Green and low-carbon monitoring system for energy-saving renovation of old residential communities

Abstract

This invention discloses a green and low-carbon monitoring system for energy-saving renovation of old residential communities, relating to the field of data management and monitoring. It includes: a central control module for deploying a control network and editing and submitting instructions for various functional modules and units; a data acquisition module for collecting the actual energy consumption coefficients and operating settings of power supply, gas supply, and water supply equipment in the area to be renovated within a preset number of cycles; a model building module for constructing and training an energy consumption prediction model, based on the current energy consumption coefficients and operating settings of several devices as input, and outputting the predicted energy consumption coefficients of these devices in the future number of cycles; analyzing historical data, real-time data, and external environmental variables, dynamically updating prediction results and adjustment strategies, accurately predicting energy consumption trends in future cycles, adjusting renovation strategies in a timely manner, identifying potential energy-saving opportunities, analyzing future carbon emission losses from renovations, and helping managers identify potential energy-saving potential and emission reduction paths.

Description

Technical Field

[0001] This invention relates to the field of data management and monitoring technology, specifically to a green and low-carbon monitoring system for energy-saving renovation of old residential communities. Background Technology

[0002] Older residential communities often suffer from outdated facilities, leading to significant energy waste. Energy-saving renovations and carbon emission monitoring in these communities are crucial for achieving sustainable development. They can optimize energy utilization efficiency, reduce unnecessary resource consumption, alleviate the economic burden on residents, and improve resource utilization efficiency across the entire region. With the development of smart technologies, carbon emission monitoring in older residential communities can be integrated with technologies such as the Internet of Things and big data analytics to form an intelligent monitoring and management system. Through real-time data monitoring and analysis, community managers can allocate resources more scientifically, optimize management strategies, and improve management efficiency and economic benefits.

[0003] Existing technologies often monitor carbon emissions separately for projects such as power supply, water supply, and gas supply, lacking multi-dimensional analysis and cross-system integration capabilities. This makes it difficult to comprehensively analyze the use of various energy sources, reducing the potential for energy conservation. Moreover, most technologies only analyze anomalies in existing data, lacking analysis of abnormal carbon emissions caused by future cycles and energy-saving retrofits. This limits the data in the present, leading to the influence of "pseudo-normal" equipment on the final retrofit strategy. Some equipment in normal operating condition may mask potential energy-saving opportunities, making it difficult to effectively predict and intervene in the future energy consumption trends of certain energy-consuming equipment.

[0004] Furthermore, it lacks adaptive capabilities and is not easy to dynamically adjust and optimize based on actual operating data, resulting in poor effectiveness of subsequent energy-saving renovation measures. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a green and low-carbon monitoring system for energy-saving renovation of old residential communities, which can effectively solve the problems of the existing technology.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] This invention discloses a green and low-carbon monitoring system for energy-saving renovation of old residential communities, comprising:

[0010] The central control module is used to deploy and manage the internal network, and to edit and submit instructions for various functional modules and units;

[0011] The data acquisition module is used to collect the actual energy consumption coefficients and operating settings of the power supply, gas supply and water supply equipment in the area to be upgraded within a preset number of cycles.

[0012] The threshold setting module is used to define standard energy consumption coefficient thresholds based on the initial operating settings of the power supply, gas supply, and water supply equipment to be modified.

[0013] The model building module is used to build and train the energy consumption prediction model. It takes the current energy consumption coefficient and current operating settings of several devices as input and outputs the predicted energy consumption coefficient of several devices in the future several periods.

[0014] The judgment and marking module is used to compare the actual energy consumption coefficient and predicted energy consumption coefficient collected by the data acquisition module for several cycles with the standard energy consumption coefficient threshold respectively.

[0015] The loss calculation module is used to mark energy consumption coefficients that violate the standard threshold and their associated equipment based on the comparison results under the standard energy consumption coefficient threshold of the judgment and marking module. Based on the marked energy consumption coefficients, it outputs the actual carbon emission loss coefficient and the predicted carbon emission loss coefficient of the marked equipment respectively.

[0016] The retrofit analysis unit is used to extract the tagged equipment that correlates the actual carbon emission loss coefficient with the predicted carbon emission loss coefficient, calculate the future retrofit carbon emissions, and obtain the retrofit carbon emission loss coefficient.

