Thermal power generating unit energy consumption real-time monitoring and playback system based on SVG vector picture

Abstract

The invention provides a thermal power generating unit energy consumption real-time monitoring and playback system based on SVG vector pictures, which comprises a data acquisition module, an SVG picture engine, a WEB server, a historical database and a playback service module which are connected through a data bus, technologies such as self-adaptive sampling, intelligent layout and multi-layer scaling are adopted, the energy consumption state of the thermal power generating unit can be comprehensively and clearly displayed in a multi-angle mode, and the monitoring capacity of the system is improved; by adopting technologies of WebSocket communication, intelligent load balancing and the like, real-time transmission of energy consumption data and high-availability deployment of the system are realized, and timeliness and stability of a monitoring picture are ensured; the technologies of hierarchical storage, automatic life cycle management and the like are adopted, efficient storage and management of mass historical energy consumption data are achieved, and the requirements of data playback and analysis mining are met; through adoption of technologies such as adaptive frame rate control and intelligent scene retrieval, smooth playback and rapid positioning of a historical energy consumption scene are realized, and data support is provided for anomaly diagnosis and trend analysis.

Description

Technical Field

[0001] The invention belongs to the technical field of thermal power generation, and in particular relates to a real-time monitoring and playback system for energy consumption of a thermal power unit based on an SVG vector picture. Background Art

[0002] In the process of thermal power generation, the energy consumption of equipment such as boilers, steam turbines, and generators directly affects the economic benefits and environmental protection indicators of the power plant. Traditional thermal power unit energy consumption monitoring systems usually use two-dimensional graphics or tables to display energy consumption data, which has the following shortcomings: First, the amount of information on the screen is limited, and it is difficult to fully reflect the energy consumption status of the equipment; second, the screen lacks interactivity, which is not convenient for users to conduct in-depth analysis; third, there is a lack of historical data playback function, and it is impossible to trace the cause of abnormal energy consumption. Therefore, it is necessary to develop a thermal power unit energy consumption monitoring system with more powerful functions and more user-friendly experience. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art and provide a real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images, so as to solve the deficiencies of the existing thermal power unit energy consumption monitoring system in terms of data visualization expression, interactivity, cross-platform adaptability and historical data analysis.

[0004] In order to achieve the above-mentioned object, the present invention provides a real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images, including a data acquisition module, an SVG image engine, a WEB server, a historical database and a playback service module, and each module is connected through a data bus;

[0005] The data acquisition module adopts multi-channel asynchronous data acquisition technology with adaptive sampling rate, dynamically adjusts the sampling frequency of each channel according to the changing characteristics of energy consumption parameters, and performs pre-processing operations such as filtering, normalization, and anomaly detection on the collected raw data;

[0006] The SVG image engine uses a rule-based adaptive layout algorithm and intelligent warning labeling function to automatically generate the optimal image layout and abnormal labeling according to the importance, relevance and threshold setting of energy consumption parameters;

[0007] The WEB server adopts a real-time two-way communication mechanism based on WebSocket and an intelligent load balancing function to ensure real-time update of the screen and high availability of the system;

[0008] The historical database adopts a layered hybrid storage architecture and automatic data lifecycle management function to meet the different needs of real-time data access and historical data query;

[0009] The playback service module adopts key-frame-based adaptive frame rate control technology and intelligent scene retrieval function to achieve smooth playback and rapid positioning of target historical scenes.

[0010] Preferably, the SVG picture engine also has a multi-level semantic zoom function, automatically adjusts the presentation granularity of graphic elements according to the picture zoom ratio, displays energy consumption information of different levels of detail at different zoom levels, and supports user-defined zoom rules and key point settings.

[0011] Preferably, the data acquisition module has a data preprocessing function, and performs preprocessing operations such as filtering, normalization, and anomaly detection on the collected raw data to improve data quality.

