterprise in the time dimension is extracted by adopting an artificial intelligent detection algorithm based on deep learning, and the association relation of the energy consumption power of each electric equipment is considered, so that the multi-scale association characteristic extraction of the energy consumption change characteristic of each electric equipment is further carried out by utilizing a network model with different receptive fields, and the energy consumption detection of the enterprise is carried out. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Specifically, in the technical scheme of the application, first, energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period are obtained. And then, considering that the energy consumption values of all the electric devices have different mode change characteristics under different time span periods, respectively arranging the energy consumption values of a plurality of preset time points of all the electric devices in a preset time period as power input vectors, and then carrying out feature mining in a multi-scale neighborhood feature extraction module so as to extract dynamic multi-scale neighborhood association features of the energy consumption power of each electric device under different time spans, thereby obtaining a plurality of power feature vectors.
Further, when the energy consumption of each electric device of all electric devices of the enterprise is actually detected, the energy consumption power of each electric device also has a corresponding association relation because the electric devices cooperate with each other to perform corresponding operation. Therefore, in the technical scheme of the application, after the multiple power feature vectors are further two-dimensionally arranged into a global power feature matrix to integrate dynamic multiscale neighborhood associated feature information of the energy consumption power of each electric equipment, feature mining is performed on the dynamic multiscale neighborhood associated feature information through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, so that multiscale associated feature information of dynamic change features of the energy consumption power values of each electric equipment, namely associated feature distribution information of energy consumption power dynamic features of a certain electric equipment in each electric equipment, is extracted, and therefore a first-scale energy consumption associated feature graph and a second-scale energy consumption associated feature graph are obtained. In particular, here, the first convolutional neural network and the second convolutional neural network have different characteristic receptive fields. Accordingly, in one specific example of the present application, the first convolutional neural network may use a first convolutional kernel having a first scale and the second convolutional neural network uses a second convolutional kernel having a second scale, wherein the first scale is different from the second scale. Also, in another specific example of the present application, the first convolutional neural network may further use a first hole convolutional kernel having a first hole rate, and the second convolutional neural network uses a second hole convolutional kernel having a second hole rate, wherein the first hole rate is different from the second hole rate, and the first hole convolutional kernel and the second hole convolutional kernel have the same size. Therefore, the multiscale associated feature extraction can be carried out on the dynamic features of the energy consumption power of the specific mutually-cooperated electric equipment in the plurality of electric equipment by utilizing the multiscale feature receptive field, so that the accuracy of the follow-up energy consumption detection of enterprises is improved.
And then, fusing the first scale energy consumption association feature map and the second scale energy consumption association feature map to obtain a classification feature map, so as to represent multi-scale dynamic association features of the energy consumption power of each electric equipment, namely, the energy consumption power dynamic feature information of the whole enterprise to be detected, which contains the association of the cooperative work among the electric equipment, and performing classification processing in a classifier to obtain a classification result for representing whether the energy consumption of the enterprise to be detected is normal. Therefore, whether the energy consumption of the enterprise to be detected is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Particularly, in the technical scheme of the application, the power feature vectors obtained through the multi-scale neighborhood feature extraction module contain multi-scale power association features in a time sequence dimension, so that after two-dimensional arrangement is a global power feature matrix, staggered distribution of association scales contained in the global power feature matrix among the arranged power feature vectors can migrate to different feature distribution directions under feature extraction of different receptive fields of the first convolutional neural network and the second convolutional neural network, and negative correlation relations exist between corresponding positions among feature matrices of the first-scale energy consumption association feature map and the second-scale energy consumption association feature map, which are arranged along a channel dimension, so that fusion effects of the first-scale energy consumption association feature map and the second-scale energy consumption association feature map are affected.
Therefore, the applicant of the present application adopts a full orthographic projection nonlinear re-weighting mode to fuse the corresponding feature matrixes of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map, and the fusion is expressed as follows:
M 1i and M 2i Diagonal matrix obtained by linear transformation of ith feature matrix of first scale energy consumption associated feature diagram and second scale energy consumption associated feature diagram respectively, M ci Is the i-th feature matrix of the classification feature map, and the division between the numerator matrix and the denominator matrix is the division by position of the matrix feature values.
