Energy data model management system, electronic equipment and computer readable storage medium

Abstract

The invention discloses an energy data model management system, an electronic device and a computer readable storage medium, the system comprises a resource management module, a one-stop modeling module, a model application management module and a co-construction upgrade module, the resource management module is used for collecting data of each link of energy production, collecting algorithm model resources, and sending the algorithm model resources to the one-stop modeling module; and the one-stop modeling module is used for establishing data and algorithm model resources and managing the data and algorithm model resources, and the one-stop modeling module is used for establishing a model visually through the data and algorithm model resources, training and reasoning the established model, and monitoring and evaluating model performance in real time according to set evaluation indexes through an automatic evaluation and tuning mechanism. According to the method, different data are integrated and managed, one-stop modeling and application functions are provided, the problems of the energy industry in the aspects of data, AI, knowledge, platform application and the like are solved, enterprises are assisted to optimize the production efficiency, and the decision-making level is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy industry intelligentization, and particularly to an energy data model management system, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the development process of today's energy industry, digital and intelligent transformation has become a key trend. However, the current energy industry faces many challenges in data processing and model construction applications:

[0003] Data management dilemma: The production, transmission, and use processes of the energy industry involve many complex systems and devices, such as various unit devices in power stations, substations and transmission lines in the power transmission network, distribution boxes and user terminals in the distribution network, etc. The data generated by these systems and devices from different sources have different formats and lack effective interconnection and interoperability with each other, forming a serious data island phenomenon. At the same time, due to the limitations of data acquisition devices or data loss during data transmission, etc., the sample data is often incomplete. For example, in a wind farm, the real-time operation data of wind turbines, meteorological environment data, and grid load data are scattered and stored in different systems and cannot be integrated in time for comprehensive analysis, making it difficult to fully explore and utilize the potential value of the data and unable to provide comprehensive support for the optimization decision-making of the energy industry.

[0004] AI aspect: The application demand for artificial intelligence technology in the energy field is increasing day by day, but there is a large gap in AI talents, and at the same time, the modeling threshold is high, making it extremely difficult to build a high-precision model. This restricts the in-depth application of AI in aspects such as energy system optimization and fault prediction.

[0005] Knowledge aspect: There is a lack of efficient knowledge modeling tools, and it is difficult to inherit and apply the experience of experts in a standardized manner to actual production and decision-making, and the value of expert knowledge cannot be fully utilized.

[0006] Platform aspect: The existing energy industry-related models often lack good interpretability, making it difficult for technicians and decision-makers to understand the operating mechanism of the model and the reliability of the prediction results, thus reducing the credibility and application value of the model. At the same time, the process efficiency of model application construction is low. From model development, testing to actual deployment and application, it takes a large amount of time and resources, and there is a lack of effective cooperation and collaboration between different technologies and systems, and it is impossible to quickly respond to the rapidly changing business needs of the energy industry and difficult to meet the urgent needs of the intelligent development of the energy industry.

[0007] Therefore, there is an urgent need for a digital-analog integrated platform that can solve the above problems and improve the production efficiency and decision-making level of the energy industry. Summary of the Invention

[0008] The object of the present invention is to provide an energy data model management system, an electronic device, and a computer-readable storage medium, which can integrate and manage different data, provide one-stop modeling and application functions, solve the problems existing in the energy industry in aspects such as data, AI, knowledge, and platform applications, and help enterprises optimize production efficiency and improve decision-making levels.

[0009] The present invention provides an energy data model management system, which includes: a resource management module, a one-stop modeling module, a model application management module, and a co-construction and upgrade module. The resource management module is used to collect data from all links of energy production, collect algorithm model resources, and manage the data and algorithm model resources. The one-stop modeling module is used to visually construct a model through data and algorithm model resources, train and infer the constructed model, and through an automatic evaluation and optimization mechanism, monitor and evaluate the model performance in real time according to the set evaluation indicators; the model application management module is used to monitor the running performance of the model in business applications, the accuracy of prediction results, and the impact on business processes in real time. The co-construction and upgrade module is used to realize the development and optimization of external participation in model applications through API services and model markets, and quickly update and iterate the model according to business requirements and data feedback.

[0010] Further, in the above energy data model management system, the resource management module includes: a data collection sub-module, a model collection sub-module, and a resource management sub-module respectively connected to the data collection sub-module and the model collection sub-module. The data collection sub-module is used to collect data from all links of energy production. The model collection sub-module is used to collect various algorithms and model resources. The resource management sub-module is used to uniformly manage the collected data and the collected algorithm model resources by establishing a resource directory and a metadata management mechanism, and record the basic information, version, applicable scenarios, and invocation methods of the resources.

