A method of energy monitoring based on big data

Abstract

The present invention relates to the field of energy monitoring, and in particular to an energy monitoring method based on big data, including real-time collection of energy data in an energy system through sensors and metering equipment; cleaning and integrating the collected energy data to remove abnormal values ​​and duplicate data; storing in an extensible database; analyzing the cleaned and integrated energy data to obtain comprehensive evaluation indicators; adjusting energy consumption in combination with energy storage and energy loss; regulating energy costs according to energy loss; constructing an energy system operation safety model based on the results of data analysis and the adjusted energy data information, monitoring the operating status of energy equipment, and timely discovering abnormal situations and issuing early warnings. The present invention realizes real-time monitoring and optimization of the energy system by collecting, storing and analyzing huge energy data, and timely feedbacks the operating status of the energy system, thereby improving energy utilization efficiency and sustainability.

Description

Technical Field

[0001] The present invention relates to the field of energy monitoring, and in particular to an energy monitoring method based on big data. Background Art

[0002] Modern energy systems are becoming increasingly complex, including multiple links such as energy production, transmission, conversion and use, involving a large amount of data and information, such as energy consumption, load changes, energy efficiency, etc. Energy monitoring refers to the process of real-time or regular data collection, recording and analysis of energy production, transmission, conversion and use in energy systems. Traditional energy monitoring methods are difficult to meet the needs of comprehensive monitoring and analysis of these complex systems, while big data technology can process multi-source, diverse and high-dimensional energy data, providing more comprehensive and accurate energy monitoring and analysis.

[0003] At present, traditional energy monitoring methods mainly rely on manual collection and analysis of energy data, which has problems such as untimely data acquisition and low analysis efficiency; energy consumption and energy costs are not regulated through energy storage and energy loss, and energy data information cannot be considered as a whole for energy monitoring; the monitoring effect is single, and problems cannot be discovered and warned in time, causing the energy system to lose balance and stability.

[0004] Therefore, there is a need for an energy monitoring method based on big data of the present invention. Summary of the invention

[0005] The present invention provides an energy monitoring method based on big data, which aims to achieve real-time monitoring and optimization of the energy system by collecting, storing and analyzing huge energy data, and timely feedback on the operation status of the energy system, thereby improving energy utilization efficiency and sustainability.

[0006] The technical solution of the present invention is specifically as follows:

[0007] An energy monitoring method based on big data includes the following steps:

[0008] S1. Collect energy data from the energy system in real time through sensors and metering equipment; clean and integrate the collected energy data, remove outliers and duplicate data; store in a scalable database;

[0009] S2. Analyze the cleaned and integrated energy data to obtain comprehensive evaluation indicators;

[0010] S3. Adjust energy consumption based on energy storage and energy loss; regulate energy costs based on energy loss;

[0011] S4. Based on the results of data analysis and the adjusted energy data information, build an energy system operation safety model, monitor the operating status of energy equipment, detect abnormal situations in time and issue early warnings.

[0012] Further, step S2 specifically includes:

[0013] The comprehensive evaluation index is calculated based on the acquired historical energy load demand information and energy utilization rate; the comprehensive performance of the energy system is classified into high level, medium level and low level according to the comprehensive evaluation index; and the energy cost is set to Cost1 at the same time.

[0014] Further, step S2 specifically includes:

[0015] The calculation process of comprehensive evaluation indicators is as follows:

[0016]

[0017] Among them, Ind represents the comprehensive evaluation index; a1 and a2 represent the weight values ​​of the predicted energy load demand and energy utilization rate respectively; Ld pre Represents the predicted value of energy load demand at time t; Ld utr Represents the energy utilization rate at time t.

[0018] Furthermore, the energy consumption after adjustment in step S3 is calculated as follows:

[0019]

[0020] Among them, Cons' represents the adjusted energy consumption; Cons0 represents the energy consumption recorded in the energy system; Loss represents the energy loss ratio; γ is a positive adjustment parameter used to balance the impact of changes in energy storage on energy consumption; ΔE s Represents the change in energy storage in time period Tim.