Here, the all-positive projection nonlinear re-weighting guarantees the all-positive of projection by a ReLU function to avoid aggregating negatively-related information, and simultaneously introduces a nonlinear re-weighting mechanism to aggregate the eigenvalue distributions of the corresponding eigenvalues of the first-scale energy consumption-associated eigenvalue graph and the second-scale energy consumption-associated eigenvalue graph with respect to each other, so that the inherent structure of the corresponding eigenvalue of the classification eigenvalue graph can penalize long-distance connection to strengthen localized coupling. Therefore, the synergistic effect of the spatial feature transformation corresponding to the full orthographic projection weighting of the corresponding feature matrixes of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map in the high-dimensional feature space is achieved, the fusion effect of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map is improved, and the classification accuracy is further improved. Therefore, the energy consumption of enterprises can be accurately and intelligently detected, and corresponding energy consumption management is further implemented on detection results, so that the energy utilization efficiency of smart cities is improved.
Based on this, the application proposes an enterprise energy consumption data management system suitable for smart cities, comprising: the energy consumption data acquisition module is used for acquiring energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period; the device energy consumption feature extraction module is used for respectively arranging energy consumption power values of each electric device at a plurality of preset time points in a preset time period into power input vectors and then obtaining a plurality of power feature vectors through the multi-scale neighborhood feature extraction module; the device-to-device correlation feature extraction module is used for performing two-dimensional arrangement on the plurality of power feature vectors to form a global power feature matrix, and then obtaining a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields; the feature fusion module is used for fusing the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map to obtain a classification feature map; and the management result generation module is used for passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the energy consumption of the enterprise to be detected is normal or not.
Fig. 1 is an application scenario diagram of an enterprise energy consumption data management system suitable for a smart city according to an embodiment of the present application. As shown in fig. 1, in this application scenario, energy consumption values of all electric devices of an enterprise to be detected at a plurality of predetermined time points within a predetermined time period are obtained by an energy consumption power meter (for example, P as illustrated in fig. 1). The data is then input to a server (e.g., S in fig. 1) deployed with an enterprise energy consumption data management algorithm for the smart city, where the server is capable of processing the input data with the enterprise energy consumption data management algorithm for the smart city to generate a classification result indicating whether the energy consumption of the enterprise to be detected is normal.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary System
Fig. 2 is a block diagram of an enterprise energy consumption data management system suitable for use in a smart city according to an embodiment of the present application. As shown in fig. 2, an enterprise energy consumption data management system 300 applicable to a smart city according to an embodiment of the present application includes: an energy consumption data acquisition module 310; a device energy consumption feature extraction module 320; an inter-device association feature extraction module 330; a feature fusion module 340; and a management result generation module 350.
The energy consumption data collection module 310 is configured to obtain energy consumption power values of all electric devices of an enterprise to be detected at a plurality of predetermined time points within a predetermined time period; the device energy consumption feature extraction module 320 is configured to respectively arrange energy consumption power values of the electric devices at a plurality of predetermined time points within a predetermined time period into power input vectors, and then obtain a plurality of power feature vectors through the multi-scale neighborhood feature extraction module; the inter-device correlation feature extraction module 330 is configured to two-dimensionally arrange the plurality of power feature vectors into a global power feature matrix, and then obtain a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a dual-flow network model including a first convolutional neural network and a second convolutional neural network, where the first convolutional neural network and the second convolutional neural network have different feature receptive fields; the feature fusion module 340 is configured to fuse the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map to obtain a classification feature map; and the management result generating module 350 is configured to pass the classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the energy consumption of the enterprise to be detected is normal.
