An intelligent energy management method and system

Abstract

The present invention discloses an intelligent energy management method and system, and relates to the field of energy monitoring. The present invention includes inputting time-sharing electricity price information of energy consumption nodes, time-sharing opening time limit of energy nodes in mining areas, basic power distribution restriction settings of energy nodes in different regions, and total power data of 6kV total step-down stations, establishing a planning energy consumption optimization model, and analyzing the hierarchical data settings of energy consumption nodes based on the EA-VNEH algorithm according to correlation analysis and energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function, for controlling energy optimization management. The present invention summarizes and analyzes the electric energy consumption data of mining areas. It provides an intuitive and scientific basis for energy conservation and consumption reduction, provides data analysis for enterprises to find energy consumption, promotes further improvement of enterprise management level and further reduction of operating costs, makes energy use more reasonable, controls waste, and achieves the purpose of energy conservation, emission reduction, and energy consumption reduction.

Description

Technical Field

[0001] The present invention relates to the field of energy monitoring, and in particular to an intelligent energy management method and system. Background Art

[0002] The existing power meters at the mining site are old and lack data remote transmission function. There is a lack of intelligent management methods for high-power consumption equipment and analysis of energy consumption data. The on-site meters are scattered, and manual meter reading is labor-intensive and error-prone.

[0003] Since it is a mining site, the existing advanced energy metering system cannot be adaptively adjusted. This is mostly due to the different degrees of industrial diversification in the mining area, and different mining industries have different types and amounts of mineral deposits, regions and corresponding energy consumption requirements, production environment requirements, energy conservation and pollution limit requirements, which leads to the inability to adapt the analysis algorithm set up in the metering system.

[0004] Therefore, there is an urgent need for an intelligent energy management method and system to achieve energy conservation and emission reduction measurement. Summary of the invention

[0005] The present invention provides an intelligent energy management method and system, which solves the problems of the prior art.

[0006] In a first aspect, the present invention provides an intelligent energy management method and system, including classifying energy meters with the same data rules under a branch of a mining area energy topology diagram according to meter reading data into energy types, and grading virtual energy consumption nodes;

[0007] Based on the energy type classification information and virtual energy consumption node classification information, the analysis is as follows: a correlation analysis of virtual energy consumption nodes under energy type is performed to obtain multiple two-dimensional energy consumption node data arrays based on energy type as a difference indicator; correlation analysis is used to summarize the mapping rules between node data;

[0008] Based on the energy consumption node classification information, the mining area energy topology diagram is reorganized into an energy consumption node link matrix;

[0009] The time-sharing electricity price information of energy consumption nodes, the time-sharing opening time limit of energy nodes in the mining area, the basic distribution restriction settings of energy nodes in different regions, and the total power data of 6kV total step-down station are input to establish a planning energy consumption optimization model. Based on the EA-VNEH algorithm, according to the correlation analysis and the energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function, the energy consumption node classification data setting is analyzed to control the energy optimization management.

[0010] Furthermore, it includes: correlation analysis includes analyzing the numerical changes between different energy meters in time sequence to see if they conform to mathematical laws, and then identifying the rules between energy meter data represented by mathematical laws based on the correlation analysis results of the two-dimensional energy consumption node data array.

[0011] Further, it includes: constructing a resource and location set of energy nodes, each energy node including three node components, namely a basic consumption node component, a dynamic consumption node component and a link-related consumption node component;

[0012] According to the time-sharing electricity price information of energy consumption nodes and the time-sharing opening time limit of energy nodes in the mining area, the objective function A is performed on the energy node components. According to the basic power distribution restriction settings of energy nodes in different regions, the objective function B is set for the location set of energy nodes. According to the total power data of the 6kV total step-down station and the control of energy optimization by minimizing the mapping energy consumption overhead, the objective function C is set for the link-related consumption node components.