[0011] Further, in the above energy data model management system, the models include machine learning algorithm models, deep learning models, mechanism models, and industry expert knowledge models.

[0012] Further, in the above energy data model management system, the one-stop modeling module includes: a data processing sub-module, and the data processing sub-module is used to perform processing operations such as cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module.

[0013] Further, in the above energy data model management system, the processing operations of cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module specifically include:

[0014] Removing noise, duplicate data, and outliers in the data through a data cleaning algorithm;

[0015] Use data conversion technology to uniformly convert data in different formats into a standard format that can be recognized and processed by the platform;

[0016] Associate and integrate data from different data sources to form a complete data set.

[0017] Furthermore, in the above energy data model management system, the processing operations of cleaning, format conversion, integration and association, and extraction and construction of features for the data collected by the resource management module further include:

[0018] Perform feature engineering on the data to extract and construct features valuable for modeling.

[0019] Furthermore, in the above energy data model management system, the one-stop modeling module further includes: a visual modeling sub-module and a training and evaluation sub-module. The visual modeling sub-module is used to construct a model through data and algorithm model resource visualization; the training and evaluation sub-module is used to train and infer the constructed model, and through an automatic evaluation and tuning mechanism, monitor and evaluate the model performance in real time according to the set evaluation indicators.

[0020] Furthermore, in the above energy data model management system, the co-construction and upgrade module includes a co-construction sub-module and an update and upgrade sub-module. The co-construction sub-module is used to realize the development and optimization of external participation in model applications through API services and the model market; the update and upgrade sub-module is used to quickly update and iterate the model according to business requirements and data feedback.

[0021] In addition, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to at least one processor, wherein the memory stores the above energy data model management system.

[0022] The present invention also provides a computer-readable storage medium, on which the above energy data model management system is stored.

[0023] The present invention solves the problems existing in the aspects of data, AI, knowledge, and platform applications in the energy industry by integrating and managing different data, provides one-stop modeling and application functions, and helps enterprises optimize production efficiency and improve decision-making levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic structural diagram of the energy data model management system according to an embodiment of the present invention.

[0025] Figure 2 is a schematic structural diagram of the device of the hardware operating environment involved in the energy data model management system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In this embodiment, an energy data model management system is taken as an example. Hereinafter, the present invention will be described in detail with reference to specific embodiments and drawings.

[0027] Please refer to Figure 1 , an energy data model management system provided by an embodiment of the present invention. The system includes: a resource management module 10, a one-stop modeling module 20, a model application management module 30, and a co-construction and upgrade module 40. The resource management module 10 is used to collect data in each link of energy production, collect algorithm model resources, and manage the data and algorithm model resources. The one-stop modeling module 20 is used to visually construct a model through data and algorithm model resources, train and infer the constructed model, and through an automatic evaluation and optimization mechanism, monitor and evaluate the model performance in real time according to the set evaluation indicators; the model application management module 30 is used to monitor the operation performance, prediction result accuracy of the model in business applications, and the impact on business processes in real time. The co-construction and upgrade module 40 is used to realize the development and optimization of external participation in model applications through API services and a model market, and quickly update and iterate the model according to business requirements and data feedback. The present invention integrates and manages different data, provides one-stop modeling and application functions, solves the problems existing in the aspects of data, AI, knowledge, and platform applications in the energy industry, and helps enterprises optimize production efficiency and improve decision-making levels.

[0028] Specifically, the resource management module 10 is the data and model resource aggregation center of the energy data model management system of the present invention. Through various data interfaces and protocols, such as database interfaces (supporting common databases such as MySQL and Oracle), API interfaces, file interfaces, and industrial protocols (including IEC104, MODBUS, etc.), it can seamlessly access structured data (such as equipment operation parameters, production plan data, etc.), semi-structured data (such as log files), and unstructured data (such as equipment fault images, video surveillance data, etc.) generated in various links of power generation, power transmission, power transformation, power distribution, power consumption, and new energy in the energy industry. At the same time, it uniformly manages various algorithms and model resources, including machine learning algorithm models, deep learning models, mechanism models, and industry expert knowledge models. By establishing a resource catalog and metadata management mechanism, detailed records of the basic information, version, applicable scenarios, call methods, etc. of the resources are realized, so as to achieve efficient retrieval, call, and sharing of data and model resources, break the barriers between resources, and provide rich and comprehensive resource support for subsequent modeling and applications.

