A method and system for evaluating energy consumption of public institutions

Abstract

The present invention relates to the field of public institution energy consumption evaluation, and in particular to a public institution energy consumption evaluation method and system, including collecting energy use data of public institutions through sensors and monitoring equipment, and performing data preprocessing; combining the preprocessed public institution energy data, establishing a public institution energy consumption identification neural network model, and performing energy consumption identification based on deep learning training neural network model; evaluating the energy efficiency of public institutions according to the energy consumption identification analysis results, introducing an energy efficiency evaluation model, and providing support for energy management decisions of public institutions; comprehensively evaluating the overall energy consumption of public institutions in combination with the public institution energy efficiency evaluation results; providing energy-saving suggestions and measures for public institutions based on the results of energy consumption analysis and comprehensive evaluation, and formulating effective energy management strategies. The present invention realizes a comprehensive evaluation of the energy consumption of public institutions and provides decision-making support for energy conservation and environmental protection.

Description

Technical Field

[0001] The present invention relates to the field of energy conservation evaluation of public institutions, and in particular to a method and system for evaluating energy consumption of public institutions. Background Art

[0002] With the intensification of the global energy crisis and the growing concern for environmental protection, energy consumption issues in public institutions have become increasingly prominent, including government agencies, schools, hospitals, etc. For example: turning on lights, air conditioners and heating equipment for a long time, even when no one is around or during non-working hours, leads to unnecessary energy consumption and increased costs; many public institutions' equipment and facilities may be aging and worn, and these equipment are usually not energy-efficient, and have high energy consumption and low efficiency, resulting in energy waste and unnecessary energy consumption; the lack of measures to monitor, analyze and adjust energy use leads to excessive energy consumption and failure to realize energy saving potential.

[0003] The existing technology for energy consumption evaluation of public institutions still has the following problems: the processing of raw data is too simple, and key variables related to energy consumption are ignored, resulting in poor accuracy of evaluation results, and unable to provide comprehensive data support for energy consumption evaluation methods of public institutions; it is difficult to monitor and identify energy consumption, unable to discover and solve energy waste problems in a timely manner, and unable to discover abnormal situations in the energy consumption process, resulting in unnecessary consumption of resources; it is impossible to make a comprehensive evaluation of the energy consumption of public institutions through energy consumption identification and analysis of public institutions and energy efficiency evaluation results, resulting in public institutions being unable to clarify their goals, resulting in energy management lacking direction and specificity, and missing opportunities to reduce energy consumption and improve energy efficiency.

[0004] In order to effectively evaluate and manage the energy consumption of public institutions, it is necessary to design a public institution energy consumption evaluation method and system. Summary of the invention

[0005] The present invention provides a method and system for evaluating energy consumption of public institutions, which aims to collect, analyze and integrate energy consumption data of public institutions, realize comprehensive evaluation of energy consumption of public institutions, and provide decision support for energy conservation and environmental protection; through accurate data processing, public institution energy consumption identification model, comprehensive energy consumption evaluation, and optimization of energy management strategies, continuous improvement and optimization can be achieved.

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

[0007] A method for evaluating energy consumption of a public institution comprises the following steps:

[0008] S1. Collect energy usage data of public institutions through sensors and monitoring equipment installed in public institutions, pre-process the data, and transmit it to the central server through Internet technology;

[0009] S2. Combine the pre-processed public institution energy data to establish a public institution energy consumption identification neural network model, and train the public institution energy consumption identification neural network model based on deep learning to perform energy consumption identification;

[0010] S3. Based on the results of energy consumption identification and analysis, evaluate the energy efficiency of public institutions and introduce energy efficiency evaluation models to provide support for energy management decisions of public institutions; conduct a comprehensive evaluation of the overall energy consumption of public institutions in combination with the results of energy efficiency evaluation of public institutions;

[0011] S4. Based on the results of energy consumption analysis and comprehensive evaluation, provide energy-saving suggestions and measures to public institutions and formulate effective energy management strategies.

[0012] Further, step S1 specifically includes:

[0013] The preprocessing includes data enhancement, interpolation correction, data mixing and data fusion operations.