[0012] Preferably, the SVG picture engine adopts a rule-based adaptive layout algorithm to automatically generate an optimal picture layout solution according to the importance and relevance of energy consumption parameters, and supports user-defined layout rules.

[0013] Preferably, the SVG image engine has an intelligent warning marking function, which automatically marks abnormal areas according to the threshold settings of the energy consumption parameters and prompts possible reasons and optimization suggestions.

[0014] Preferably, the WEB server adopts a real-time two-way communication mechanism based on WebSocket to establish a persistent full-duplex communication channel between the browser and the server, supports the server to actively push real-time energy consumption data and warning information, and ensures real-time updating of the screen.

[0015] Preferably, the WEB server has an intelligent load balancing function, which dynamically adjusts the load distribution strategy of the server cluster according to the client's access volume and network conditions to ensure high availability and scalability of the system.

[0016] Preferably, the historical database adopts a layered hybrid storage architecture, which divides the energy consumption data into a real-time layer, an archive layer, and a backup layer according to the time granularity, and uses an in-memory database, a time series database, and a distributed file system for storage, respectively, which not only meets the low latency requirements of real-time data access, but also takes into account the high throughput requirements of historical data queries.

[0017] Preferably, the historical database has an automatic data lifecycle management function, which automatically performs cold and hot stratification and elimination archiving of data according to the timeliness and access frequency of the data, thereby improving storage utilization.

[0018] Preferably, it also includes a data analysis module, which adopts a multi-model fusion machine learning algorithm to comprehensively analyze real-time and historical energy consumption data, automatically discover energy consumption patterns, predict trends, diagnose abnormal causes, provide energy-saving decisions, and form a multi-dimensional energy consumption analysis report; the data analysis module also has an incremental learning function, which can dynamically optimize the algorithm model according to user feedback, and continuously improve the accuracy and applicability of the analysis.

[0019] The real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images provided by the present invention has at least the following beneficial effects:

[0020] (1) Adopting technologies such as adaptive sampling, intelligent layout, and multi-layer scaling, it can comprehensively, clearly, and multi-angle display the energy consumption status of thermal power units, thus improving the monitoring capability of the system;

[0021] (2) Using WebSocket communication, intelligent load balancing and other technologies, the real-time transmission of energy consumption data and high-availability deployment of the system are realized, ensuring the timeliness and stability of the monitoring screen;

[0022] (3) Adopting technologies such as hierarchical storage and automatic lifecycle management, the efficient storage and management of massive historical energy consumption data is realized, meeting the needs of data playback and analysis and mining;

[0023] (4) Adaptive frame rate control, intelligent scene retrieval and other technologies are used to achieve smooth playback and rapid positioning of historical energy consumption scenes, providing data support for abnormal diagnosis and trend analysis;

[0024] (5) The data analysis module integrates multiple models and can automatically generate multi-dimensional energy consumption analysis reports to assist in energy-saving improvements and optimization decisions, thereby improving energy management levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0026] Figure 1 The present invention is a framework diagram of a real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images.

[0027] Figure 2 The invention is a process framework diagram of a method for real-time monitoring and playback of energy consumption of a thermal power unit based on SVG vector images. DETAILED DESCRIPTION

[0028] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0030] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Embodiment 1:

[0032] Reference Figure 1 This embodiment provides a real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images, including:

[0033] The data acquisition module is used to collect energy consumption parameters of various equipment in thermal power units, such as boiler fuel consumption, turbine main steam flow, generator power, etc. The module adopts multi-channel asynchronous data acquisition technology with adaptive sampling rate. According to the changing characteristics of each energy consumption parameter, the sampling frequency of each acquisition channel is dynamically adjusted to ensure data integrity while reducing redundant data transmission and improving acquisition efficiency.