[0029] That is, the resource management module 10 includes: a data collection sub-module 101, a model collection sub-module 102, and a resource management sub-module 103 that is respectively connected to the data collection sub-module 101 and the model collection sub-module 102. The data collection sub-module 101 is used to collect data in each link of energy production, that is, by using a variety of interfaces (database interfaces, API interfaces, file interfaces, industrial protocols, etc.), to collect structured, semi-structured, and unstructured data from each link of power generation, power transmission, power transformation, power distribution, power consumption, and new energy in the energy industry. The model collection sub-module 102 is used to collect various types of algorithm and model resources, including machine learning algorithm models, deep learning models, mechanism models, and industry expert knowledge models, etc. The resource management sub-module 103 is used to uniformly manage the collected data and the collected algorithm model resources by establishing a resource catalog and a metadata management mechanism, record the basic information, version, applicable scenarios, call methods, etc. of the resources, and achieve efficient retrieval, call, and sharing.

[0030] The one-stop modeling module 20 includes: a data processing sub-module 201, a visual modeling sub-module 202, and a training and evaluation sub-module 203. The data processing sub-module 201 is used to perform processing operations such as cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module 10. First, the data cleaning algorithm is used to remove noise, duplicate data, and outliers in the data to improve the quality and accuracy of the data; then, the data conversion technology is used to uniformly convert data in different formats into a standard format that can be recognized and processed by the platform; then, data integration is performed to associate and integrate data from different data sources to form a complete data set. In addition, feature engineering processing will also be performed on the data to extract and construct features valuable for modeling, providing a high-quality data basis for subsequent model construction.

[0031] The visual modeling sub-module 202 is used to construct a model through the visualization of data and algorithm model resources. The energy data model management system of the present invention provides a rich variety of visual modeling tools and interfaces, covering a variety of modeling methods. Among them, the modeling project function supports users to create and manage modeling projects, set the goals, scopes, and parameters of the projects; the process engine allows users to design modeling processes through visual operations such as dragging and connecting, realizing flexible control of the modeling process.

[0032] The knowledge modeling function is based on a PN (Petri net) graphical modeling engine, which can transform the experience and knowledge of experts into executable model rules in a graphical way, promoting the visual expression and inheritance of knowledge; the AI modeling function integrates mainstream deep learning frameworks (such as TensorFlow, PyTorch, etc.) and machine learning algorithm libraries, supporting users to quickly build AI models through simple parameter settings and data input.

[0033] The simulation modeling function can simulate and model the operation process of the energy system to help users verify the rationality and effectiveness of the model; hybrid modeling supports the integration of different types of modeling methods (such as knowledge modeling and AI modeling) to solve complex energy business problems; the prefabricated model development function provides a series of verified prefabricated model templates that users can customize and modify according to actual needs, greatly shortening the modeling time.

[0034] The canvas management function provides a visual workspace for users to facilitate the design, layout, and adjustment of the model structure and components; the visualization analysis function can visually display the data and results during the modeling process, such as drawing data charts and visualizing model evaluation metrics, to help users intuitively understand the data and the performance of the model.

[0035] The training and evaluation sub-module 203 is used to train and infer the constructed model. Through an automatic evaluation and optimization mechanism, it monitors and evaluates the model performance in real time according to the set evaluation metrics. The training and evaluation sub-module 203 utilizes the powerful computing resources of the platform to perform training and inference operations on the constructed model. During the training process, through the automatic evaluation and optimization mechanism, the performance of the model is monitored and evaluated in real time according to the set evaluation metrics (such as accuracy, recall rate, mean squared error, etc.), and optimization algorithms (such as stochastic gradient descent, adaptive moment estimation, etc.) are used to adjust and optimize the model parameters to improve the accuracy and generalization ability of the model.

[0036] The model application management module 30 is used to monitor in real time the operation performance of the model in business applications, the accuracy of prediction results, and the impact on business processes. After the model is trained and optimized, it is deployed into the actual business environment through the model release function to realize the online application of the model. At the same time, through the model application supervision function, it monitors in real time indicators such as the operation performance of the model in business applications, the accuracy of prediction results, and the impact on business processes.

[0037] The co-construction and upgrade module 40 includes a co-construction sub-module 401 and an update and upgrade sub-module 402. The co-construction sub-module 401 is used to realize the external participation in the development and optimization of model applications through API services and the model market, that is, it supports the co-construction of industry models and the co-construction of industry applications, and encourages multiple parties such as energy enterprises, research institutions, and software developers to participate in the development and optimization of models and applications. Through API services and the model market, the sharing and trading of models and applications are realized to promote the optimal allocation of resources and collaborative innovation.

[0038] The update and upgrade sub-module 402 is used to quickly update and iterate the model according to business requirements and data feedback. During the model application process, the model is quickly updated and iterated according to business requirements and data feedback, and the updated model is timely applied to the actual business through the one-key deployment function, realizing the agile development and co-evolution of the model and the application, ensuring that the model can always accurately reflect the actual situation of the energy business, and providing reliable support for business decisions.