[0013] Based on the objective function and correlation, the energy consumption node link matrix is ​​analyzed, and the meter reading data is substituted to obtain the predetermined value and the output value of the energy consumption node link matrix. The difference is set as the error signal, and the error signal is used to update the setting weight of the BP network. The BP network uses three layers of neurons to process the objective function A, objective function B, objective function C, the output value of the energy consumption node link matrix and the error signal to obtain the connection weight setting between the hidden layer activation function and the control parameters of the output layer activation function;

[0014] The three-layer neurons of BP network include the first layer with multiple given input values, the second layer of hidden layer neurons, and the third layer of output layer neurons;

[0015] According to the output layer control parameters, PID control is performed on the energy consumption node link matrix, and the control parameters corresponding to the optimal control value at each given moment are iterated cyclically.

[0016] Furthermore, it also includes: obtaining the energy topology diagram of the mining area, obtaining historical meter reading data and analyzing the energy meter branch where each energy meter reading data corresponds to the energy meter, and collecting the main and branch data of different energy meters.

[0017] Furthermore, according to the output PID control parameters, the link matrix of the energy consumption node is adaptively adjusted and controlled to adjust the power distribution and power consumption control schemes of the corresponding nodes.

[0018] Furthermore, the correlation analysis also includes classifying the mapping combinations of node data into candidate mapping nodes, necessary mapping nodes, and bottom-level nodes with the lowest energy consumption;

[0019] In the process of constructing the planning energy consumption optimization model, the energy demand of the necessary mapping nodes is constrained, the mapping law is modeled based on mixed integer linear programming, the necessary mapping nodes are used as mapping constraints, the total power data of the 6kV total step-down station is used as constraints, and the minimization of the mapping energy consumption overhead is used as the objective function. It is converted into an NP-hard problem, and the constraint range of the node variables is set.

[0020] Furthermore, the first layer of the BP network has multiple given input values ​​including the objective function A, the objective function B, the objective function C, the output value of the energy consumption node link matrix and the error signal.

[0021] Furthermore, based on the output value of the third layer of neurons, the control parameters of the PID are reassigned, the results are calculated through the PID algorithm, assigned to the load module of the corresponding node, the output signal is filtered, and the output of the energy consumption node link matrix is ​​obtained. Based on the error signal generated after the current filtering, it is determined whether the iterative PID control value meets the requirements. When the PID control value meets the output condition of achieving the optimal control value for the node link matrix at the current moment, the loop ends;

[0022] In a second aspect, the present invention provides an intelligent energy management system, characterized in that it is used to implement any method as in the first aspect, including a collection module, an analysis module, an energy topology block diagram, an energy consumption optimization model and a control module; the collection module outputs historical meter reading data to the analysis module; the energy topology block diagram is connected to the analysis module;

[0023] The analysis module loads the energy meter branch where each meter reading data corresponds to the energy meter in the historical meter reading data, collects the main and branch energy topology diagrams of different energy meters, and classifies the energy meters with the same data rules under the energy topology diagram according to the meter reading data, and classifies the virtual energy consumption nodes; the analysis module is used to analyze the correlation of virtual energy consumption nodes under energy types, and based on the energy consumption node classification information, reorganize the mining area energy topology diagram into an energy consumption node link matrix, enter the energy consumption node time-sharing electricity price information, the energy node time-sharing opening time limit in the mining area, the basic distribution restriction settings of energy nodes in different regions, and the total power data of 6kV total step-down station, and establish a planned energy consumption optimization model; the analysis module is used to analyze the energy consumption node classification data settings based on the EA-VNEH algorithm based on the correlation analysis and the energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function, for controlling energy optimization management and outputting control parameters to the control module; the control module regulates the node energy distribution and power consumption data based on the control parameters.

[0024] The present invention provides an intelligent energy management method and system, which realizes digital management of on-site meters, remote meter reading, centralized monitoring, real-time control of energy trends, clarification of energy consumption patterns, formulation of reasonable operation strategies, and reduction of energy waste.