[0021] Further, step S3 specifically includes:

[0022] According to the energy loss, monitoring and control obtain the energy cost correction coefficient OP and compensate the energy cost.

[0023] Furthermore, when compensating for energy costs: the energy cost correction factor is compared with the predefined energy cost correction factor OP pre Compare and compensate the energy cost according to the comparison results. The specific process is as follows:

[0024] If OP≥OP pre , then the energy cost to be compensated is Cost2,

[0025] If OP <OP pre , then the energy cost to be compensated is Cost2,

[0026] Further, in step S4, the energy system operation safety model is constructed, and the specific process is as follows:

[0027]

[0028]

[0029] Among them, H put represents the output result of the energy system operation security model; σ represents the activation function; b represents the bias; ω y Represents the weight coefficient of the yth layer; represents the data input of the yth layer; Y represents the total number of layers of the multilayer perceptron, y∈[1,Y]; bi represents the adjustment factor; pi represents the balance factor; Attention(Inf E , G) represents the optimized attention mechanism; the corrected energy consumption, compensated energy cost and other related energy information are E tal , represents the feature matrix of the input energy information; G represents the additional attention guide matrix introduced; softmax represents the activation function, which converts a vector containing any real number into a probability distribution; Q represents the query matrix; K represents the key matrix; V represents the value matrix; d k Represents the dimension of the key vector, which is used to scale the dot product to prevent the gradient of the softmax function from being too small.

[0030] Beneficial effects:

[0031] 1. The present invention can objectively evaluate the overall performance of the energy system through comprehensive evaluation indicators. The comprehensive evaluation indicators take into account multiple key factors such as energy load demand and energy utilization rate, and provide a comprehensive evaluation of the energy system in terms of energy supply and utilization; making the evaluation results more intuitive and comparable, and being able to better understand the actual situation of the energy system and make comparisons and analyses, thereby promoting the optimization and upgrading of the energy system and improving energy utilization efficiency.

[0032] 2. The present invention can optimize energy utilization efficiency and reduce energy consumption costs by rationally managing and utilizing the energy storage system; and by monitoring the dynamic changes of energy storage and energy loss, it can adjust energy consumption in real time to minimize energy waste and loss; by making adjustments based on energy storage and loss conditions, it can maintain the balance and stability of the energy system and ensure continuous energy supply and safe operation.

[0033] By monitoring energy loss and compensating energy costs based on the obtained energy cost correction coefficient, cost optimization can be achieved and more accurate energy cost measurement can be provided; energy loss is the loss and waste in the energy system. By monitoring and controlling energy loss, energy costs can be reduced and the economic benefits of energy can be improved; it helps to achieve accurate energy cost accounting and management, provide reliable energy cost data to support decision-making and evaluation, and take corresponding measures for optimization and management.

[0034] 3. By establishing an energy system operation safety model, the present invention can learn a more robust and generalized feature representation to adapt to different energy system scenarios and changes, and improve the prediction accuracy and stability on unseen data; the multilayer perceptron is a powerful neural network model with excellent modeling capabilities when processing nonlinear and complex energy system data. It can learn nonlinear relationships and patterns in input data and capture key features of energy system operation safety; the attention mechanism enables the model to automatically focus on important parts of the input data related to the energy system operation safety; the combination of the multilayer perceptron and the attention mechanism helps to achieve monitoring of the safe operation and optimized management of the energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of an energy monitoring method based on big data of the present invention;

[0036] Figure 2 This is a module diagram of an energy monitoring system based on big data of the present invention. DETAILED DESCRIPTION

[0037] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0038] See attached Figure 1 , this embodiment provides an energy monitoring method based on big data, comprising the following steps:

[0039] S1. Collect data of various energy sources in the energy system in real time, including energy consumption, energy output, energy conversion efficiency, etc., through sensors, metering equipment, etc.; transmit to the data storage server by wired or wireless means, and store the collected energy data in a scalable database to ensure data security and accessibility. The data storage server can have high capacity and high reliability to cope with a large number of data storage needs. Clean and integrate the collected energy data, remove outliers and duplicate data, and make the data consistent and comparable. This helps to improve the accuracy and reliability of subsequent data analysis.