Fig. 3 is a system architecture diagram of an enterprise energy consumption data management system suitable for a smart city according to an embodiment of the present application. As shown in fig. 3, in the system architecture of the enterprise energy consumption data management system 300 applicable to a smart city, first, energy consumption power values of all electric devices of an enterprise to be detected at a plurality of preset time points within a preset time period are obtained through the energy consumption data acquisition module 310; the device energy consumption feature extraction module 320 arranges the energy consumption power values of each electric device acquired by the energy consumption data acquisition module 310 at a plurality of preset time points in a preset time period into power input vectors respectively, and then obtains a plurality of power feature vectors through a multi-scale neighborhood feature extraction module; next, the inter-device correlation feature extraction module 330 performs two-dimensional arrangement on the multiple power feature vectors obtained by the device energy consumption feature extraction module 320 to obtain a global power feature matrix, and then obtains a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a dual-flow network model including a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields; then, the feature fusion module 340 fuses the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map obtained by the inter-device associated feature extraction module 330 to obtain a classification feature map; furthermore, the management result generating module 350 passes the classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the energy consumption of the enterprise to be detected is normal.
Specifically, during the operation of the enterprise energy consumption data management system 300 applicable to the smart city, the energy consumption data collection module 310 is configured to obtain energy consumption power values of all electric devices of the enterprise to be detected at a plurality of predetermined time points within a predetermined time period. It should be understood that the existing enterprise energy consumption management system is generally simple to monitor the total energy consumption value to detect whether the enterprise energy consumption is normal, and takes into account that the enterprise energy consumption usage amount itself changes along with time and service conditions, so in the technical scheme of the application, a deep learning-based artificial intelligent detection algorithm is adopted to extract multi-scale dynamic correlation characteristics of the energy consumption power of each electric equipment in the enterprise in the time dimension, and the energy consumption power of each electric equipment is considered to have a correlation relationship, so that a network model with different receptive fields is further utilized to extract the multi-scale correlation characteristics of the energy consumption change characteristics of each electric equipment, and the energy consumption detection of the enterprise is performed. In a specific example of the application, the energy consumption power values of all electric equipment of the enterprise to be detected at a plurality of preset time points in a preset time period can be obtained through an energy consumption power meter.
Specifically, in the operation process of the enterprise energy consumption data management system 300 applicable to the smart city, the device energy consumption feature extraction module 320 is configured to arrange the energy consumption power values of the electric devices at a plurality of predetermined time points within a predetermined time period into power input vectors respectively, and then obtain a plurality of power feature vectors through the multi-scale neighborhood feature extraction module. And considering that the energy consumption power values of all the electric devices have different mode change characteristics under different time span periods, further arranging the energy consumption power values of a plurality of preset time points of each electric device in a preset time period as power input vectors respectively, and then carrying out feature mining in a multi-scale neighborhood feature extraction module so as to extract dynamic multi-scale neighborhood association features of the energy consumption power of each electric device under different time spans, thereby obtaining a plurality of power feature vectors.
Fig. 4 is a block diagram of a device energy consumption feature extraction module in an enterprise energy consumption data management system suitable for use in a smart city according to an embodiment of the present application. As shown in fig. 4, the device energy consumption feature extraction module 320 includes: a first scale feature extraction unit 321, configured to input the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale feature extraction unit 322 configured to input the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale power feature vector, where the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and a multi-scale cascading unit 323, configured to cascade the first neighborhood scale power feature vector and the second neighborhood scale power feature vector to obtain the plurality of power feature vectors. The step of inputting the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector includes: performing one-dimensional convolution encoding on the power input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale power feature vector;
Wherein, the formula is:
wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated with a convolution kernel function, w is the size of the first convolution kernel, and X represents the power input vector. And inputting the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood-scale power feature vector, comprising: performing one-dimensional convolution encoding on the power input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale power feature vector;
wherein, the formula is:
wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated with a convolution kernel function, m is the size of the second convolution kernel, and X represents the power input vector.