[0025] The present invention realizes energy sub-item measurement and summarizes and analyzes the electric energy consumption data of the mining area. It understands the energy consumption status of the mining area, provides an intuitive and scientific basis for energy saving and consumption reduction, provides data analysis for enterprises to find energy consumption, promotes further improvement of enterprise management level and further reduction of operating costs, makes energy use more reasonable, controls waste, and achieves the purpose of energy saving, emission reduction and energy consumption reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0027] Figure 1 A main flow chart of an intelligent energy management method provided by an exemplary embodiment of the present invention.

[0028] Figure 2 A specific flow chart of controlling optimal energy management in an intelligent energy management method provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of systems and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0030] In the existing technology, due to the different types and amounts of mineral deposits, the regions in which they are located and the corresponding energy consumption requirements, production environment requirements, energy conservation and pollution limit requirements, the analysis algorithms set in the metering system cannot be adaptively changed. Due to the large number of energy meter types in the metering system in the mining area, the data correlation information is poorly constructed, and the load control scheme of the energy meter causes large interference between multiple loads. Due to the influence of load jitter, the noise effect of the output of the control parameter itself is affected.

[0031] Therefore, the present invention conceives to solve the problem of noise effect influence through filtering, adopts multiple filtering methods, such as Kalman filtering, and constructs the NP-hard problem of node classification by reorganizing the energy topology block diagram of the mining area, and converts it into, constructing a three-layer BP neural network layer to solve the output PID control parameter problem, adopts EA-VNEH algorithm to solve the constructed NP-hard problem, and adopts BP neural network to solve the PID optimal control problem of the node corresponding to the load, so as to realize the optimal energy consumption node analysis.

[0032] The specific application scenario of the present invention is mining area energy monitoring and control.

[0033] The present invention provides an intelligent energy management method and system, aiming to solve the above technical problems in the prior art.

[0034] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0035] Embodiment 1: This embodiment provides an intelligent energy management method, such as Figure 1 As shown, including:

[0036] s0. Obtain the energy topology diagram of the mining area, obtain historical meter reading data and analyze the energy meter branch where each energy meter reading data corresponds to, and collect the data of the main circuit and branch of different energy meters;

[0037] s1. Energy meters with the same data pattern under the branch of the mining area energy topology diagram are classified into energy types according to meter reading data, and virtual energy consumption nodes are graded; based on the energy consumption of the mining area, the location of the mining area machines and the type of energy consumption are queried and included in the mining area energy topology diagram;

[0038] s2, based on energy type classification information and virtual energy consumption node classification information;

[0039] The analysis is as follows: a correlation analysis of virtual energy consumption nodes under energy type is performed to obtain multiple two-dimensional energy consumption node data arrays based on energy type as the difference indicator; the correlation analysis is used to summarize the mapping rules between node data; the correlation analysis includes analyzing the numerical changes between different energy tables in time sequence to see if they conform to mathematical laws, and then identifying the rules between energy table data represented by mathematical laws based on the correlation analysis results of the two-dimensional energy consumption node data array.

[0040] s3. Based on the energy consumption node classification information, the energy topology diagram of the mining area is reorganized into an energy consumption node link matrix;

[0041] s4. Enter the time-sharing electricity price information of energy consumption nodes, the time-sharing opening time limit of energy nodes in the mining area, the basic distribution restriction settings of energy nodes in different regions, and the total power data of 6kV total step-down station, and establish a planned energy consumption optimization model. Based on the EA-VNEH algorithm, according to the correlation analysis and the energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function, analyze the energy consumption node classification data setting for controlling energy optimization management.

[0042] The s4 step specifically includes, Figure 2 As shown:

[0043] s41. Construct a resource and location set of energy nodes, where each energy node includes three node components, namely, a basic consumption node component, a dynamic consumption node component, and a link-related consumption node component;

[0044] s42. According to the time-sharing electricity price information of energy consumption nodes and the time-sharing opening time limit of energy nodes in the mining area, the objective function A is performed on the energy node components. According to the basic power distribution restriction setting of energy nodes in different regions, the objective function B is set for the location set of energy nodes. According to the total power data of the 6kV total step-down station and the control of energy optimization by minimizing the mapping energy consumption overhead, the objective function C is set for the link-related consumption node components.