[0014] Further, step S2 specifically includes:

[0015] The public institution energy consumption identification neural network model includes an input layer, a fully connected layer, an analysis layer, a judgment layer, and an output layer; the energy usage data features of the public institution that need to be identified are input into the input layer of the public institution energy consumption identification neural network model, and the data information is defined to have a total of Q features, wherein the input layer and the analysis layer transmit feature information through the fully connected layer, and the public institution energy consumption data is analyzed in the analysis layer; the analysis result of the analysis layer is transmitted to the judgment layer, and the energy consumption situation of the public institution is judged and identified; the judgment layer transmits the judgment result to the output layer, and the output layer outputs the output result of the public institution energy consumption identification neural network model.

[0016] Further, step S3 specifically includes:

[0017] The energy efficiency evaluation model Model, Model = {Ta E ,Ty,Fau,Bd,Fic};

[0018] Among them, E represents the total amount of energy obtained by public institutions; Ty represents the type of energy consumption of public institutions, ty N It represents the total number of types involved; Fau represents the fault conditions of the energy system of the public institution; Fic represents the evaluation results of energy efficiency; Bd represents the collection of building or equipment information of the public institution.

[0019] Further, in step S3,

[0020]

[0021] Among them, G stion represents the correlation between different energy types of public institutions; dem represents the total energy demand of public energy institutions obtained from historical data; cor represents the evaluation correction parameter of energy efficiency; Inf(Bd) represents the impact function of building or equipment information of public institutions on energy efficiency; α Fau represents the sensitivity of the public institution's energy system to fault conditions; t fin Indicates the selected end time node; t act Indicates the selected start time node; LI represents the output result of the public institution energy consumption identification neural network model.

[0022] Furthermore, a comprehensive evaluation of the overall energy consumption of public institutions is conducted:

[0023]

[0024] Among them, Com represents the comprehensive evaluation value of energy consumption evaluation of public institutions; Represents the characteristic coefficient of the energy evaluation system; δ 0 Re(l) represents the energy consumption weight of public institutions; Re(l) represents the evaluation function, which is used to quantitatively evaluate the energy consumption.

[0025] A public institution energy consumption evaluation system includes the following parts:

[0026] Energy information acquisition module, data processing module, energy consumption identification module, energy efficiency assessment module, comprehensive evaluation module, and decision support module;

[0027] An energy information acquisition module is used to collect energy information of public institutions, including energy consumption data, energy sources, and energy costs; interact with energy metering equipment, sensors, and energy suppliers to obtain energy consumption data in real time and pass it to the data processing module;

[0028] The data processing module receives the data provided by the energy information acquisition module and performs pre-processing operations such as data cleaning, feature extraction, data enhancement, correction and improvement, and data fusion to extract useful information and features, in preparation for the subsequent energy consumption identification module, energy efficiency assessment module, and comprehensive evaluation module;

[0029] The energy consumption identification module uses the data provided by the data processing module to identify and judge the energy consumption of public institutions, analyze and model the energy consumption data, and generate corresponding identification results; the model output results are transmitted to the energy efficiency assessment module;

[0030] Energy efficiency assessment module, which assesses the energy efficiency of public institutions, uses energy data information to calculate energy efficiency, and transmits the assessment results to the comprehensive evaluation module;

[0031] The comprehensive evaluation module comprehensively considers the results of energy consumption identification and energy efficiency assessment to evaluate the overall energy consumption of public institutions and provide a basis for decision-making;

[0032] The decision-making support module provides energy consumption optimization suggestions and measures based on the results of the energy consumption identification module, energy efficiency assessment module and comprehensive evaluation module, formulates energy management strategies, and helps decision makers make reasonable energy consumption management decisions.

[0033] Beneficial effects:

[0034] 1. The present invention can supplement or correct these missing or abnormal values ​​through interpolation correction, reduce errors in the data processing process, and make the data more credible and usable; the feature set of public institution energy use data obtained after interpolation correction is mixed and improved, which is helpful to extract more comprehensive feature representation, capture more details and change patterns of public institution energy consumption data, and improve the accuracy and identification ability of evaluation; and then the original data and the mixed and improved data are merged, which is helpful to more accurately analyze and evaluate the energy consumption of public institutions, and provide data support for more comprehensive and multi-dimensional energy consumption evaluation.