[0017] The weight setting module is used to preset the weights of actual, predicted and retrofitted carbon emission loss coefficients, and to perform weighted calculations on the current actual, predicted and retrofitted carbon emission loss coefficients to obtain the total carbon emission loss of several devices.

[0018] The aggregation module is used to aggregate the total carbon emission loss data of all devices and generate a visual report to be submitted to the central control module.

[0019] Furthermore, the central control module is interconnected with a feedback module via a wireless network. The feedback module receives the actual energy consumption coefficient collected by the data acquisition module in the next cycle or the energy consumption coefficient manually written, and submits it to the threshold setting module for judgment. When it is judged that the threshold of the threshold setting module is violated, it jumps to the loss calculation module to calculate the actual carbon emission loss coefficient, compares the current actual carbon emission loss coefficient with the predicted carbon emission coefficient of the previous cycle, and calculates the difference as the adjustment reference coefficient of the energy consumption prediction model of the model building module.

[0020] Furthermore, the energy consumption prediction model in the model building module is constructed using a regression analysis algorithm, and its expression is:

[0021]

[0022] In the formula, Ei,t+k P represents the predicted energy consumption coefficient of device i over the next k periods. o The intercept term represents the model, m represents the number of independent variables used for prediction, and P represents the number of independent variables used for prediction. j Represents each independent variable X i,j,t The regression coefficient, X i,j,t Z represents the value of device i at time t, n represents the number of other external factors affecting energy consumption, and Y represents the value of the j-th independent variable for each external factor. i,l,t The regression coefficient, Z i,l,t e represents the value of the l-th external factor for device i at time t. i,j,t This represents the error term.

[0023] Furthermore, the training process of the energy consumption prediction model in the model building module is as follows:

[0024] Step 1: Obtain the actual energy consumption coefficient of each device at different time periods through the data acquisition module, record the device type, operating mode and set parameters, collect climate conditions, time factors and socio-economic factors, and convert them into a model-readable format to form a training set;

[0025] Step 2: Select characteristic independent variables that are closely related to equipment energy consumption;

[0026] Step 3: Use the training set to determine the corresponding regression coefficients using the least squares method, and continue to optimize the parameters;

[0027] Step 4: Put the trained energy consumption prediction model into real-time prediction calculation, and add the evaluation feedback of the prediction results to the training set.

[0028] Furthermore, during the comparison operation phase, the judgment and marking module triggers a jump based on the comparison result. If the comparison result does not violate the standard threshold state, it jumps to the threshold setting module and the model building module. If the comparison result violates the standard threshold state, it jumps to the loss calculation module. During the stage where the judgment and marking module feeds back the comparison result to the loss calculation module, it also simultaneously feeds back the data source threshold setting module and the model building module.

[0029] Furthermore, the central control module is interconnected with a storage module via a wireless network. The storage module is used to receive the collected and output data from each functional module, classify and store them, and support cloud backup and reading and writing to external storage media.

[0030] Furthermore, the modification analysis unit is further equipped with sub-modules, including an extraction module, an indexing module, and a definition module. The extraction module and the indexing module are interconnected via a wireless network, and the indexing module and the definition module are interconnected via a wireless network.

[0031] The extraction module is used to extract a list of devices marked by the judgment and labeling module as violating the threshold, and to create a label for each device.

[0032] The indexing module is used to use the tags generated by the extraction module as keywords to query historical carbon emission loss data of tag-associated devices in the internal network and to query network carbon emission loss data of tag-associated devices in the Internet.

[0033] The definition module is used to obtain historical and network carbon emission loss data from the index module, integrate carbon emission loss data of devices that violate thresholds based on device type and running time, and output the integrated associated carbon emission loss data.

[0034] Furthermore, the tagging content of the extraction module includes: the current status of the device, operating attributes, tagging reason and tagging time. After the tagging content is generated, it synchronously jumps to the central control module to request storage permission.

[0035] Furthermore, the weight setting module retains historical preset data during the preset process of actual, predicted and modified carbon emission loss coefficient weights. When weighted calculations are performed on similar equipment with energy consumption coefficient errors within the allowable error range, the module directly jumps to the historical preset data for application.