[0034] The SVG screen engine is used to convert the collected real-time energy consumption data into vector graphics to generate intuitive and beautiful energy consumption monitoring screens. The engine uses a rule-based adaptive layout algorithm to automatically generate the optimal screen layout solution based on the importance and relevance of energy consumption parameters, thereby improving the information density and readability of the screen. At the same time, the engine also provides an intelligent warning marking function, which automatically marks abnormal areas according to the preset energy consumption threshold, and gives possible cause analysis and optimization suggestions, so that users can quickly locate and deal with energy consumption problems.

[0035] The WEB server is used to publish the vector monitoring images generated by the SVG image engine to the client browser in the form of a web page. The server uses a real-time two-way communication mechanism based on WebSocket to establish a persistent full-duplex communication channel with the client. On the one hand, the server can actively push new energy consumption data and alarm information to the client in real time to ensure the real-time nature of the monitoring image; on the other hand, the client can also feed back the user's interactive operations to the server in real time to achieve functions such as image zooming and panning. At the same time, the server also has an intelligent load balancing function, which can dynamically adjust the load distribution strategy of the server cluster according to the concurrent access volume of the client and the network status, thereby ensuring the high availability and scalability of the system.

[0036] The historical database is used to store the massive historical energy consumption data collected by the data collection module, providing data support for energy consumption playback, statistical analysis and other functions. The database adopts a layered hybrid storage architecture, which divides the energy consumption data into real-time layer, archive layer and backup layer according to the time granularity. It uses memory databases such as Redis, time series databases such as InfluxDB, and distributed file systems such as HDFS for storage, which not only meets the low latency requirements of real-time data access, but also takes into account the high throughput requirements of historical data query. In addition, the database also provides automatic data lifecycle management functions, which automatically performs cold and hot stratification and eliminates archives of data according to the timeliness and access frequency of the data, which improves storage utilization while simplifying the complexity of data management.

[0037] Preferably, the time series database is a Yunjie time series database.

[0038] The playback service module is used to respond to the client's historical data playback request, extract energy consumption data from the historical database in time series, and reproduce the historical energy consumption monitoring scene. This module uses keyframe-based adaptive frame rate control technology to dynamically adjust the keyframe selection strategy according to the change range of energy consumption data and the user's playback speed, while ensuring the smoothness of playback and minimizing the amount of data transmission. At the same time, the module also provides an intelligent scene retrieval function. Users can search for target scenes according to a combination of multiple conditions such as time range, energy consumption events, and equipment status, quickly locate historical time points of interest, and improve the flexibility and efficiency of data playback.

[0039] The system of this embodiment also integrates a data analysis module, which uses a multi-model fusion machine learning algorithm to comprehensively analyze real-time and historical energy consumption data, automatically discover the energy consumption pattern during the operation of the equipment, predict the energy consumption trend in the future, diagnose the cause of abnormal energy consumption, and provide decision-making suggestions for energy-saving optimization, and finally form a multi-dimensional energy consumption analysis report. This module also has an incremental learning function, which can dynamically adjust and optimize the algorithm model based on the user's feedback and evaluation of the analysis results, so that it can continuously adapt to new energy consumption scenarios and continuously improve the accuracy and practicality of the analysis.

[0040] The workflow of this embodiment is as follows:

[0041] (1) The data acquisition module collects energy consumption data of each device in the thermal power unit at an adaptive sampling rate, pre-processes the raw data, writes the real-time data into the data bus, and archives it to the historical database regularly;

[0042] (2) The SVG image engine reads real-time energy consumption data from the data bus, generates SVG vector monitoring images according to adaptive layout rules, and performs intelligent alarm annotation;

[0043] (3) The WEB server pushes the SVG monitoring screen to the client browser for display in real time through WebSocket, and feeds back the client's interactive events to the SVG screen engine. When the number of concurrent visits increases, the WEB server automatically adjusts the load balancing strategy to ensure the real-time transmission of the screen and the availability of the system.