[0035] 2. The present invention can obtain highly accurate energy consumption identification results by training the public institution energy consumption identification neural network model, eliminates the tedious process of traditional analysis and data processing, and greatly improves the efficiency and accuracy of energy consumption identification; the energy consumption identification results based on the deep learning model can provide customized energy consumption optimization suggestions for public institutions, identify energy-saving potential, provide targeted energy-saving suggestions and measures, and help public institutions achieve continuous improvement in energy management; it can also formulate strategic plans, budget allocations and energy investment decisions based on the analysis results of the model to optimize energy utilization and reduce operating costs; the public institution energy consumption identification neural network model analyzes energy consumption data on a real-time or regular basis. If abnormal energy consumption occurs, the model can detect it in time and trigger an alarm, enabling public institutions to quickly discover and solve energy consumption problems and reduce energy waste.

[0036] 3. Through the identification and analysis of energy consumption of public institutions, the present invention enables managers of public institutions to understand and manage energy consumption, and identify abnormal situations and issue alarms. The introduction of the energy efficiency evaluation model provides a scientific evaluation method, which can quantitatively evaluate energy efficiency and provide support for energy management decisions of public institutions. According to the results of energy efficiency evaluation, public institutions can formulate corresponding energy management strategies and measures to improve energy efficiency and reduce energy consumption, thereby saving energy costs. By combining the results of energy efficiency evaluation of public institutions, a comprehensive evaluation of the overall energy consumption of public institutions can be conducted, the overall situation of their own energy consumption can be understood, and directions for improvement and optimization can be provided for public institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of a method for evaluating energy consumption of a public institution according to the present invention;

[0038] Figure 2 This is a module diagram of a public institution energy consumption evaluation system of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] See attached Figure 1 This embodiment provides a method for evaluating energy consumption of a public institution, comprising the following steps:

[0041] S1. Collect energy usage data of public institutions through sensors and monitoring equipment installed in public institutions, process the data, and transmit it to the central server through Internet technology.

[0042] Through sensors and monitoring equipment installed in various areas of public institutions, including smart meters, temperature sensors, humidity sensors, etc., energy usage data of various energy-consuming equipment in public institutions, such as lighting, air conditioning, heating, etc., real-time collection of various energy consumption data such as electricity, water resources, gas, etc., and transmission to the central server through the Internet (IoT) technology. Specifically, it involves electricity consumption, water resource consumption, gas consumption, fuel consumption, renewable energy utilization and other aspects.

[0043] The energy usage data of public institutions obtained are preprocessed. First, data cleaning is performed to check whether there are missing values, outliers or erroneous data in the data, and they are handled according to the situation. Noise data may still exist after data cleaning. Filters are used to smooth the data to remove noise interference and improve data quality. Then, the data after preliminary processing is converted and compressed to extract feature information that is valuable for the analysis task. Feature extraction methods can be applied, such as principal component analysis, wavelet transform, frequency domain analysis, etc., to convert the data into more representative feature vectors.

[0044] In the process of data enhancement, it is very important to ensure the quality and authenticity of the data. In order to reduce the error in the data processing process, data processing correction is performed; the feature set of the enhanced public institution energy usage data is defined as D, which contains n data points, and each data point is represented by (x i ,y i ), where i = 1, 2, ..., n; perform interpolation correction on any data point x and find its s nearest neighbor points. The specific process is as follows:

[0045]

[0046] Li(x)=Π[(x j ) / (x i -x j )]

[0047] Where f(x) represents the target value of the data point x after interpolation correction; Li(x) represents the Lagrange basis function; α i Represents the smoothing coefficient, which is used to control the smoothness of the interpolation; x j Represents the horizontal coordinates of other known data points involved in the interpolation calculation, i≠j.

[0048] Furthermore, the smoothing coefficient can adjust the interpolation to be smoother or closer to the original data point; generally, the larger the smoothing coefficient, the smoother the interpolation result; the smaller the smoothing coefficient, the closer the interpolation result is to the original data.