[0036] Furthermore, the central control module is interconnected with the data acquisition module, the threshold setting module, and the model building module via a wireless network; the judgment and marking module is interconnected with the threshold setting module, the model building module, and the loss calculation module via a wireless network; the loss calculation module is interconnected with the transformation analysis unit via a wireless network; and the weight setting module is interconnected with the loss calculation module, the transformation analysis unit, and the aggregation module via a wireless network.

[0037] (III) Beneficial Effects

[0038] Compared with known prior art, the technical solution provided by this invention has the following beneficial effects:

[0039] 1. By constructing an energy consumption prediction model, analyzing historical data, real-time data, and external environmental variables, generating in-depth insight reports, dynamically updating prediction results and adjustment strategies to adapt to the ever-changing operating environment, accurately predicting energy consumption trends for future cycles, and adjusting and transforming strategies in a timely manner to reduce the impact of "pseudo-normal" equipment. Through a multi-dimensional analysis mechanism, it can not only identify data anomalies but also uncover potential energy-saving opportunities and improve energy efficiency.

[0040] 2. By establishing a judgment and marking mechanism through real-time data collection and analysis, when the monitored indicators exceed the set range, the fault can be quickly identified, early warning can be given, and resource waste and potential losses can be avoided. By summarizing and analyzing various data, regular reports and monitoring charts are generated, and the data is fed back into the transformation strategy to realize the data-driven decision-making process. Through the feedback control mechanism, the system monitors various indicators and adjusts parameters in real time during operation to ensure the best energy-saving effect.

[0041] 3. By analyzing the carbon emission losses from future retrofits, managers can identify potential energy-saving potential and emission reduction pathways, providing a feasibility analysis for retrofit plans. Quantitative analysis of carbon emission losses can help communities clarify the economic benefits when implementing energy-saving retrofits, thereby enabling them to allocate funds and resources wisely. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0043] Figure 1 This is a schematic diagram of the framework of the present invention;

[0044] Figure 2 This is a flowchart illustrating the training process of the energy consumption prediction model in this invention.

[0045] The labels in the diagram represent: 1. Central control module; 2. Data acquisition module; 3. Threshold setting module; 4. Model building module; 5. Judgment marking module; 6. Loss calculation module.

[0046] 7. Modification and Analysis Unit; The modification and analysis unit includes: 71. Extraction Module; 72. Index Module; 73. Definition Module;

[0047] 8. Weight setting module; 9. Summary module; 10. Feedback module; 11. Storage module. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0049] The present invention will be further described below with reference to embodiments.

[0050] Example 1

[0051] The green and low-carbon monitoring system for energy-saving renovation of old residential communities in this embodiment, such as Figure 1 As shown, it includes:

[0052] Central control module 1 is used to deploy the control intranet and to edit and submit instructions for various functional modules and units;

[0053] Data acquisition module 2 is used to collect the actual energy consumption coefficients and operating settings attributes of the power supply, gas supply and water supply equipment in the area to be transformed within a preset number of cycles. The operating settings attributes include: equipment type, operating mode and set parameters.

[0054] The threshold setting module 3 is used to define standard energy consumption coefficient thresholds based on the initial operating settings of the power supply, gas supply, and water supply equipment to be modified; based on the initial operating settings, it defines reasonable standard energy consumption coefficient thresholds to provide an effective baseline for comparison of the system, ensuring the scientific nature and accuracy of long-term monitoring and reducing resource waste.

[0055] Model building module 4 is used to build and train the energy consumption prediction model. Based on the current energy consumption coefficient and current operating settings of several devices as input, it outputs the predicted energy consumption coefficient of several devices in the future several cycles, providing the system with forward-looking analysis, enabling managers to take energy-saving measures in advance and optimize the operation of equipment.

[0056] The judgment and marking module 5 is used to compare the actual and predicted energy consumption coefficients collected by the data acquisition module 2 for several cycles with the standard energy consumption coefficient threshold. During the comparison operation phase, the judgment and marking module 5 triggers a jump based on the comparison result. If the comparison result does not violate the standard threshold, it jumps to the threshold setting module 3 and the model building module 4. If the comparison result violates the standard threshold, it jumps to the loss calculation module 6. The judgment and marking module 5 feeds back the comparison result to the loss calculation module 6, and simultaneously feeds back to the data source threshold setting module 3 and the model building module 4. By automatically comparing the actual and predicted energy consumption coefficients and making status judgments, the automation level of the system is improved. When a violation of the standard threshold is found, the next step of the loss calculation process can be effectively triggered, thereby improving the response speed.