[0045] s43. Analyze the energy consumption node link matrix based on the objective function and correlation, substitute the meter reading data, obtain the predetermined value and the output value of the energy consumption node link matrix, set the difference as the error signal, and re-update the set weight of the BP network with the error signal;

[0046] The first layer of BP network has multiple given input values: objective function A, objective function B, objective function C, energy consumption node link matrix output value and error signal;

[0047] The BP network uses three layers of neurons to process the target function A, target function B, target function C, the output value of the energy consumption node link matrix and the error signal to obtain the connection weight setting between the hidden layer activation function and the control parameters of the output layer activation function; the correlation analysis also includes the classification of the mapping combination of node data, the classification of candidate mapping nodes, necessary mapping nodes and the bottom nodes with the lowest energy consumption;

[0048] In the process of constructing the planning energy consumption optimization model, the energy demand of the necessary mapping nodes is constrained, the mapping law is modeled based on mixed integer linear programming, the necessary mapping nodes are used as mapping constraints, the total power data of the 6kV total step-down station is used as constraints, and the minimization of the mapping energy consumption overhead is used as the objective function. It is converted into an NP-hard problem, and the constraint range of the node variables is set.

[0049] s44, BP network three-layer neurons include the first layer of multiple given input values, the second layer of hidden layer neurons, and the third layer of output layer neurons; according to the output layer control parameters, the energy consumption node link matrix is ​​PID controlled, and the control parameters corresponding to the optimal control value at each given time are cyclically iterated;

[0050] Specifically: based on the output value of the third layer of neurons, the PID control parameters are reassigned, the results are calculated through the PID algorithm, assigned to the load module of the corresponding node, the output signal is filtered, and the output of the energy consumption node link matrix is ​​obtained. Based on the error signal generated after the current filtering, it is determined whether the iterative PID control value meets the requirements. When the PID control value meets the output condition of achieving the optimal control value for the node link matrix at the current moment, the loop ends.

[0051] s45. According to the output PID control parameters, the energy consumption node link matrix is ​​adaptively adjusted and controlled to adjust the power distribution and power consumption control scheme of the corresponding nodes.

[0052] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0053] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0054] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0055] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0056] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0057] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the claims above.

Claims

1. An intelligent energy management method, characterized in that: include: Energy meters with the same data pattern under the branch of the mining area energy topology diagram are classified into energy types according to meter reading data, and virtual energy consumption nodes are graded; Based on the energy type classification information and virtual energy consumption node classification information, the analysis is as follows: a correlation analysis of virtual energy consumption nodes under energy type is performed to obtain multiple two-dimensional energy consumption node data arrays based on energy type as a difference indicator; correlation analysis is used to summarize the mapping rules between node data; Based on the energy consumption node classification information, the mining area energy topology diagram is reorganized into an energy consumption node link matrix; The time-sharing electricity price information of energy consumption nodes, the time-sharing opening time limit of energy nodes in the mining area, the basic distribution restriction settings of energy nodes in different regions, and the total power data of 6kV total step-down station are input to establish a planning energy consumption optimization model. Based on the EA-VNEH algorithm, according to the correlation analysis and the energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function, the energy consumption node classification data setting is analyzed to control the energy optimization management.

2. The intelligent energy management method according to claim 1, characterized in that: include: Correlation analysis involves analyzing the numerical changes between different energy meters in chronological order to see if they conform to mathematical laws, and then identifying the rules between energy meter data represented by mathematical laws based on the correlation analysis results of the two-dimensional energy consumption node data array.