[0049] F represents the feature set of public institution energy usage data obtained after interpolation correction, and hybrid enhancement is performed at the same time, because the interpolation correction processing can provide more accurate local information, while the original public institution energy usage data can provide more global background information; the specific data hybrid enhancement process is as follows:

[0050]

[0051] Among them, T represents the data after hybrid enhancement; c represents the total number of adjacent points; γ represents the hybrid influence factor; Aq represents the Qth nearest neighbor point to the data point x after interpolation correction.

[0052] The original institutional energy usage data is then combined with the corrected, hybridized data as follows:

[0053]

[0054] Among them, Z represents the fused data; X t represents the original institutional energy usage data at time t; δ represents the fusion parameter, which is used to control the weight between the original data and the corrected mixed data; Represents a constant adjustment parameter to ensure a smooth fusion process.

[0055] The present invention can supplement or correct these missing or abnormal values ​​through interpolation correction, reduce errors in the data processing process, and make the data more credible and usable; the feature set of public institution energy use data obtained after interpolation correction is mixed and improved, which is helpful to extract more comprehensive feature representation, capture more details and change patterns of public institution energy consumption data, and improve the accuracy and identification ability of evaluation; and then the original data and the mixed and improved data are merged, which is helpful to more accurately analyze and evaluate the energy consumption of public institutions, and provide data support for more comprehensive and multi-dimensional energy consumption evaluation.

[0056] S2. Use data analytics and deep learning methods to analyze the energy usage data of public institutions by comparing energy data across different time periods and between different devices, so as to further evaluate and optimize the energy usage of public institutions.

[0057] A neural network model for identifying energy consumption in public institutions is established. Energy consumption is identified based on the further processed energy usage data of public institutions. The neural network model for identifying energy consumption in public institutions is trained based on deep learning, which includes an input layer, a fully connected layer, an analysis layer, a judgment layer, and an output layer.

[0058] The energy usage data features of public institutions that need to be identified are input into the input layer of the public institution energy consumption identification neural network model. The data information is defined to have a total of Q features. The input layer and the analysis layer transmit feature information through the fully connected layer. The energy consumption data of public institutions are analyzed in the analysis layer. The specific process is as follows:

[0059] Ih 1 =ω 1 Data g +b 1

[0060]

[0061] Among them, Ih 1 Represents the input of the analysis layer; ω 1 Represents the weight value of the input layer and the analysis layer; Data g represents the g-th feature data of the analysis layer input, g∈[1,Q]; b 1 Indicates the bias of the analysis layer; Lm 1 Represents the output of the analysis layer; R represents the total number associated with the dth unit. Specifically, each different type of energy consumption point is regarded as a unit; Ti represents the recorded time period, l represents a certain moment, l∈[0,Ti]; Represents the qth type of energy consumption sample data in the input feature information; represents the p-th energy consumption sample data in the input feature information; γ represents the coefficient of the control kernel function width; τ represents the energy attenuation parameter in the public institution energy consumption system; V co It represents the energy usage rate; Are represents the area of ​​public institutions radiated by different types of energy.

[0062] The analysis results of the analysis layer are transferred to the judgment layer to identify the energy consumption of public institutions, find out the abnormal energy consumption, and customize reasonable energy consumption management strategies to reduce energy consumption costs and improve energy efficiency. The specific process is as follows:

[0063] Ih 2 =ω 2 Lm 1 +b 2

[0064]

[0065] Among them, Ih 2 Represents the input of the judgment layer; ω 2 Indicates the weight value of the analysis layer and the judgment layer; b 2 Indicates the bias of the judgment layer; Lm 2 Represents the output of the judgment layer; Sr 0 represents the learning factor; cy represents the energy efficiency index of the public institution; rat represents the proportionality coefficient; ef represents the initial cost of energy for the public institution; represents the average price of the ρth type of energy during the recording period; β represents the energy price volatility coefficient; y u Indicates the impact of environmental factors on energy consumption in public institutions; represents the energy utilization rate of public institutions; ε represents the pre-set threshold of the judgment layer, which is derived based on historical experimental data and the expert experience of energy managers of public institutions.