[0057] The loss calculation module 6 is used to mark energy consumption coefficients that violate the standard threshold and their associated equipment based on the comparison results of the standard energy consumption coefficient threshold of the judgment and marking module 5. Based on the marked energy consumption coefficients, it outputs the actual carbon emission loss coefficient and the predicted carbon emission loss coefficient of the marked equipment respectively. By marking all illegal energy consumption and their associated equipment and calculating their actual and predicted carbon emission loss coefficients, it provides specific data support for subsequent transformation, thereby realizing effective tracking and analysis and improving the operability of the data.

[0058] The retrofit analysis unit 7 is used to extract the tagged equipment that is associated with the actual carbon emission loss coefficient and the predicted carbon emission loss coefficient, calculate the future retrofit carbon emissions, and obtain the retrofit carbon emission loss coefficient. By extracting data from the actual and predicted losses, it can calculate the future retrofit carbon emission loss coefficient, provide a quantitative basis for retrofit investment decisions, and ensure the economic and environmental benefits of the retrofit plan.

[0059] The weight setting module 8 is used to preset the weights of actual, predicted, and retrofitted carbon emission loss coefficients. It performs weighted calculations on the current actual, predicted, and retrofitted carbon emission loss coefficients to obtain the total carbon emission loss of several devices. During the preset process of the weights of the actual, predicted, and retrofitted carbon emission loss coefficients, the weight setting module 8 retains historical preset data. When weighted calculations are performed on similar devices whose energy consumption coefficient errors are within the allowable error range, it directly jumps to the historical preset data for application. Through effective weighted calculations using preset weights, a comprehensive assessment of the carbon emission loss of different devices can be achieved. The historical data retention mechanism allows for rapid response within the error range, reduces redundant calculations, and improves efficiency.

[0060] The aggregation module 9 is used to aggregate the total carbon emission loss data of all equipment and generate a visual report to be submitted to the central control module 1, which helps management to quickly assess the current carbon emission reduction effect.

[0061] The central control module 1 is connected to the feedback module 10 via a wireless network. The feedback module 10 receives the actual energy consumption coefficient collected by the data acquisition module 2 in the next cycle or the energy consumption coefficient manually written, and submits it to the threshold setting module 3 for judgment. When it is judged that the threshold of the threshold setting module 3 is violated, it jumps to the loss calculation module 6 to calculate the actual carbon emission loss coefficient. The current actual carbon emission loss coefficient is compared with the predicted carbon emission coefficient of the previous cycle, and the difference is used as the adjustment reference coefficient of the energy consumption prediction model of the model building module 4. This realizes real-time data feedback and processing, improves system quality, and enhances interactivity with users.

[0062] The central control module 1 is connected to the storage module 11 via a wireless network. The storage module 11 is used to receive the collected and output data from each functional module, classify and store them, support cloud backup and reading and writing to external storage media, strengthen the management and protection of historical data, and ensure the security and traceability of data.

[0063] As one implementation method in this embodiment, such as Figure 1 As shown, the central control module 1 is interconnected with the data acquisition module 2, the threshold setting module 3, and the model building module 4 via a wireless network. The judgment and marking module 5 is interconnected with the threshold setting module 3, the model building module 4, and the loss calculation module 6 via a wireless network. The loss calculation module 6 is interconnected with the transformation analysis unit 7 via a wireless network. The weight setting module 8 is interconnected with the loss calculation module 6, the transformation analysis unit 7, and the summary module 9 via a wireless network.

[0064] Compared with existing technologies, it has significant advantages in accurate data collection, efficient carbon emission monitoring, forecasting capabilities, and decision support. Its high degree of automation and modular design not only improve the efficiency of energy management but also provide managers with real-time and accurate decision-making basis, promoting the green and low-carbon transformation of old residential areas. This, in turn, helps to improve resource utilization efficiency, reduce operating costs, and is in line with the concept of sustainable development, providing strong technical support for future urban management.