[0044] (4) When the client requests historical data playback, the playback service module extracts energy consumption data from the historical database in time series after receiving the request, and transmits it to the client using adaptive frame rate control technology. The client synchronizes the playback screen according to the key frame timestamp sent by the server; users can also use the intelligent scene retrieval function to quickly locate the target historical time point;

[0045] (5) The data analysis module regularly extracts energy consumption data for a period of time from the historical database, combines it with real-time data, and comprehensively runs multiple machine learning models to generate analysis results such as energy consumption patterns, trend predictions, abnormal diagnosis, and energy-saving decisions, forming an energy consumption analysis report; users can provide feedback and evaluation on the analysis results, and the data analysis module dynamically optimizes the algorithm model based on this.

[0046] Embodiment 2:

[0047] Based on Example 1, this Example 2 performs technical optimization. Specifically, an adaptive data compression technology is adopted: before the data acquisition module writes the collected energy consumption data into the data bus and the historical database, it first performs adaptive compression on the data. This technology automatically selects the optimal compression algorithm and compression parameters according to the data type, change characteristics, etc. of the energy consumption parameters, and minimizes the overhead of data transmission and storage while ensuring the quality of data recovery. For example, for analog parameters that change slowly, a combination of adaptive differential encoding and run-length encoding can be adopted, while for switch parameters that change dramatically, an adaptive dictionary encoding method can be adopted. The adaptive compression technology not only improves the efficiency of data transmission and storage, but also reduces the network bandwidth and storage capacity requirements of the system.

[0048] As an implementation method, in this embodiment, an adaptive compression algorithm selection mechanism based on reinforcement learning is also introduced. Through continuous trial and error and feedback, the optimal compression strategy and parameter combination under different data characteristics are autonomously learned, and the algorithm performance evaluation index is set to achieve automatic optimization of the compression effect.

[0049] Embodiment 3:

[0050] Based on Example 1, this Example 3 performs technical optimization. Specifically, intelligent data completion technology is used: in the actual collection process, data missing may occur due to equipment failure, network interruption and other reasons. In order to ensure the continuity of energy consumption monitoring and analysis, this embodiment introduces intelligent data completion technology. This technology uses machine learning algorithms to automatically estimate and fill in missing data points by analyzing the correlation and historical change patterns between energy consumption parameters. For example, it can be combined with linear regression, random forest and other algorithms to dynamically fit the optimal estimate based on the data characteristics before and after the missing point and the status of other related parameters. Intelligent data completion technology improves the integrity and availability of energy consumption data and reduces the impact of missing data on subsequent analysis and decision-making.

[0051] As an implementation method, in this embodiment, a data completion framework based on a generative adversarial network (GAN) is also adopted. Through game learning between the generator and the discriminator, the distribution characteristics of the missing data are automatically fitted, and a data quality assessment mechanism is introduced to perform confidence analysis on the completion results, select high-confidence data for subsequent analysis, and improve the accuracy and reliability of data completion.

[0052] Embodiment 4:

[0053] Based on Example 1, this Example 4 performs technical optimization. Specifically, it adopts augmented reality interaction technology: the SVG picture engine supports the fusion of energy consumption monitoring screen and real-scene image of the equipment to form an augmented reality interaction interface. The user points the camera of the mobile terminal at the actual equipment, and the system automatically identifies the equipment model and key components, and superimposes the real-time energy consumption data, alarm information, etc. on the corresponding components in the form of virtual labels. Users can further view detailed information such as the historical energy consumption trend and abnormal diagnosis of the component by clicking on the virtual label. Augmented reality interaction technology provides a more intuitive and vivid human-computer interaction method. Users can easily grasp the energy consumption status of the equipment without in-depth understanding of the complex system architecture and data model, which greatly reduces the threshold of use.

[0054] As an implementation method, in this embodiment, a deep learning-based image recognition and target detection algorithm is also integrated to perform intelligent analysis on the real-scene image of the equipment, automatically extract the visual features of the equipment model and key components, and match them with a pre-established feature library to achieve accurate identification and association of equipment information.