3. The intelligent energy management method according to claim 2, characterized in that: include: Construct a resource and location set of energy nodes. Each energy node includes three node components, namely, basic consumption node component, dynamic consumption node component and link-related consumption node component. According to the time-sharing electricity price information of energy consumption nodes and the time-sharing opening time limit of energy nodes in the mining area, the objective function A is set for the energy node component; according to the basic power distribution limit setting of energy nodes in different regions, the objective function B is set for the location set of energy nodes; according to the total power data of the 6kV total step-down station and the control of energy optimization by minimizing the mapping energy consumption overhead, the objective function C is set for the link-related consumption node component; Based on the objective function and correlation, the energy consumption node link matrix is ​​analyzed, and the meter reading data is substituted to obtain the predetermined value and the output value of the energy consumption node link matrix. The difference is set as an error signal, and the error signal is used to re-update the setting weight of the BP network. The BP network uses three layers of neurons to process the objective function A, the objective function B, the objective function C, the output value of the energy consumption node link matrix and the error signal to obtain the connection weight setting between the hidden layer activation function and the control parameters of the output layer activation function; The three-layer neurons of BP network include the first layer with multiple given input values, the second layer of hidden layer neurons, and the third layer of output layer neurons; According to the output layer control parameters, PID control is performed on the energy consumption node link matrix, and the control parameters corresponding to the optimal control value at each given moment are iterated cyclically.

4. The intelligent energy management method according to claim 3, characterized in that: Also includes: Obtain the energy topology diagram of the mining area, obtain historical meter reading data and analyze the energy meter branch where each meter reading data corresponds to the energy meter, and collect the data of the main and branch of different energy meters.

5. The intelligent energy management method according to claim 4, characterized in that: According to the output PID control parameters, the link matrix of the energy consumption node is adaptively adjusted and controlled to adjust the power distribution and power consumption control scheme of the corresponding node.

6. An intelligent energy management method according to claim 5, characterized in that: The correlation analysis also includes classifying the mapping combinations of node data into candidate mapping nodes, necessary mapping nodes and bottom-level nodes with the lowest energy consumption; In the process of constructing the planning energy consumption optimization model, the energy demand of the necessary mapping nodes is constrained, the mapping law is modeled based on mixed integer linear programming, the necessary mapping nodes are used as mapping constraints, the total power data of the 6kV total step-down station is used as constraints, and the minimization of the mapping energy consumption overhead is used as the objective function. It is converted into an NP-hard problem, and the constraint range of the node variables is set.

7. An intelligent energy management method according to claim 6, characterized in that: in, The first layer of the BP network has multiple given input values, including the objective function A, objective function B, objective function C, the output value of the energy consumption node link matrix and the error signal.

8. An intelligent energy management method according to claim 7, characterized in that: Based on the output value of the third layer of neurons, the PID control parameters are reassigned, the results are calculated through the PID algorithm, and assigned to the load module of the corresponding node. The output signal is filtered to obtain the output of the energy consumption node link matrix. Based on the error signal generated after the current filtering, it is determined whether the iterative PID control value meets the requirements. When the PID control value meets the output condition of achieving the optimal control value for the node link matrix at the current moment, the loop ends.

9. An intelligent energy management system, characterized in that: Used to implement an intelligent energy management method as described in any one of claims 1 to 8, comprising a collection module, an analysis module, an energy topology block diagram, an energy consumption optimization model and a control module; The acquisition module collects historical meter reading data and outputs it to the analysis module; The energy topology block diagram is connected to the analysis module; The analysis module loads the energy meter branch where each energy meter corresponding to each meter reading data in the historical meter reading data is located, collects the main and branch energy topology diagrams of different energy meters, and classifies the energy types of energy meters with the same data rules under the energy topology diagram according to the meter reading data, and classifies the virtual energy consumption nodes; The analysis module is used to analyze the correlation of virtual energy consumption nodes under energy types, and based on the energy consumption node classification information, reorganize the mining area energy topology block diagram into an energy consumption node link matrix, input the time-sharing electricity price information of energy consumption nodes, the time-sharing opening time limit of energy nodes in the mining area, the basic power distribution restriction settings of energy nodes in different regions, and the total power data of 6kV total step-down station, and establish a planning energy consumption optimization model; An analysis module is used to analyze the energy consumption node classification data settings for controlling energy optimization management and output control parameters to the control module based on the EA-VNEH algorithm according to the correlation analysis and the energy consumption node link matrix, with minimizing the mapping energy consumption overhead as the objective function; The control module regulates node energy distribution and power consumption data based on control parameters.

Images