[0065] Example 2

[0066] At other levels, this embodiment also provides a process for constructing and training an energy consumption prediction model, such as... Figure 2 As shown, the energy consumption prediction model is constructed using a regression analysis algorithm, and the expression is:

[0067]

[0068] In the formula, E i,t+k P represents the predicted energy consumption coefficient of device i over the next k periods. o The intercept term represents the predicted energy consumption coefficient when all independent variables are zero, m represents the number of independent variables used for prediction, and each independent variable has a certain influence weight on energy consumption. P j Represents each independent variable X i,j,t The regression coefficients represent the degree of influence of independent variable j on the energy consumption coefficient of device i, X. i,j,t Let Z represent the value of the j-th independent variable of device i at time t, including: device type, current energy consumption coefficient, set parameters, and operating mode; n represents the number of other external factors affecting energy consumption, which are added manually; and Y represents the value corresponding to each external factor Z. i,l,tThe regression coefficient Z represents the degree of influence of external factor l on the energy consumption coefficient of equipment i. i,l,t The value of device i at time t represents the l-th external factor, including: time factor, environmental factor, and socioeconomic factor, e i,j,t This represents the error term, which includes random fluctuations or noise.

[0069] like Figure 2 As shown, the training process for the energy consumption prediction model is as follows:

[0070] Step 1: Obtain the actual energy consumption coefficient of each device at different time periods through data acquisition module 2, record the device type, operating mode and set parameters, collect climate conditions, time factors and socio-economic factors, and convert them into a model-readable format to form a training set;

[0071] Step 2: Select characteristic independent variables that are closely related to equipment energy consumption;

[0072] Step 3: Use the training set to determine the corresponding regression coefficients using the least squares method, and continue to optimize the parameters;

[0073] Step 4: Put the trained energy consumption prediction model into real-time prediction calculation, and add the evaluation feedback of the prediction results to the training set.

[0074] Through the above formulas and steps, the energy consumption prediction model can provide quantitative data support for the energy-saving renovation of old residential areas, and help promote the implementation and optimization of energy-saving measures.

[0075] Example 3

[0076] In this embodiment, as Figure 1 As shown, the modification analysis unit 7 has sub-modules, including an extraction module 71, an index module 72, and a definition module 73. The extraction module 71 and the index module 72 are interconnected via a wireless network, and the index module 72 and the definition module 73 are interconnected via a wireless network.

[0077] The extraction module 71 is used to extract the list of devices marked by the judgment and marking module 5 as violating the threshold, and create a tag for each device. The customized device tagging allows managers to directly understand the actual situation of the devices, which helps to quickly take targeted measures. The tagging content includes: the current status of the device, operating attributes, tagging reason and tagging time. After the tagging content is generated, it synchronously jumps to the central control module 1 to request storage permission, ensuring that the tagging content is stored and backed up in a timely manner in the internal network, improving the security and reliability of data, and effectively preventing data loss or leakage.

[0078] The index module 72 is used to use the tags generated by the extraction module 71 as keywords to query and obtain historical carbon emission loss data of tag-associated devices in the internal network and query network carbon emission loss data of tag-associated devices in the Internet; it performs bidirectional data query to obtain historical carbon emission loss data of tag-associated devices. The multi-channel data acquisition method improves the integrity and accuracy of the data and ensures the diversity of decision-making basis.

[0079] Module 73 is defined to obtain historical and network carbon emission loss data obtained from index module 72. It integrates carbon emission loss data of devices that violate thresholds based on device type and operating time, and outputs the integrated carbon emission loss data. This enables data analysis to generate more representative and accurate carbon emission loss data. Compared with the isolated analysis of traditional methods, this integration can reveal deeper patterns.

[0080] Compared with existing technologies, by linking the historical carbon emission data of equipment with its current status, managers can assess the effectiveness of current renovations and provide data support for future renovation measures, making decisions more scientific and precise. Through multi-dimensional data collection, dynamic feedback mechanisms, and customized equipment labeling, the carbon emission loss monitoring and analysis capabilities of energy-saving renovation systems in old residential areas have been improved.