Specifically, in the operation process of the enterprise energy consumption data management system 300 suitable for a smart city, the inter-device correlation feature extraction module 330 is configured to two-dimensionally arrange the plurality of power feature vectors into a global power feature matrix, and then obtain a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a dual-flow network model including a first convolutional neural network and a second convolutional neural network, where the first convolutional neural network and the second convolutional neural network have different feature receptive fields. When the energy consumption of each electric equipment of all electric equipment of an enterprise is actually detected, the energy consumption power of each electric equipment also has a corresponding association relation because the electric equipment can cooperate with each other to perform corresponding operation. Therefore, in the technical scheme of the application, after the multiple power feature vectors are further two-dimensionally arranged into a global power feature matrix to integrate dynamic multiscale neighborhood associated feature information of the energy consumption power of each electric equipment, feature mining is performed on the dynamic multiscale neighborhood associated feature information through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, so that multiscale associated feature information of dynamic change features of the energy consumption power values of each electric equipment, namely associated feature distribution information of energy consumption power dynamic features of a certain electric equipment in each electric equipment, is extracted, and therefore a first-scale energy consumption associated feature graph and a second-scale energy consumption associated feature graph are obtained. In particular, here, the first convolutional neural network and the second convolutional neural network have different characteristic receptive fields. Accordingly, in one specific example of the present application, the first convolutional neural network may use a first convolutional kernel having a first scale and the second convolutional neural network uses a second convolutional kernel having a second scale, wherein the first scale is different from the second scale. Also, in another specific example of the present application, the first convolutional neural network may further use a first hole convolutional kernel having a first hole rate, and the second convolutional neural network uses a second hole convolutional kernel having a second hole rate, wherein the first hole rate is different from the second hole rate, and the first hole convolutional kernel and the second hole convolutional kernel have the same size. Therefore, the multiscale associated feature extraction can be carried out on the dynamic features of the energy consumption power of the specific mutually-cooperated electric equipment in the plurality of electric equipment by utilizing the multiscale feature receptive field, so that the accuracy of the follow-up energy consumption detection of enterprises is improved. More specifically, after the multiple power feature vectors are two-dimensionally arranged into a global power feature matrix, a first scale energy consumption correlation feature map and a second scale energy consumption correlation feature map are obtained through a dual-flow network model including a first convolutional neural network and a second convolutional neural network, and the method comprises the following steps: performing convolution processing of a first convolution kernel on input data in forward transfer of layers by using layers of the first convolution neural network: carrying out convolution processing on input data to obtain a convolution characteristic diagram; carrying out pooling treatment based on a local feature matrix on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network is the first scale energy consumption correlation characteristic diagram, and the input of the first layer of the first convolutional neural network is a global power characteristic matrix; and performing convolution processing of a second convolution kernel on the input data in forward transfer of layers using layers of the second convolution neural network: carrying out convolution processing on input data to obtain a convolution characteristic diagram; carrying out pooling treatment based on a local feature matrix on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the second convolutional neural network is the second scale energy consumption correlation characteristic diagram, and the input of the first layer of the second convolutional neural network is a global power characteristic matrix.
Specifically, in the operation process of the enterprise energy consumption data management system 300 applicable to the smart city, the feature fusion module 340 is configured to fuse the first scale energy consumption related feature map and the second scale energy consumption related feature map to obtain a classification feature map. In the technical scheme of the application, the first scale energy consumption association feature map and the second scale energy consumption association feature map are fused to obtain a classification feature map, so that the multi-scale dynamic association feature of the energy consumption power of each electric equipment is represented, namely the energy consumption power dynamic feature information of the whole enterprise to be detected, which contains the association of cooperative work among the electric equipment. Particularly, in the technical scheme of the application, the power feature vectors obtained through the multi-scale neighborhood feature extraction module contain multi-scale power association features in a time sequence dimension, so that after two-dimensional arrangement is a global power feature matrix, staggered distribution of association scales contained in the global power feature matrix among the arranged power feature vectors can migrate to different feature distribution directions under feature extraction of different receptive fields of the first convolutional neural network and the second convolutional neural network, and negative correlation relations exist between corresponding positions among feature matrices of the first-scale energy consumption association feature map and the second-scale energy consumption association feature map, which are arranged along a channel dimension, so that fusion effects of the first-scale energy consumption association feature map and the second-scale energy consumption association feature map are affected. Therefore, the applicant of the present application adopts a full orthographic projection nonlinear re-weighting mode to fuse the corresponding feature matrixes of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map, and the fusion is expressed as follows:
Wherein M is 1i And M 2i Diagonal matrix, M, obtained by linear transformation of the ith feature matrix of the first scale energy consumption associated feature map and the second scale energy consumption associated feature map respectively ci Is the ith feature matrix of the classification feature map, and ReLU (·) represents the ReLU activation function,the method is characterized in that the method comprises the steps of multiplying a matrix, dividing the matrix eigenvalues by the division between a numerator matrix and a denominator matrix, wherein exp (·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the calculation of a natural exponential function value with the eigenvalues of all positions in the matrix as powers. Here, the all-positive projection nonlinear re-weighting guarantees the all-positive of projection by a ReLU function to avoid aggregating negatively-related information, and simultaneously introduces a nonlinear re-weighting mechanism to aggregate the eigenvalue distributions of the corresponding eigenvalues of the first-scale energy consumption-associated eigenvalue graph and the second-scale energy consumption-associated eigenvalue graph with respect to each other, so that the inherent structure of the corresponding eigenvalue of the classification eigenvalue graph can penalize long-distance connection to strengthen localized coupling. Therefore, the synergistic effect of the spatial feature transformation corresponding to the full orthographic projection weighting of the corresponding feature matrixes of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map in the high-dimensional feature space is achieved, the fusion effect of the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map is improved, and the classification accuracy is further improved. Thus, the enterprise energy consumption can be accurately and intelligently detected, and the corresponding energy consumption pipe is implemented for the detection result And the energy utilization efficiency of the smart city is improved.