[0066] If the output result is 1, it means that the energy consumption of the public institution is normal and the status quo can be maintained and the operation and maintenance work can be completed on time; if the output result is -1, it means that the energy consumption of the public institution is abnormal, which may involve energy consumption exceeding the expected range, energy utilization efficiency decline, energy waste and other problems. At the same time, an alarm will be triggered and an abnormal report will be sent to remind relevant personnel to pay attention and take corresponding actions in time. This means that the energy consumption of public institutions has certain fluctuations, but is still within an acceptable range, and the corresponding results will be output.

[0067] The judgment layer transmits the judgment result to the output layer, and finally the output layer outputs the output result of the public institution energy consumption identification neural network model. The specific process is as follows:

[0068] LI=ω 3 Lm 2 +b 3

[0069] Among them, LI represents the output result of the output layer; ω 3 Represents the weight value of the judgment layer and the output layer; b 3 Represents the bias of the output layer.

[0070] By training the public institution energy consumption identification neural network model, the present invention can obtain highly accurate energy consumption identification results, eliminate the cumbersome process of traditional analysis and data processing, and greatly improve the efficiency and accuracy of energy consumption identification; the energy consumption identification results based on the deep learning model can provide customized energy consumption optimization suggestions for public institutions, identify energy-saving potential, provide targeted energy-saving suggestions and measures, and help public institutions achieve continuous improvement in energy management; it can also formulate strategic plans, budget allocations and energy investment decisions based on the analysis results of the model to optimize energy utilization and reduce operating costs; the public institution energy consumption identification neural network model analyzes energy consumption data on a real-time or regular basis. If abnormal energy consumption occurs, the model can detect it in time and trigger an alarm, so that public institutions can quickly discover and solve energy consumption problems and reduce energy waste.

[0071] S3. Based on the results of energy consumption identification and analysis, the energy efficiency of public institutions is evaluated, and an energy efficiency evaluation model is introduced to provide support for energy management decisions of public institutions; combined with the results of energy efficiency evaluation of public institutions, a comprehensive evaluation of the overall energy consumption of public institutions is conducted.

[0072] Based on the results of energy consumption identification and analysis, the energy efficiency of public institutions is evaluated and an energy efficiency evaluation model is introduced to provide support for energy management decisions of public institutions and promote the improvement of energy efficiency. The calculation process is as follows:

[0073] Model = {TaE ,Ty,Fau,Bd,Fic}

[0074] Among them, E represents the total amount of energy obtained by public institutions; Ty represents the type of energy consumption of public institutions, ty N It represents the total number of types involved, including electricity consumption, water consumption, gas consumption, fuel consumption, and renewable energy utilization. Fau represents the failure of the energy system of public institutions. Fic represents the evaluation results of energy efficiency. Bd represents the collection of building or equipment information of public institutions, for example, the insulation performance of the building's exterior walls, window types, roof materials, etc. can affect the building's thermal insulation and airtightness, thereby affecting the stability of indoor temperature and energy consumption. The equipment and devices used in the building, such as lighting equipment, household appliances, heating equipment, etc., have a direct impact on energy efficiency. Equipment with higher energy efficiency can reduce energy consumption and reduce the overall energy consumption of the building.

[0075]

[0076]

[0077] Among them, G stion represents the correlation between different energy types in public institutions; Ti represents the time period recorded; θ 1 represents the step size parameter, which is used to control the update speed in each iteration; θ 2 represents the responsiveness of different types of energy to the energy system of public institutions; θ 3 represents the regulatory parameter regulating the correlation; O zl represents the utilization rate of type z energy at time l; ml represents the utilization rate of type m energy at time l; dem represents the total energy demand of the public energy agency obtained from historical data; cor represents the evaluation correction parameter of energy efficiency; Inf(Bd) represents the impact function of the building or equipment information of the public agency on energy efficiency; α Fau represents the sensitivity of the public institution's energy system to fault conditions; t fin Indicates the selected end time node; t act Indicates the selected start time node.

[0078] Furthermore, the comprehensive evaluation value Com of the energy consumption evaluation of public institutions is calculated as follows:

[0079]

[0080] in, Represents the characteristic coefficient of the energy evaluation system; δ 0Represents the energy consumption weight of public institutions; Re(l) represents the evaluation function, which is used to quantitatively evaluate the energy consumption.