[0055] Embodiment 5:

[0056] Based on Example 1, this Example 5 performs technical optimization. Specifically, it adopts energy consumption prediction and optimization technology: the data analysis module incorporates energy consumption prediction and optimization technology, and can establish an energy consumption prediction model based on historical energy consumption data, equipment operating parameters, environmental factors, etc., and perform rolling predictions on energy consumption trends for a period of time in the future. The prediction results can provide a basis for optimizing equipment operation. For example, before the peak energy consumption period arrives, the operating parameters of the equipment can be adjusted in advance to reduce unnecessary energy consumption expenses. The module can also use optimization algorithms, such as particle swarm optimization, genetic algorithms, etc., to solve the optimal combination of equipment operating parameters and minimize energy consumption costs while meeting process constraints. Energy consumption prediction and optimization technology enables the system to have the ability to actively save energy and increase efficiency, which can significantly improve the level of energy management.

[0057] As an implementation method, in this embodiment, a modeling method based on the combination of physical laws and data-driven is also adopted, and equipment mechanism knowledge and historical operation data are comprehensively utilized to construct a multi-scale and multi-granularity energy consumption prediction model. The model interpretability analysis technology is introduced to perform sensitivity analysis and feature importance ranking on the prediction results to enhance the credibility and interpretability of the prediction results. In terms of optimization, multi-objective optimization can be combined with reinforcement learning to adaptively balance multiple optimization objectives such as energy consumption, cost, and efficiency, and through continuous exploration and trial and error, the optimal control strategy is learned to generate an operational and explainable energy-saving optimization plan.

[0058] Embodiment 6:

[0059] Based on Example 1, this Example 6 performs technical optimization. Specifically, it adopts cross-platform mobile access technology: the WEB server adopts responsive design and adaptive rendering technology to support users to access the energy consumption monitoring screen through various mobile terminals. The server can dynamically adjust the layout, scaling, and interaction mode of the SVG screen according to the screen size, resolution, operating system and other parameters of the mobile terminal to adapt to different display environments and operating habits. At the same time, the server also provides an offline caching mechanism to temporarily store the most recently visited monitoring screens locally on the mobile terminal, so that browsing can continue even in the event of a network interruption, ensuring the continuity and smoothness of the user experience. Cross-platform mobile access technology makes the application scenarios of the system more flexible and diverse. Users can grasp the energy consumption dynamics of the equipment anytime and anywhere and respond to abnormal situations in a timely manner.

[0060] As an implementation method, in this embodiment, an adaptive rendering strategy based on user portraits and device fingerprints is also introduced, which comprehensively considers factors such as user preferences, device performance, network conditions, etc., dynamically adjusts the screen content and interaction methods, and provides a personalized access experience; in terms of offline caching, incremental updates and version management mechanisms can be used to balance cache timeliness and data volume, and introduce security sandboxes and exception recovery mechanisms to improve the security and robustness of mobile access.

[0061] Through the above five embodiments, the functions of the system are further enriched and improved, starting from data collection, human-computer interaction, data analysis, mobile applications and other aspects, significantly improving the practicality and innovation of the system, representing the latest development direction of energy consumption monitoring and management technology. The integrated application of these extended technologies will make the present invention a highly intelligent, personalized, mobile energy consumption monitoring and optimization platform, providing all-round technical support for energy saving and consumption reduction of thermal power units.