Specifically, during the operation of the enterprise energy consumption data management system 300, the management result generation module 350 is configured to pass the classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the energy consumption of the enterprise to be detected is normal. Namely, the classification characteristic diagram is subjected to classification processing in a classifier to obtain a classification result used for indicating whether the energy consumption of the enterprise to be detected is normal. Therefore, whether the energy consumption of the enterprise to be detected is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved. Specifically, the classifier includes a plurality of fully connected layers and a Softmax layer cascaded with a last fully connected layer of the plurality of fully connected layers. In the classification process of the classifier, the classification feature map is first projected as a vector, for example, in a specific example, the classification feature map is expanded along a row vector or a column vector to form a classification feature vector; then, performing multiple full-connection coding on the classification feature vectors by using multiple full-connection layers of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax layer of the classifier, namely, classifying the coding classification feature vector by using the Softmax classification function to obtain a classification result for indicating whether the energy consumption of the enterprise to be detected is normal. More specifically, in one specific example of the present application, the classification feature map is processed using the classifier to obtain a classification result according to the following formula:
O＝softmax{(W n ,B n ):…:(W 1 ,B 1 ) Project (F), where Project (F) represents projecting the classification feature map as a vector, W 1 To W n Weight matrix for all the connection layers of each layer, B 1 To B n Representing the bias vector for each fully connected layer.
Fig. 5 is a block diagram of a management result generation module in an enterprise energy consumption data management system applicable to a smart city according to an embodiment of the present application. As shown in fig. 5, the management result generating module 350 includes: a developing unit 351 configured to develop the classification feature map into classification feature vectors based on row vectors or column vectors; a full-connection encoding unit 352, configured to perform full-connection encoding on the classification feature vector by using multiple full-connection layers of the classifier to obtain an encoded classification feature vector; and a classification result generating unit 353, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the enterprise energy consumption data management system 300 applicable to smart cities according to the embodiments of the present application is illustrated, which extracts multi-scale dynamic correlation features of energy consumption power of each electric device in a time dimension by adopting an artificial intelligent detection algorithm based on deep learning, and considers that the energy consumption power of each electric device also has a correlation relationship, so that the multi-scale correlation feature extraction of energy consumption change features between each electric device is further performed by using a network model with different receptive fields, and thus, the energy consumption detection of the enterprise is performed. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Exemplary method
Fig. 6 is a flowchart of an enterprise energy consumption data management method suitable for a smart city according to an embodiment of the present application. As shown in fig. 6, the enterprise energy consumption data management method applicable to the smart city according to the embodiment of the application includes the steps of: s110, acquiring energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period; s120, respectively arranging the energy consumption power values of the electric equipment at a plurality of preset time points in a preset time period into power input vectors, and then obtaining a plurality of power feature vectors through a multi-scale neighborhood feature extraction module; s130, two-dimensionally arranging the power feature vectors into a global power feature matrix, and then obtaining a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields; s140, fusing the first scale energy consumption associated feature map and the second scale energy consumption associated feature map to obtain a classification feature map; and S150, passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the energy consumption of the enterprise to be detected is normal or not.
