Energy regulation and control system, regulation and control method and electronic equipment

Abstract

The embodiment of the invention provides an energy regulation and control system, a regulation and control method and electronic equipment, and belongs to the technical field of data processing. The energy regulation and control system comprises an Internet of Things platform module used for collecting various equipment data of an oil field station; the data platform module is used for carrying out data preprocessing on the various equipment data; the algorithm platform module is used for performing energy regulation and control based on the various equipment data after data preprocessing by using an operational research optimization algorithm or a machine learning method; and the business platform module is used for performing correlation analysis on the various equipment data based on a correlation analysis method and determining an operation strategy of the oil field station based on a correlation analysis result. The embodiment of the invention is used for solving the defects that an existing scheme lacks a comprehensive and multi-dimensional energy planning system, so that the system cost is reduced, and the load efficiency of an oil field station is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to an energy regulation system, an energy regulation method, an electronic device, a machine-readable storage medium, and a computer program product. Background Technology

[0002] Zero-carbon oilfield stations refer to oilfield stations that achieve "net-zero" emissions by leveraging new energy sources for power and heat and carbon reduction technologies, and through the reengineering of production and operation processes, based on energy conservation and emission reduction. As the new energy landscape gradually takes shape, the energy infrastructure construction of zero-carbon oilfield stations is developing towards a new integrated and collaborative model. In this process, multiple fields such as energy, transportation, information, and ecology are achieving deep integration. Existing solutions lack a comprehensive, multi-dimensional energy planning system to reduce energy management costs and improve the load efficiency of oilfield stations. Summary of the Invention

[0003] The purpose of this invention is to provide an energy regulation system, regulation method, and electronic device to address the shortcomings of existing solutions that lack a comprehensive and multi-dimensional energy planning system, thereby reducing energy management costs and improving the load efficiency of oilfield stations.

[0004] To achieve the above objectives, embodiments of the present invention provide an energy regulation system, comprising:

[0005] The Internet of Things (IoT) platform module is used to collect data from various equipment at oilfield stations;

[0006] The data platform module is used to preprocess the data from the various devices.

[0007] The algorithm platform module is used to perform energy regulation based on the preprocessed data from the various devices using operations research optimization algorithms or machine learning methods.

[0008] The business platform module is used to perform correlation analysis on the data of the various equipment based on the correlation analysis method, and to determine the operation strategy of the oilfield station based on the correlation analysis results.

[0009] Optionally, the energy regulation using operations research optimization algorithms based on the preprocessed data from the various devices includes:

[0010] The data from these various devices were determined as decision variables;

[0011] An objective function is constructed based on the decision variables, and the objective function characterizes the minimum operating cost of equipment at oilfield stations.

[0012] Constraints are constructed based on the energy utilization rate of the equipment at the oilfield station;

[0013] Solve the objective function that satisfies the constraints to obtain the optimal device dataset;

[0014] Energy regulation is performed on the oilfield station based on the optimal equipment dataset.

[0015] Optionally, the various device data includes operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed various device data using machine learning methods includes:

[0016] The operating data of the power generation equipment is used as the input data of the load forecasting model, and the load data of the load equipment is used as the label data of the operating data of the power generation equipment to train the load forecasting model.

[0017] The operating data of the power generation equipment to be predicted is input into the trained load prediction model to perform load prediction and obtain the load prediction results of the load equipment.

[0018] Energy regulation is carried out based on the load forecast results.

[0019] Optionally, the multiple equipment data packages include equipment production data and wellhead production data; the correlation analysis of the multiple equipment data based on the correlation analysis method, and the determination of the oilfield station operation strategy based on the correlation analysis results, include:

[0020] Correlation analysis of the equipment production data and the wellhead production data is performed based on grey relational analysis or Pearson correlation analysis.

[0021] Based on the correlation analysis results, target equipment production data with a correlation higher than a set threshold with the wellhead production data are determined, and the operation strategy of the oilfield station is determined based on the target equipment production data.

[0022] Optionally, the system further includes a microservice platform module, which manages the microservices in the IoT platform module, the data platform module, the algorithm platform module, and the business platform module; the microservices include at least one of registration, configuration, load balancing, gateway management, and circuit breaker / rate limiting.

[0023] Optionally, the system further includes an operation and maintenance platform module, which is used to perform operation and maintenance monitoring on the IoT platform module, the data platform module, the algorithm platform module, and the business platform module using at least one of the following methods: continuous integration, container orchestration, security scanning, service disaster recovery, alarms, and performance monitoring.

[0024] On the other hand, embodiments of the present invention also provide an energy regulation method applied to the aforementioned energy regulation system, the method comprising:

[0025] Collect data from various equipment at oilfield stations;

[0026] Data preprocessing is performed on the data from the various devices;

[0027] Energy regulation is performed based on the preprocessed data from the various devices using operations research optimization algorithms or machine learning methods.

[0028] Correlation analysis is performed on the data of the various equipment based on the correlation analysis method, and the operation strategy of the oilfield station is determined based on the correlation analysis results.