[0040] S2. Use big data analysis algorithms and models to conduct statistical, correlation and predictive analysis on the cleaned and integrated energy data.

[0041] The energy-related data is analyzed to obtain a comprehensive evaluation index, which is divided into different levels according to the value of the comprehensive evaluation index. In this embodiment, the comprehensive evaluation index is calculated based on the historical energy load demand information and energy utilization rate obtained. The specific process is as follows:

[0042]

[0043] Among them, Ind represents the comprehensive evaluation index; a1 and a2 represent the weight values ​​of the predicted energy load demand and energy utilization rate respectively; Ld pre Represents the predicted value of energy load demand at time t; Ld utr Represents the energy utilization rate at time t. Among them, σ utr , σ pre Represent the standard deviation of the recorded energy load demand and energy utilization rate, respectively.

[0044] The comprehensive performance of the energy system is divided into high, medium and low levels through comprehensive evaluation indicators; and the energy cost and energy consumption are set according to the performance level. Specifically, the energy cost under standard conditions is defined as Cost, and the energy consumption under standard conditions is defined as Cons. The specific process is as follows:

[0045] If the comprehensive performance evaluation index of the energy system is above 90% (including equal to 90%) and belongs to the high level, the energy cost is set to Cost1, Cost1 = β1*Cost;

[0046] If the comprehensive performance evaluation index of the energy system is between 70% and 90% (including 70%), which is a medium level, the energy cost is set to Cost1, Cost1 = β2*Cost;

[0047] If the comprehensive performance evaluation index of the energy system is below 70% and is at a low level, the energy cost is set to Cost1, Cost1 = β3*Cost; where β1, β2, and β3 represent the corresponding high-level, medium-level, and low-level adjustment coefficients, respectively; β1, β2, and β3>0.

[0048] The present invention can objectively evaluate the overall performance of the energy system through comprehensive evaluation indicators. The comprehensive evaluation indicators take into account multiple key factors such as energy load demand and energy utilization rate, and provide a comprehensive evaluation of the energy system in terms of energy supply and utilization; making the evaluation results more intuitive and comparable, and being able to better understand the actual situation of the energy system and make comparisons and analyses, thereby promoting the optimization and upgrading of the energy system and improving energy utilization efficiency.

[0049] S3. Adjust energy consumption based on energy storage and energy loss; regulate energy costs based on energy loss.

[0050] Energy consumption is regulated based on energy storage and energy loss. Energy storage refers to the capacity or scale that can be used to store energy.

[0051] The dynamic change of energy storage refers to the change of energy inflow and outflow in the energy storage system over time. The stored energy may change due to energy input, output and loss. The calculation process is:

[0052]

[0053] Among them, ΔE s represents the change of energy storage in time period Tim, t∈[0,Tim]; E in represents the total expected energy input; m represents the number of different sensor locations in the energy storage system; E n' Indicates the amount of energy obtained at the n'th position; E n represents the amount of energy obtained at the nth location; vir represents the external influence; Sp represents the average flow rate during the energy storage process; e l Represents the energy loss coefficient.

[0054] Calculate the adjusted energy consumption as follows:

[0055]

[0056] Among them, Cons' represents the adjusted energy consumption; Cons0 represents the energy consumption recorded in the energy system; Loss represents the energy loss ratio; γ is a positive adjustment parameter used to balance the impact of changes in energy storage on energy consumption.

[0057] Then, according to the energy loss, monitoring and control are used to obtain the energy cost correction coefficient, and the energy cost is compensated. The specific process is as follows:

[0058]

[0059] Where OP is the energy cost correction factor; P is the energy market price; τ(t) is the time-dependent function; and eff is the energy conversion efficiency.