[0062] Embodiment 7:

[0063] Reference Figure 2 This embodiment 7 provides a method for real-time monitoring and playback of energy consumption of a thermal power unit based on an SVG vector image. The method is based on the system described in the above embodiment and includes the following steps:

[0064] Step 1: The data acquisition module collects energy consumption data of each device in the thermal power unit at an adaptive sampling rate, and uses adaptive data compression technology to compress and encode the original data, thereby reducing transmission and storage overhead while ensuring data quality; then the compressed real-time data is written to the data bus and archived to the historical database regularly; when data is missing, the intelligent data completion process is automatically triggered, and the missing values ​​are estimated and filled using machine learning algorithms to ensure data continuity and integrity;

[0065] Step 2: The SVG image engine reads the real-time energy consumption data from the data bus, generates an SVG vector monitoring image according to the adaptive layout rules, and performs intelligent alarm annotation; when receiving a query request from the user through the augmented reality interactive interface, it extracts the historical energy consumption data and diagnostic information of the relevant components, and displays them on the real-life image of the equipment, realizing seamless integration of data and real objects;

[0066] Step 3: The WEB server pushes the SVG monitoring screen to the client browser for display in real time through WebSocket, and feeds back the client's interactive events to the SVG screen engine; when receiving an access request from a mobile terminal, it automatically identifies the terminal type, uses cross-platform adaptive rendering technology to dynamically adjust the screen layout and interaction mode, and enables an offline cache mechanism to ensure a smooth access experience in a mobile environment; when the number of concurrent visits increases, the WEB server automatically adjusts the load balancing strategy to ensure the real-time transmission of the screen and the availability of the system;

[0067] Step 4: When the client requests historical data playback, the playback service module extracts energy consumption data from the historical database in time series after receiving the request, and transmits it to the client using adaptive frame rate control technology. The client synchronizes the playback screen according to the key frame timestamp sent by the server; users can also use the intelligent scene retrieval function to quickly locate the target historical time point;

[0068] Step 5: The data analysis module regularly extracts energy consumption data for a period of time from the historical database, combines real-time data and external environmental parameters, runs the energy consumption prediction model, and makes a rolling prediction of the energy consumption trend for a period of time in the future; at the same time, it uses the optimization algorithm to solve the optimal combination of equipment operating parameters and automatically generates an energy-saving optimization plan; then, based on the above analysis results, it outputs an energy consumption analysis report containing energy consumption patterns, trend predictions, abnormal diagnosis, optimization suggestions, etc., and pushes it to relevant users; users can provide feedback and evaluation on the analysis results, and the data analysis module dynamically adjusts and optimizes the prediction and optimization models accordingly.

[0069] The method of this embodiment makes full use of the various innovative technologies proposed in the above embodiments to form a complete and intelligent energy consumption monitoring and optimization solution. Its advantages are:

[0070] (1) The use of technologies such as adaptive sampling, data compression, and intelligent completion significantly improves the efficiency of data collection and transmission, reduces system resource overhead, and ensures data quality and integrity, laying a solid foundation for subsequent analysis;

[0071] (2) The use of technologies such as adaptive layout, intelligent annotation, and augmented reality interaction has greatly enriched the information expression of the monitoring screen and provided a more intuitive and flexible human-computer interaction method, enabling users to easily understand and control the energy consumption status of the equipment;

[0072] (3) The use of WebSocket communication, cross-platform adaptive rendering, offline caching and other technologies has broken through the limitations of time and space, and achieved real-time push and mobile access to energy consumption information. Users can obtain the required information anytime, anywhere, and from a variety of terminals, greatly improving the availability and convenience of the system;

[0073] (4) Adopting technologies such as adaptive frame rate control and intelligent scene retrieval, the transmission efficiency and retrieval experience of historical data playback are optimized, providing users with a comprehensive and smooth historical scene reproduction, facilitating the tracing and analysis of abnormal situations;

[0074] (5) Energy consumption prediction and optimization technologies are used to enable the system to have the ability to conduct active analysis and decision-making, predict energy consumption trends in advance, automatically generate energy-saving plans, transform passive monitoring into active optimization, give full play to the value of energy consumption data, and realize the leap from intelligent and refined energy management.