[0039] In addition, an embodiment of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores the energy data model management system in the above embodiment.

[0040] Next, refer to Figure 2 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 2 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure.

[0041] As Figure 2 shown, the electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0042] Generally, the following systems may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices including, for example, magnetic tapes, hard disks, etc.; and communication devices. The communication device may allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an electronic device having various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0043] This embodiment provides a computer-readable storage medium, which stores the energy data model management system in the above embodiment.

[0044] The computer-readable storage medium provided by the embodiments of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above. The above computer-readable storage medium may be included in an electronic device; or it may exist separately and not be assembled into the electronic device.

[0045] The present invention integrates and manages different data, provides one-stop modeling and application functions, solves the problems existing in the energy industry in aspects such as data, AI, knowledge, and platform applications, and helps enterprises optimize production efficiency and improve decision-making levels.

[0046] The description and application of the present invention here are illustrative and are not intended to limit the scope of the present invention to the above embodiments. Modifications and changes to the embodiments disclosed here are possible, and various substitutions and equivalents of components are known to those of ordinary skill in the art. Those skilled in the art should clearly understand that the present invention can be implemented in other forms, structures, arrangements, proportions, and with other components, materials, and parts without departing from the spirit or essential characteristics of the present invention. Other modifications and changes can be made to the embodiments disclosed here without departing from the scope and spirit of the present invention.

Claims

1. An energy data model management system, characterized in that, The system includes: a resource management module, a one-stop modeling module, a model application management module, and a co-construction and upgrade module. The resource management module is used to collect data from all links of energy production, collect algorithm model resources, and manage the data and algorithm model resources. The one-stop modeling module is used to visually construct a model through data and algorithm model resources, train and infer the constructed model, and through an automatic evaluation and optimization mechanism, monitor and evaluate the model performance in real time according to the set evaluation indicators. The model application management module is used to monitor the running performance of the model in business applications, the accuracy of prediction results, and the impact on business processes in real time. The co-construction and upgrade module is used to realize the development and optimization of external participation in model applications through API services and model markets, and quickly update and iterate the model according to business requirements and data feedback.

2. The energy data model management system according to claim 1, characterized in that The resource management module includes: a data collection sub-module, a model collection sub-module, and a resource management sub-module respectively connected to the data collection sub-module and the model collection sub-module. The data collection sub-module is used to collect data from all links of energy production. The model collection sub-module is used to collect various algorithms and model resources. The resource management sub-module is used to uniformly manage the collected data and the collected algorithm model resources by establishing a resource directory and a metadata management mechanism, and record the basic information, version, applicable scenarios, and invocation methods of the resources.

3. The energy data model management system according to claim 2, characterized in that The models include machine learning algorithm models, deep learning models, mechanism models, and industry expert knowledge models.

4. The energy data model management system according to claim 1, characterized in that The one-stop modeling module includes: a data processing sub-module, which is used to perform processing operations such as cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module.

5. The energy data model management system according to claim 4, characterized in that, The processing operations of cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module specifically include: Removing noise, duplicate data, and outliers in the data through data cleaning algorithms; Using data conversion technologies to uniformly convert data in different formats into a standard format that can be recognized and processed by the platform; Associating and integrating data from different data sources to form a complete data set.

6. The energy data model management system according to claim 5, characterized in that, The processing operations of cleaning, format conversion, integration and association, and feature extraction and construction on the data collected by the resource management module also include: Performing feature engineering processing on the data to extract and construct features valuable for modeling.

7. The energy data model management system according to claim 4, wherein The one-stop modeling module also includes: a visual modeling sub-module and a training and evaluation sub-module. The visual modeling sub-module is used to visually construct a model through data and algorithm model resources. The training and evaluation sub-module is used to train and infer the constructed model, and through an automatic evaluation and optimization mechanism, monitor and evaluate the model performance in real time according to the set evaluation indicators.

8. The energy data model management system according to claim 1, characterized in that, The co-construction and upgrade module includes a co-construction sub-module and an update and upgrade sub-module. The co-construction sub-module is used to realize the development and optimization of external participation in model applications through API services and model markets. The update and upgrade sub-module is used to quickly update and iterate the model according to business requirements and data feedback.

9. An electronic device, the electronic device comprising: At least one processor; And a memory communicatively connected to at least one processor, wherein the memory stores the energy data model management system according to any one of claims 1-8.

10. A computer-readable storage medium storing the energy data model management system according to any one of claims 1-8.

Images