[0081] Through the identification and analysis of energy consumption of public institutions, the present invention enables managers of public institutions to understand and manage energy consumption, and identify abnormal situations and issue alarms. The introduction of the energy efficiency evaluation model provides a scientific evaluation method, which can quantitatively evaluate energy efficiency and provide support for energy management decisions of public institutions. According to the results of energy efficiency evaluation, public institutions can formulate corresponding energy management strategies and measures to improve energy efficiency and reduce energy consumption, saving energy costs. By combining the results of energy efficiency evaluation of public institutions, the overall energy consumption of public institutions can be comprehensively evaluated, the overall situation of their own energy consumption can be understood, and directions for improvement and optimization can be provided for public institutions.

[0082] S4. Based on the results of energy consumption analysis and comprehensive evaluation, provide public institutions with specific energy-saving suggestions and measures and formulate effective energy management strategies, including improving equipment efficiency, reducing energy waste, and adopting renewable energy.

[0083] In this embodiment, traditional incandescent lamps and fluorescent lamps can be replaced with LED lamps, which have higher energy efficiency and lifespan, and can reduce energy consumption by adjusting the lighting brightness and using sensors to automatically control the switch; ensure that the walls, ceilings, floors and windows of the building have good insulation properties to reduce the conduction and loss of energy, which can be achieved by adding insulation materials, sealing door and window gaps and installing double-layer windows; regularly inspect and maintain the HVAC system, clean and replace air filters to ensure the normal operation of the system, and consider installing high-efficiency heat exchangers, adjusting temperature settings and using intelligent control systems to reduce energy consumption.

[0084] At the same time, it is recommended to use energy-saving office equipment with high energy labels, such as computers, printers and copiers. When not in use, turn off the equipment in time or use energy-saving mode to avoid standby energy consumption. Organize training activities on energy conservation and sustainable development to improve the energy-saving awareness and behavior of public agency staff. It is also necessary to consider installing solar panels or wind power generation equipment on the buildings of public institutions to use renewable energy to partially meet energy needs. In addition, the use of other renewable energy sources such as geothermal energy and biomass energy can be advocated.

[0085] See attached Figure 2 , this embodiment provides a public institution energy consumption evaluation system, including the following contents:

[0086] Energy information acquisition module, data processing module, energy consumption identification module, energy efficiency assessment module, comprehensive evaluation module, and decision support module;

[0087] Energy information acquisition module, which is used to collect energy information of public institutions, including energy consumption data, energy sources, energy costs, etc.; interact with energy metering equipment, sensors, energy suppliers, etc., obtain energy consumption data in real time, and pass it to the data processing module;

[0088] The data processing module receives the data provided by the energy information acquisition module and performs pre-processing operations such as data cleaning, feature extraction, data enhancement, correction and improvement, and data fusion to extract useful information and features, in preparation for the subsequent energy consumption identification module, energy efficiency assessment module, and comprehensive evaluation module;

[0089] The energy consumption identification module uses the data provided by the data processing module to identify and judge the energy consumption of public institutions, analyze and model the energy consumption data, and generate corresponding identification results; the model output results are transmitted to the energy efficiency assessment module;

[0090] Energy efficiency assessment module, which assesses the energy efficiency of public institutions, uses energy consumption data and other relevant information to calculate energy efficiency, and transmits the assessment results to the comprehensive evaluation module;

[0091] The comprehensive evaluation module comprehensively considers the results of energy consumption identification and energy efficiency assessment to evaluate the overall energy consumption of public institutions and provide a basis for decision-making;

[0092] The decision-making support module provides energy consumption optimization suggestions and measures based on the results of the energy consumption identification module, energy efficiency assessment module and comprehensive evaluation module, formulates energy management strategies, and helps decision makers make reasonable energy consumption management decisions.

[0093] 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.

[0094] 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] 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.

[0096] 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.