[0075] In summary, the method proposed in this embodiment integrates a number of cutting-edge technologies, realizes a full-process closed loop of energy consumption data collection, monitoring, analysis, and optimization, is data-driven, with intelligence as the core and optimization as the goal, and represents a major change and innovation in the energy management model. It is of great significance to promote energy conservation, emission reduction, quality improvement and efficiency enhancement in the thermal power industry, and shows good application prospects.

[0076] Finally, it should be emphasized that the present invention is not limited to the above-mentioned implementation mode. The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time monitoring and playback system for energy consumption of thermal power units based on SVG vector images, characterized in that: It includes data acquisition module, SVG image engine, WEB server, historical database and playback service module, and each module is connected through a data bus; The data acquisition module adopts multi-channel asynchronous data acquisition technology with adaptive sampling rate, dynamically adjusts the sampling frequency of each channel according to the changing characteristics of energy consumption parameters, and performs pre-processing operations such as filtering, normalization, and anomaly detection on the collected raw data; The SVG image engine uses a rule-based adaptive layout algorithm and intelligent warning labeling function to automatically generate the optimal image layout and abnormal labeling according to the importance, relevance and threshold setting of energy consumption parameters; The WEB server adopts a real-time two-way communication mechanism based on WebSocket and an intelligent load balancing function to ensure real-time update of the screen and high availability of the system; The historical database adopts a layered hybrid storage architecture and automatic data lifecycle management function to meet the different needs of real-time data access and historical data query; The playback service module adopts key-frame-based adaptive frame rate control technology and intelligent scene retrieval function to achieve smooth playback and rapid positioning of target historical scenes.

2. The system according to claim 1, characterized in that The SVG image engine also has a multi-level semantic zoom function, which automatically adjusts the presentation granularity of graphic elements according to the image zoom ratio, displays energy consumption information of different levels of detail at different zoom levels, and supports user-defined zoom rules and key point settings.

3. The system according to claim 1, characterized in that The data acquisition module has a data preprocessing function, which performs preprocessing operations such as filtering, normalization, and anomaly detection on the collected raw data to improve data quality.

4. The system according to claim 1, characterized in that The SVG picture engine adopts a rule-based adaptive layout algorithm to automatically generate an optimal picture layout solution according to the importance and relevance of energy consumption parameters, and supports user-defined layout rules.

5. The system according to claim 1, characterized in that The SVG image engine has an intelligent warning marking function, which automatically marks abnormal areas according to the threshold settings of energy consumption parameters and prompts possible reasons and optimization suggestions.

6. The system according to claim 1, characterized in that The WEB server adopts a real-time two-way communication mechanism based on WebSocket to establish a persistent full-duplex communication channel between the browser and the server, supports the server to actively push real-time energy consumption data and warning information, and ensures real-time updating of the screen.

7. The system according to claim 1, characterized in that The WEB server has an intelligent load balancing function, which dynamically adjusts the load distribution strategy of the server cluster according to the client's access volume and network conditions to ensure high availability and scalability of the system.

8. The system according to claim 1, characterized in that The historical database adopts a layered hybrid storage architecture, which divides the energy consumption data into a real-time layer, an archive layer, and a backup layer according to the time granularity, and uses an in-memory database, a time series database, and a distributed file system for storage, respectively, which not only meets the low latency requirements of real-time data access, but also takes into account the high throughput requirements of historical data queries.

9. The system according to claim 1, characterized in that The historical database has an automatic data lifecycle management function, which automatically performs cold and hot stratification and eliminates and archives data according to the timeliness and access frequency of the data, thereby improving storage utilization.

10. The system according to any one of claims 1 to 9, characterized in that: It also includes a data analysis module that uses a multi-model fusion machine learning algorithm to comprehensively analyze real-time and historical energy consumption data, automatically discover energy consumption patterns, predict trends, diagnose abnormal causes, provide energy-saving decisions, and form a multi-dimensional energy consumption analysis report; the data analysis module also has an incremental learning function, which can dynamically optimize the algorithm model based on user feedback, and continuously improve the accuracy and applicability of the analysis.

Images