[0060] The energy cost correction factor is compared with the predefined energy cost correction factor OP pre Compare and accurately compensate energy costs based on the comparison results. The specific process is as follows:

[0061] If OP≥OP pre , then the energy cost to be compensated is Cost2,

[0062] If OP <OP pre , then the energy cost to be compensated is Cost2,

[0063] The present invention can optimize energy utilization efficiency and reduce energy consumption costs by rationally managing and utilizing the energy storage system; and by monitoring the dynamic changes of energy storage and energy loss, it can adjust energy consumption in real time to minimize energy waste and loss; by making adjustments based on energy storage and loss conditions, it can maintain the balance and stability of the energy system and ensure continuous energy supply and safe operation.

[0064] By monitoring energy loss and compensating energy costs based on the obtained energy cost correction coefficient, cost optimization can be achieved and more accurate energy cost measurement can be provided; energy loss is the loss and waste in the energy system. By monitoring and controlling energy loss, energy costs can be reduced and the economic benefits of energy can be improved; it helps to achieve accurate energy cost accounting and management, provide reliable energy cost data to support decision-making and evaluation, and take corresponding measures for optimization and management.

[0065] S4. Based on the results of data analysis and adjusted energy data information, realize real-time monitoring of energy utilization, monitor the operating status of energy equipment, promptly detect abnormal situations and issue early warnings, promptly notify relevant personnel and take measures to make adjustments and repairs.

[0066] The results of the analysis can be displayed in a visual way through the result display interface, so that the staff can intuitively understand the operation status and effects of the energy system.

[0067] In this embodiment, according to the adjusted energy consumption and energy cost, combined with other relevant energy information, an energy system operation safety model is constructed. By introducing a multi-layer perceptron and an attention mechanism, it can better adapt to different energy system scenarios and changes, and improve the stability of the energy monitoring process. The specific process is as follows:

[0068]

[0069]

[0070] Among them, H put represents the output result of the energy system operation security model; σ represents the activation function; b represents the bias; ω y Represents the weight coefficient of the yth layer; represents the data input of the yth layer; Y represents the total number of layers of the multilayer perceptron, y∈[1,Y]; bi represents the adjustment factor; pi represents the balance factor; Attention(Inf E , G) represents the optimized attention mechanism; the corrected energy consumption, compensated energy cost and other related energy information are E tal , represents the feature matrix of the input energy information; G represents the additional attention guide matrix introduced; softmax represents the activation function, which converts a vector containing any real number into a probability distribution; Q represents the query matrix; K represents the key matrix; V represents the value matrix; d k Represents the dimension of the key vector, which is used to scale the dot product to prevent the gradient of the softmax function from being too small.

[0071] By establishing an energy system operation safety model, the present invention can learn a more robust and generalized feature representation to adapt to different energy system scenarios and changes, and improve the prediction accuracy and stability on unseen data; the multilayer perceptron is a powerful neural network model with excellent modeling capabilities when processing nonlinear and complex energy system data, and can learn nonlinear relationships and patterns in input data and capture key features of energy system operation safety; the attention mechanism enables the model to automatically focus on important parts of the input data related to the energy system operation safety; the combination of the multilayer perceptron and the attention mechanism helps to achieve monitoring of the safe operation and optimized management of the energy system.

[0072] See attached Figure 2 , this embodiment provides an energy monitoring system based on big data, including the following contents:

[0073] Data acquisition and processing module, comprehensive evaluation index module, energy consumption adjustment module, energy cost correction module, energy cost compensation module, system operation safety module;

[0074] The data acquisition and processing module is responsible for acquiring energy-related data from various data sources, such as energy consumption data, load data, energy production data, etc.; collecting real-time data through sensors, smart meters, monitoring equipment, etc., and processing and cleaning the data to ensure the accuracy and integrity of the data;

[0075] The comprehensive evaluation index module generates comprehensive evaluation indicators by analyzing and calculating energy data, helping staff understand the operating status and efficiency level of the energy system and providing support for subsequent analysis;

[0076] The energy consumption adjustment module adjusts energy consumption based on data analysis results, combined with energy storage and energy loss, and optimizes the allocation and scheduling of energy consumption to achieve rational use and conservation of energy;