In one example, in the enterprise energy consumption data management method applicable to the smart city, the step S120 includes: inputting the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale power feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and cascading the first neighborhood scale power feature vector and the second neighborhood scale power feature vector to obtain the plurality of power feature vectors. The step of inputting the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector includes: performing one-dimensional convolution encoding on the power input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale power feature vector;
Wherein, the formula is:
wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated with a convolution kernel function, w is the size of the first convolution kernel, and X represents the power input vector. And inputting the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood-scale power feature vector, comprising: performing one-dimensional convolution encoding on the power input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale power feature vector;
wherein, the formula is:
wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated with a convolution kernel function, m is the size of the second convolution kernel, and X represents the power input vector.
In one example, in the enterprise energy consumption data management method applicable to the smart city, the step S130 includes: the first convolutional neural network uses a first convolutional kernel having a first scale and the second convolutional neural network uses a second convolutional kernel having a second scale, wherein the first scale is different from the second scale; and the first convolutional neural network uses a first hole convolutional kernel having a first hole rate, and the second convolutional neural network uses a second hole convolutional kernel having a second hole rate, wherein the first hole rate is different from the second hole rate, and the first hole convolutional kernel and the second hole convolutional kernel have the same size.
In one example, in the enterprise energy consumption data management method applicable to the smart city, the step S140 includes: fusing the first scale energy consumption correlation feature map and the second scale energy consumption correlation feature map by the following formula to obtain the classification feature map;
wherein, the formula is:
wherein M is 1i And M 2i Diagonal matrix, M, obtained by linear transformation of the ith feature matrix of the first scale energy consumption associated feature map and the second scale energy consumption associated feature map respectively ci Is the ith feature matrix of the classification feature map, and ReLU (·) represents the ReLU activation function,the method is characterized in that the method comprises the steps of multiplying a matrix, dividing the matrix eigenvalues by the division between a numerator matrix and a denominator matrix, wherein exp (·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the calculation of a natural exponential function value with the eigenvalues of all positions in the matrix as powers.
In one example, in the enterprise energy consumption data management method applicable to the smart city, the step S150 includes: expanding the classification characteristic map into classification characteristic vectors based on row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the enterprise energy consumption data management method suitable for smart cities according to the embodiment of the application is clarified, by adopting an artificial intelligent detection algorithm based on deep learning to extract multi-scale dynamic correlation characteristics of energy consumption power of each electric equipment in the enterprise in a time dimension, and considering that the energy consumption power of each electric equipment also has a correlation relationship, the multi-scale correlation characteristic extraction of energy consumption change characteristics among the electric equipment is further carried out by utilizing a network model with different receptive fields, and the energy consumption detection of the enterprise is carried out. Therefore, whether the enterprise energy consumption is normal or not can be accurately detected, and corresponding energy consumption management is further implemented, so that the energy utilization efficiency of the smart city is improved.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present application is described with reference to fig. 7.
Fig. 7 illustrates a block diagram of an electronic device according to an embodiment of the present application.
As shown in fig. 7, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. On which one or more computer program instructions may be stored that may be executed by the processor 11 to implement the functions in the enterprise energy consumption data management system suitable for smart cities and/or other desired functions of the various embodiments of the present application described above. Various contents such as a power feature vector may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 7 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions described in the above-described "exemplary systems" section of the present description in an enterprise energy consumption data management method applicable to smart cities according to various embodiments of the present application.
The computer program product may write program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in the functions described in the above-mentioned "exemplary systems" section of the present description, according to various embodiments of the present application, in an enterprise energy consumption data management method suitable for smart cities.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is 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 (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.