[0081] In summary, this invention overcomes the shortcomings of existing technologies through innovations in a unified platform, multi-dimensional analysis, dynamic prediction, adaptive management, visual reporting, and real-time monitoring. It improves the efficiency and accuracy of energy management, helps to effectively reduce energy consumption and carbon emissions, and provides decision-makers with a more scientific basis for promoting green, low-carbon, and sustainable development.

[0082] In actual implementation, after the central control module 1 verifies the identity of the administrator, the invention issues instructions. The data acquisition module 2 collects the energy consumption parameters of the power supply, gas supply and water supply equipment to be modified in the detected area within a preset number of cycles, obtains the operating setting attributes of the power supply, gas supply and water supply equipment to be modified, and calculates the standard energy consumption parameter threshold of the operating settings of the power supply, gas supply and water supply equipment to be modified through the threshold setting module 3.

[0083] By comparing the collected energy consumption parameters over several cycles with the standard energy consumption parameter threshold, the marking module 5 marks the energy consumption parameters that violate the standard threshold and their associated equipment. Based on the marked energy consumption coefficient, the loss calculation module 6 calculates the current carbon emission loss coefficient of the marked equipment.

[0084] The prediction model is constructed by the model building module 4. Based on the current energy consumption parameters and current operating settings of several devices as input, the model outputs the predicted energy consumption coefficients of several devices in the future several cycles. The predicted energy consumption parameters are compared with the standard energy consumption parameter thresholds. Energy consumption parameters that violate the standard thresholds and their associated devices are marked. Based on the marked energy consumption coefficients, the predicted carbon emission loss coefficients of the marked devices are calculated by the loss calculation module 6.

[0085] The extraction module 71 extracts all the marked devices associated with the carbon emission loss coefficient, obtains the retrofit data of available associated devices in history and the Internet through the index module 72, and the definition module 73 merges and calculates the future retrofit carbon emissions to obtain the retrofit carbon emission loss coefficient.

[0086] The weight setting module 8 presets the weights of the current, predicted and retrofit carbon emission loss coefficients, and assigns weights to the current, predicted and retrofit carbon emission loss coefficients accordingly. The summarization module 9 summarizes the total carbon emission loss of several devices and submits it to the management end. The feedback module 10 defines the actual data for future cycles, and the storage module 11 records all collected and analyzed data.

[0087] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The green low-carbon monitoring system for energy-saving reconstruction of old residential quarters, characterized in that, The utility model relates to a kind of carbon emission loss prediction and analysis system, including: Central control module (1) is used to deploy control intranet, and the instruction of each functional module and unit is edited and submitted; Data acquisition module (2) is used to collect the actual energy consumption coefficient of the power supply, gas supply and water supply equipment in the preset period and the operation setting attribute; Threshold setting module (3) is used to define the standard energy consumption coefficient threshold based on the initial operation setting of the power supply, gas supply and water supply equipment to be transformed; Model construction module (4) is used to construct and train the energy consumption prediction model, and the current energy consumption coefficient and the current operation setting attribute of several devices are input, and the predicted energy consumption coefficient of several devices in the future several periods is output; Judgment marking module (5) is used to compare the actual energy consumption coefficient and the predicted energy consumption coefficient collected by the data acquisition module (2) in several periods with the standard energy consumption coefficient threshold respectively; Loss calculation module (6) is used to mark the energy consumption coefficient and its associated device that violate the standard threshold based on the comparison result of the standard energy consumption coefficient threshold in the judgment marking module (5), and output the actual carbon emission loss coefficient and the predicted carbon emission loss coefficient of the marked device based on the marked energy consumption coefficient; Transformation analysis unit (7) is used to extract the marked device associated with the actual carbon emission loss coefficient and the predicted carbon emission loss coefficient, calculate the future transformation carbon emission, and obtain the transformation carbon emission loss coefficient; Weight setting module (8) is used to preset the actual, predicted and transformation carbon emission loss coefficient weight, and the current actual, predicted and transformation carbon emission loss coefficient is weighted and calculated correspondingly to obtain the total carbon emission loss of several devices; Summary module (9) is used to summarize the total carbon emission loss data of all devices to generate a visual report and submit it to the central control module (1); The central control module (1) is connected with the feedback module (10) through wireless network interaction, and the feedback module (10) is used to receive the actual energy consumption coefficient collected by the next period data acquisition module (2) or the energy consumption coefficient actively written by human, and submit it to the threshold setting module (3) for judgment. When it is judged that it violates the threshold setting module (3) threshold, the actual carbon emission loss coefficient is calculated by jumping to the loss calculation module (6), and the difference value is calculated as the adjustment reference coefficient of the energy consumption prediction model in the model construction module (4) by comparing the current actual carbon emission loss coefficient with the previous period predicted carbon emission coefficient; The energy consumption prediction model in the model construction module (4) is constructed by regression analysis algorithm, and the expression is: ； In the formula, Representative equipment In the future Predicted energy consumption coefficient for the cycle, The intercept term representing the model, This represents the number of independent variables used for prediction. Represents each independent variable The regression coefficients, Representative equipment In time Upper The values ​​of the independent variables, This represents the number of other external factors that affect energy consumption. The representative corresponds to each external factor. The regression coefficients, Representative equipment In time Upper The value of an external factor, This represents the error term.

2. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, The training process of the energy consumption prediction model in the model construction module (4) is: Step 1: obtain the actual energy consumption coefficient of each device in different time periods, record the type, operation mode and setting parameter of the device, collect the climate condition, time factor and social and economic factor, and convert them into model readable format to form the training set; Step 2: select the characteristic independent variable closely related to device energy consumption; Step 3: determine the corresponding regression coefficient by least square method using the training set, and continuously accept parameter optimization; Step 4: put the trained energy consumption prediction model into real-time prediction calculation, and add the evaluation feedback of prediction result to the training set.

3. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, The judgment mark module (5) triggers a jump based on the comparison result in the comparison operation stage. When the comparison result does not exist the state of violating the standard threshold, the jump is to the threshold setting module (3) and the model construction module (4) operation. When the comparison result exists the state of violating the standard threshold, the jump is to the loss calculation module (6) operation. The judgment mark module (5) feeds back the comparison result to the loss calculation module (6) in the comparison result stage, and synchronously feeds back to the data source threshold setting module (3) and the model construction module (4).

4. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, The central control module (1) is connected with the storage module (11) through wireless network interaction. The storage module (11) is used for receiving the collected data and output data of each functional module, classifying storage, supporting cloud backup and reading and writing of external storage medium.

5. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, The transformation analysis unit (7) is provided with a sub-module, the sub-module includes an extraction module (71), an index module (72) and a definition module (73), the extraction module (71) and the index module (72) are connected through wireless network interaction, the index module (72) and the definition module (73) are connected through wireless network interaction, wherein: The extraction module (71) is used for extracting the device list marked by the judgment mark module (5) as violating the threshold, and creating a label for each device; The index module (72) is used for taking the label generated by the extraction module (71) as a keyword to query the historical carbon emission loss data of the label associated device in the internal network and query the network carbon emission loss data of the label associated device in the Internet; The definition module (73) is used for obtaining the historical and network carbon emission loss data obtained by the index module (72), integrating the carbon emission loss data of the devices associated with the threshold violation based on the device type and the running time, and outputting the integrated associated carbon emission loss data.

6. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 5, characterized in that, The marking content of the extraction module (71) includes the current state, running attribute, marking reason and marking time of the device. After the marking content is generated, it is synchronously jumped to the central control module (1) to request to obtain the storage permission.

7. The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, In the preset process of the actual, predicted and transformed carbon emission loss coefficient weight, the historical preset data is reserved. When the energy consumption coefficient error of the same type device within the allowable error range is weighted, the historical preset data is directly applied. 8.The old cell energy-saving reconstruction green low-carbon monitoring system according to claim 1, characterized in that, The central control module (1) is connected with the data acquisition module (2), the threshold setting module (3) and the model construction module (4) through wireless network interaction. The judgment mark module (5) is connected with the threshold setting module (3), the model construction module (4) and the loss calculation module (6) through wireless network interaction. The loss calculation module (6) is connected with the transformation analysis unit (7) through wireless network interaction. The weight setting module (8) is connected with the loss calculation module (6), the transformation analysis unit (7) and the summary module (9) through wireless network interaction.

Images