[0097] 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. A method for evaluating energy consumption of a public institution, characterized in that: The following steps are involved: S1. Collect energy usage data of public institutions through sensors and monitoring equipment installed in public institutions, pre-process the data, and transmit it to the central server through Internet technology; S2. Combine the pre-processed public institution energy data to establish a public institution energy consumption identification neural network model, and train the public institution energy consumption identification neural network model based on deep learning to perform energy consumption identification; S3. Based on the results of energy consumption identification and analysis, evaluate the energy efficiency of public institutions and introduce energy efficiency evaluation models to provide support for energy management decisions of public institutions; The energy efficiency assessment model , ; in, It represents the total amount of energy obtained by public institutions; Indicates the type of energy consumption of public institutions, Indicates the total number of types involved; Indicates fault conditions in the energy systems of public institutions; Indicates the evaluation result of energy efficiency; Represents a collection of building or equipment information for a public institution; ； in, Represents the correlation between different energy types in public institutions; It represents the total energy demand obtained by public energy agencies based on historical data; represents the evaluation correction parameter of energy efficiency; Functions representing the impact of building or equipment information on energy efficiency in public institutions; Indicates the sensitivity of the utility's energy system to failure conditions; Indicates the selected end time node; Indicates the selected start time node; represents the output of the neural network model for energy consumption identification in public institutions; Conduct a comprehensive evaluation of the overall energy consumption of public institutions in combination with the results of the energy efficiency assessment of public institutions; ； in, It represents the comprehensive evaluation value of energy consumption evaluation of public institutions; It represents the characteristic coefficient of the energy evaluation system; represents the energy consumption weight of public institutions; represents the evaluation function, which is used to quantitatively evaluate the energy consumption; Indicates the time period recorded; represents the base of natural logarithms; S4. Based on the results of energy consumption analysis and comprehensive evaluation, provide energy-saving suggestions and measures to public institutions and formulate energy management strategies.

2. A method for evaluating energy consumption of public institutions according to claim 1, characterized in that: The step S1 specifically includes: The data preprocessing includes operations of data enhancement, interpolation correction, data mixing and enhancement, and data fusion.

3. A method for evaluating energy consumption of public institutions according to claim 1, characterized in that: The step S2 specifically includes: The public institution energy consumption identification neural network model includes an input layer, a fully connected layer, an analysis layer, a judgment layer, and an output layer; the public institution energy usage data features to be identified are input into the input layer of the public institution energy consumption identification neural network model, and the data information is defined as The input layer and the analysis layer transmit feature information through the fully connected layer, and the energy consumption data of the public institution is analyzed in the analysis layer; the analysis result of the analysis layer is transmitted to the judgment layer, and the energy consumption of the public institution is judged and identified; the judgment layer transmits the judgment result to the output layer, and the output layer outputs the output result of the public institution energy consumption identification neural network model.

4. A public institution energy consumption evaluation system, applied to a public institution energy consumption evaluation method according to claim 1, characterized in that: Includes the following parts: Energy information acquisition module, data processing module, energy consumption identification module, energy efficiency assessment module, comprehensive evaluation module, and decision support module; The energy information acquisition module is used to collect energy information of public institutions, including energy consumption data, energy sources, and energy costs; interact with energy metering equipment, sensors, and energy suppliers to acquire energy consumption data in real time and pass it to the data processing module; The data processing module receives the data provided by the energy information acquisition module, and performs pre-processing operations such as data cleaning, feature extraction, data enhancement, correction and improvement, and data fusion to extract useful information and features, so as to prepare for the subsequent energy consumption identification module, the energy efficiency assessment module, and the comprehensive evaluation module; The energy consumption identification module uses the data provided by the data processing module to identify and judge the energy consumption of the public institution, analyzes and models the energy consumption data, and generates corresponding identification results; the model output results are transmitted to the energy efficiency evaluation module; The energy efficiency evaluation module evaluates the energy efficiency of public institutions, calculates energy utilization efficiency using energy data information, and transmits the evaluation results to the comprehensive evaluation module; The comprehensive evaluation module comprehensively considers the energy consumption identification and energy efficiency assessment results, evaluates the overall energy consumption of public institutions, and provides a basis for decision-making; The decision support module provides energy consumption optimization suggestions and measures based on the results of the energy consumption identification module, the energy efficiency evaluation module and the comprehensive evaluation module, formulates energy management strategies, and helps decision makers make energy consumption management decisions.

Images