[0029] Optionally, the energy regulation using operations research optimization algorithms based on the preprocessed data from the various devices includes:

[0030] The data from these various devices were determined as decision variables;

[0031] An objective function is constructed based on the decision variables, and the objective function characterizes the minimum operating cost of equipment at oilfield stations.

[0032] Constraints are constructed based on the energy utilization rate of the equipment at the oilfield station;

[0033] Solve the objective function that satisfies the constraints to obtain the optimal device dataset;

[0034] Energy regulation is performed on the oilfield station based on the optimal equipment dataset.

[0035] Optionally, the various device data includes operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed various device data using machine learning methods includes:

[0036] The operating data of the power generation equipment is used as the input data of the load forecasting model, and the load data of the load equipment is used as the label data of the operating data of the power generation equipment to train the load forecasting model.

[0037] The operating data of the power generation equipment to be predicted is input into the trained load prediction model to perform load prediction and obtain the load prediction results of the load equipment.

[0038] Energy regulation is carried out based on the load forecast results.

[0039] Optionally, the multiple equipment data packages include equipment production data and wellhead production data; the correlation analysis of the multiple equipment data based on the correlation analysis method, and the determination of the oilfield station operation strategy based on the correlation analysis results, include:

[0040] Correlation analysis of the equipment production data and the wellhead production data is performed based on grey relational analysis or Pearson correlation analysis.

[0041] Based on the correlation analysis results, target equipment production data with a correlation higher than a set threshold with the wellhead production data are determined, and the operation strategy of the oilfield station is determined based on the target equipment production data.

[0042] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-described energy regulation method when executing the program.

[0043] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described energy regulation method.

[0044] On the other hand, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described energy regulation method.

[0045] Through the above technical solutions, embodiments of the present invention utilize operations research optimization algorithms or machine learning methods to perform energy regulation based on preprocessed data from various equipment; and perform correlation analysis on the data from these various equipment using correlation analysis methods, and determine the operation strategy of oilfield stations based on the correlation analysis results. Embodiments of the present invention reduce energy management costs and improve the load efficiency of oilfield stations by using operations research optimization algorithms or machine learning for energy regulation and determining operation strategies based on correlation analysis data analysis methods.

[0046] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0048] Figure 1 This is one of the structural schematic diagrams of the energy regulation system provided by the present invention;

[0049] Figure 2This is the second schematic diagram of the energy regulation system provided by the present invention;

[0050] Figure 3 This is the third schematic diagram of the energy regulation system provided by the present invention;

[0051] Figure 4 This is the fourth schematic diagram of the energy regulation system provided by the present invention;

[0052] Figure 5 This is a flowchart illustrating the energy regulation method provided by the present invention;

[0053] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0054] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0055] System Implementation Examples

[0056] Please refer to Figure 1 This invention provides an energy regulation system, comprising: an Internet of Things platform module 10, a data platform module 20, an algorithm platform module 30, a business platform module 40, a microservice platform module 50, and an operation and maintenance platform module 60.

[0057] The IoT platform module 10 is used to collect data from various devices at the oilfield station. It primarily stores and uploads data reported by the hardware devices. This data includes data from smart meters, inverters, fiber optic temperature sensors, load controllers, smart battery charge / discharge controllers, converters, energy storage controllers, environmental monitoring instruments, integrated photovoltaic and energy storage units, and oil density and viscosity sensors.

[0058] The data platform module 20 processes, analyzes, and displays the collected data, primarily through data dashboards and intelligent reports. Data processing mainly includes preprocessing the data from the various devices. Specifically, after collection, data cleaning and analysis are performed in the data platform module 20. For data cleaning, load-related data is cleaned using methods such as missing value handling, data discretization, and data standardization, based on the characteristics of the equipment data. For data from oilfield stations, due to the high frequency of data point reporting, equipment-related data is cleaned using methods such as deduplication and data standardization. The missing value handling, data discretization, and data standardization can be calculated using existing formulas; specific calculation formulas are not listed here.

[0059] After data analysis and cleaning, the data is stored based on the analysis results. Generally, a combination of time-series databases and relational databases is used. Time-series data is used to store equipment data, while the cleaned and analyzed results are stored in a relational database such as MySQL.

[0060] The algorithm platform module 30 utilizes operations research optimization algorithms and machine learning methods to optimize preprocessed data and apply the optimizations to real-world scenarios. For example, the algorithm platform module 30 can be used to perform energy regulation based on the preprocessed data from various devices using operations research optimization algorithms or machine learning methods.

[0061] Business platform module 40 is responsible for the precise control, detection, analysis, and explicit predictive capabilities of the energy regulation system, including algorithm platform capabilities. It is used to perform correlation analysis on data from various devices based on correlation analysis methods, and to determine the operational strategies for oilfield stations based on the correlation analysis results.