[0077] The energy cost correction module obtains the energy cost correction coefficient based on energy loss and other energy-related information, performs cost correction on energy cost data, and takes into account the fluctuation of actual energy prices and changes in cost factors as a whole to provide more accurate energy cost data;

[0078] Energy cost compensation module, which provides suggestions and strategies for energy cost compensation by analyzing energy cost correction coefficients and pre-defined energy cost correction coefficients to reduce energy costs and improve benefits;

[0079] The system operation safety module is used to monitor the operating status and safety of the energy system, and promptly identify and report potential risks and failures. It provides early warning and fault diagnosis functions through real-time monitoring and anomaly detection of energy data, helping to ensure the safe operation of the energy system.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0084] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. An energy monitoring method based on big data, characterized in that: The following steps are involved: S1. Collect energy data from the energy system in real time through sensors and metering equipment; clean and integrate the collected energy data, remove outliers and duplicate data; store in a scalable database; S2. Analyze the cleaned and integrated energy data to obtain comprehensive evaluation indicators; S3. Adjust energy consumption based on energy storage and energy loss; regulate energy costs based on energy loss; Where, ΔE s represents the change of energy storage in time period Tim, t∈[0,Tim]; E in represents the total expected energy input; m represents the number of different sensor locations in the energy storage system; E n' Indicates the amount of energy obtained at the n'th position; E n represents the amount of energy obtained at the nth location; vir represents the external influence; Sp represents the average flow rate during the energy storage process; e l represents the energy loss coefficient; Among them, Cons' represents the adjusted energy consumption; Cons0 represents the energy consumption recorded in the energy system; Loss represents the energy loss ratio; γ is a positive adjustment parameter used to balance the impact of changes in energy storage on energy consumption; According to energy loss, monitoring and control obtain the energy cost correction coefficient to compensate for energy costs. The specific process is as follows: Where OP represents the energy cost correction coefficient; P represents the energy market price; τ(t) represents the time-dependent function; eff represents the energy conversion efficiency; S4. Based on the results of data analysis and the adjusted energy data information, build an energy system operation safety model, monitor the operating status of energy equipment, and promptly detect abnormal situations and issue early warnings; Among them, H put represents the output result of the energy system operation security model; σ represents the activation function; b represents the bias; ω y Represents the weight coefficient of the yth layer; represents the data input of the yth layer; Y represents the total number of layers of the multilayer perceptron, y∈[1,Y]; bi represents the adjustment factor; pi represents the balance factor; Attention(Inf E , G) represents the optimized attention mechanism; the corrected energy consumption, compensated energy cost and other related energy information are E tal , represents the feature matrix of the input energy information; G represents the additional attention guide matrix introduced; softmax represents the activation function, which converts a vector containing any real number into a probability distribution; Q represents the query matrix; K represents the key matrix; V represents the value matrix; d k Represents the dimension of the key vector, which is used to scale the dot product to prevent the gradient of the softmax function from being too small.

2. The energy monitoring method based on big data according to claim 1 is characterized in that: The step S2 specifically includes: The comprehensive evaluation index is calculated based on the acquired historical energy load demand information and energy utilization rate; the comprehensive performance of the energy system is classified into high level, medium level and low level according to the comprehensive evaluation index; and the energy cost is set to Cost1 at the same time.

3. The energy monitoring method based on big data according to claim 2 is characterized in that: The step S2 specifically includes: The calculation process of the comprehensive evaluation index is as follows: Among them, Ind represents the comprehensive evaluation index; a1 and a2 represent the weight values ​​of the predicted energy load demand and energy utilization rate respectively; Ld pre Represents the predicted value of energy load demand at time t; Ld utr Represents the energy utilization rate at time t.

4. The energy monitoring method based on big data according to claim 1 is characterized in that: When compensating for energy costs: The energy cost correction factor is compared with the predefined energy cost correction factor OP pre Compare and compensate the energy cost according to the comparison results. The specific process is as follows: If OP≥OP pre , then the energy cost to be compensated is Cost2, If OP <OP pre , then the energy cost to be compensated is Cost2,

Images