The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (6)
1. An enterprise energy consumption data management system suitable for a smart city, comprising:
The energy consumption data acquisition module is used for acquiring energy consumption power values of all electric equipment of an enterprise to be detected at a plurality of preset time points in a preset time period;
the device energy consumption feature extraction module is used for respectively arranging energy consumption power values of each electric device at a plurality of preset time points in a preset time period into power input vectors and then obtaining a plurality of power feature vectors through the multi-scale neighborhood feature extraction module;
the device-to-device correlation feature extraction module is used for performing two-dimensional arrangement on the plurality of power feature vectors to form a global power feature matrix, and then obtaining a first-scale energy consumption correlation feature map and a second-scale energy consumption correlation feature map through a double-flow network model comprising a first convolutional neural network and a second convolutional neural network, wherein the first convolutional neural network and the second convolutional neural network have different feature receptive fields;
the feature fusion module is used for fusing the first-scale energy consumption associated feature map and the second-scale energy consumption associated feature map to obtain a classification feature map; and
the management result generation module is used for enabling the classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the energy consumption of an enterprise to be detected is normal or not;
The feature fusion module is further configured to: fusing the first scale energy consumption correlation feature map and the second scale energy consumption correlation feature map by the following formula to obtain the classification feature map;
wherein, the formula is:
wherein M is 1i And M 2i Diagonal matrix, M, obtained by linear transformation of the ith feature matrix of the first scale energy consumption associated feature map and the second scale energy consumption associated feature map respectively ci Is the ith feature matrix of the classification feature map, and ReLU (·) represents the ReLU activation function,the method is characterized in that the method comprises the steps of multiplying a matrix, dividing the matrix eigenvalues by the division between a numerator matrix and a denominator matrix, wherein exp (·) represents the exponential operation of the matrix, and the exponential operation of the matrix represents the calculation of a natural exponential function value with the eigenvalues of all positions in the matrix as powers.
2. The enterprise energy consumption data management system for smart cities of claim 1, wherein the device energy consumption feature extraction module comprises:
a first scale feature extraction unit, configured to input the power input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale power feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length;
A second scale feature extraction unit, configured to input the power input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale power feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and
and the multiscale cascading unit is used for cascading the first neighborhood scale power eigenvector and the second neighborhood scale power eigenvector to obtain the multiple power eigenvectors.
3. The enterprise energy consumption data management system for smart cities according to claim 2, wherein,
a first scale feature extraction unit, further configured to: performing one-dimensional convolution encoding on the power input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale power feature vector;
wherein, the formula is:
wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of the first convolution kernel, and X represents the power input vector;
A second scale feature extraction unit, further configured to: performing one-dimensional convolution encoding on the power input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale power feature vector;
wherein, the formula is:
wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated with a convolution kernel function, m is the size of the second convolution kernel, and X represents the power input vector.
4. The enterprise energy consumption data management system for smart cities of claim 3, wherein the first convolutional neural network uses a first convolutional kernel having a first scale and the second convolutional neural network uses a second convolutional kernel having a second scale, wherein the first scale is different from the second scale.
5. The enterprise energy consumption data management system for smart cities of claim 3, wherein the first convolutional neural network uses a first hole convolutional kernel having a first hole rate and the second convolutional neural network uses a second hole convolutional kernel having a second hole rate, wherein the first hole rate is different from the second hole rate, and wherein the first hole convolutional kernel and the second hole convolutional kernel have the same size.
6. The enterprise energy consumption data management system for smart cities of claim 5, wherein the management result generation module comprises:
a developing unit for developing the classification feature map into classification feature vectors based on row vectors or column vectors;
the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a plurality of full-connection layers of the classifier so as to obtain coded classification characteristic vectors; and
and the classification result generation unit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211480976.4A CN115759658B (en) | 2022-11-24 | 2022-11-24 | Enterprise energy consumption data management system suitable for smart city |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211480976.4A CN115759658B (en) | 2022-11-24 | 2022-11-24 | Enterprise energy consumption data management system suitable for smart city |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115759658A CN115759658A (en) | 2023-03-07 |
| CN115759658B true CN115759658B (en) | 2023-07-18 |
Family
ID=85336930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211480976.4A Active CN115759658B (en) | 2022-11-24 | 2022-11-24 | Enterprise energy consumption data management system suitable for smart city |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759658B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115964360B (en) * | 2023-03-14 | 2023-05-16 | 山东省地震工程研究院 | Method and system for building earthquake safety evaluation database |
| CN116247824B (en) * | 2023-03-30 | 2023-11-17 | 国网河南省电力公司安阳供电公司 | Control method and system for power equipment |
| CN116821745B (en) * | 2023-04-10 | 2024-04-09 | 浙江万能弹簧机械有限公司 | Control method and system of intelligent linear cutting slow wire-moving equipment |
| CN116597163A (en) * | 2023-05-18 | 2023-08-15 | 广东省旭晟半导体股份有限公司 | Infrared optical lens and method for manufacturing the same |
| CN116975728B (en) * | 2023-08-07 | 2024-01-26 | 山东省地质矿产勘查开发局第八地质大队(山东省第八地质矿产勘查院) | Safety management method and system for coal bed methane drilling engineering |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099684A (en) * | 2022-07-18 | 2022-09-23 | 江西中科冠物联网科技有限公司 | Enterprise safety production management system and management method thereof |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108830199B (en) * | 2018-05-31 | 2021-04-16 | 京东方科技集团股份有限公司 | Method and device for identifying traffic light signal, readable medium and electronic equipment |
| CN112766199B (en) * | 2021-01-26 | 2022-04-29 | 武汉大学 | Hyperspectral image classification method based on self-adaptive multi-scale feature extraction model |
| CN114049935A (en) * | 2021-11-23 | 2022-02-15 | 齐鲁工业大学 | HER2 image classification system based on multi-convolution neural network |
| CN114926683A (en) * | 2022-05-23 | 2022-08-19 | 中山大学 | Air flight target classification identification method and device and computer readable storage medium |
| CN115293265A (en) * | 2022-08-05 | 2022-11-04 | 河北建筑工程学院 | Non-invasive monitoring method and system for building electricity utilization |
| CN115203380B (en) * | 2022-09-19 | 2022-12-20 | 山东鼹鼠人才知果数据科技有限公司 | Text processing system and method based on multi-mode data fusion |
-
2022
- 2022-11-24 CN CN202211480976.4A patent/CN115759658B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099684A (en) * | 2022-07-18 | 2022-09-23 | 江西中科冠物联网科技有限公司 | Enterprise safety production management system and management method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115759658A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115759658B (en) | Enterprise energy consumption data management system suitable for smart city | |
| CN115783923B (en) | Elevator fault mode identification system based on big data | |
| CN115796173B (en) | Data processing method and system for supervising reporting requirements | |
| CN116247824B (en) | Control method and system for power equipment | |
| CN116015837A (en) | Intrusion detection method and system for computer network information security | |
| CN115834433B (en) | Data processing method and system based on Internet of things technology | |
| CN115827257B (en) | CPU capacity prediction method and system for processor system | |
| CN115880036B (en) | Parking space level dynamic sharing intelligent management and control transaction platform | |
| CN116579618B (en) | Data processing method, device, equipment and storage medium based on risk management | |
| CN116486622A (en) | Traffic intelligent planning system and method based on road data | |
| CN116151845A (en) | Product full life cycle management system and method based on industrial Internet of things technology | |
| CN115324843A (en) | Wind generating set fault diagnosis system and method based on monitoring data | |
| CN116308754A (en) | Bank credit risk early warning system and method thereof | |
| CN116403253A (en) | Face recognition monitoring management system and method based on convolutional neural network | |
| CN116151604A (en) | Office system flow analysis system and method under web environment | |
| CN116151545A (en) | Multi-wind motor group power control optimization system | |
| CN116624977B (en) | Building automatic control system and method based on artificial intelligence | |
| CN104468272A (en) | Flow matrix estimation method and device | |
| CN116844088A (en) | Online dust remover control system and method thereof | |
| CN116128250A (en) | Electricity selling deviation management method and system for spot market | |
| CN117077955A (en) | Energy management system and method for optical storage grid-connected power generation system | |
| CN116526670A (en) | Information fusion method for power big data visualization | |
| CN115953183A (en) | Electricity selling company electricity purchasing and selling risk prediction system and method for spot market | |
| CN116383714A (en) | Equipment protection system for bucket wheel machine and method thereof | |
| CN116821745B (en) | Control method and system of intelligent linear cutting slow wire-moving equipment |
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 |