[0062] For example, in an oilfield well site scenario, equipment at the well site is regulated to achieve the goal of source following load. Through the overall system architecture design, over 1000 pieces of reported equipment data are received per second via the IoT platform module 10. After receiving the data, a rule engine performs structured processing on the equipment data. The data platform module 20 cleans, classifies, and aggregates the data before handing it over to the algorithm platform module 30. Operations research optimization algorithms and / or machine learning methods are used to calculate the data, resulting in a more economical energy dispatching scheme (e.g., storing electricity when electricity prices are low, and controlling the output of electricity from storage devices during peak hours to achieve better peak-valley arbitrage and save on grid electricity usage costs). In addition, the energy regulation system also performs correlation analysis on the operational data in the well site through the business platform module 40. The results of this correlation analysis identify equipment data that has a significant impact on oilfield well site production, enabling the formulation of comprehensive operational strategies. Based on these strategies, precise regulation of power generation and load equipment in the well site is implemented, increasing the proportion of green electricity by 30%.

[0063] Therefore, embodiments of the present invention utilize operations research optimization algorithms or machine learning methods to perform energy regulation based on preprocessed data from various equipment; and perform correlation analysis on the data from these various equipment using correlation analysis methods, and determine the operation strategy of the oilfield station based on the correlation analysis results. These embodiments of the present invention reduce energy management costs and improve the load efficiency of oilfield stations by using operations research optimization algorithms or machine learning for energy regulation and determining operation strategies based on correlation analysis data analysis methods.

[0064] In other aspects of the embodiments of the present invention, the energy regulation based on the preprocessed data of the various equipment using an operations research optimization algorithm includes: determining the various equipment data as decision variables; constructing an objective function based on the decision variables, wherein the objective function characterizes the minimum operating cost of the equipment at the oilfield station; constructing constraints based on the energy utilization rate of the equipment at the oilfield station; solving the objective function that satisfies the constraints to obtain an optimal equipment dataset; and performing energy regulation on the oilfield station based on the optimal equipment dataset.

[0065] This invention can determine the usage time and unit time operating cost of various devices (inverters, converters, etc.) as decision variables. Based on these decision variables, this invention constructs an objective function as follows:

[0066]

[0067] Where C represents the operating cost of equipment at the oilfield station, x i c is the usage time of device i; i Let be the unit time operating cost of device i; n is the total number of devices.

[0068] The constraints for energy utilization based on the equipment at the oilfield station in this embodiment of the invention are as follows:

[0069]

[0070] Among them, g i e represents the power generation efficiency of device i; i x represents the energy consumption of device i per unit time. i η is the usage time of device i; target This represents the desired energy efficiency; n is the total number of devices.

[0071] It should be noted that, in addition to the constraint on energy utilization rate, other possible constraints need to be considered, such as: equipment capacity constraint: the power generation of each piece of equipment cannot exceed its maximum capacity; energy supply constraint: total energy consumption cannot exceed the available energy supply; and time or period constraint: if the differences in electricity prices or changes in energy demand during different time periods (such as peak, normal, and off-peak hours) are considered, time or period constraints also need to be introduced. These constraints can be expressed as linear inequalities or equations and added to the linear programming model.

[0072] Through the above steps, we can construct a linear programming model that represents the objective function of minimizing the operating cost of oilfield stations and the constraints of energy utilization efficiency. Then, a linear programming solver (such as MATLAB or Python's SciPy library) can be used to solve this model to find the optimal equipment dataset representing the optimal equipment usage scheme. Energy regulation of the oilfield stations can then be implemented based on this optimal equipment dataset. These schemes ensure that energy utilization is maximized and costs are minimized while meeting the oilfield's production needs.

[0073] In other aspects of the embodiments of the present invention, the multiple device data includes operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed multiple device data using machine learning methods includes: using the operating data of the power generation equipment as input data of a load prediction model, using the load data of the load equipment as label data of the operating data of the power generation equipment, and training the load prediction model; inputting the operating data of the power generation equipment to be predicted into the trained load prediction model to perform load prediction, and obtaining the load prediction result of the load equipment; and performing energy regulation based on the load prediction result.

[0074] In one embodiment, the efficiency of coordinated operation between power generation equipment and load equipment is improved. To this end, a large amount of operational data can be collected, including the output power of power generation equipment, the electricity demand of load equipment, and the load status of the power grid. Then, machine learning algorithms (such as support vector machines, neural networks, etc.) are used to analyze and model this data.

[0075] In this embodiment of the invention, the operating data of the power generation equipment (which may be historical operating data) is used as input data for the load forecasting model, and the load data of the load equipment is used as label data for the operating data of the power generation equipment. The load forecasting model is trained by this method. Through training, the correlation and influence patterns between the power generation equipment and the load equipment can be obtained. These patterns can be used to predict future energy demand. Based on these prediction results, more precise energy regulation schemes can be formulated. For example, when the electricity demand of the load equipment (peak grid load) is predicted to arrive based on the operating data of the power generation equipment, the output power of the power generation equipment can be adjusted in advance to meet the load demand and avoid grid fluctuations. Alternatively, during peak electricity demand, the power output of energy storage devices can be regulated to achieve better peak-valley arbitrage and save on grid electricity usage costs. The load forecasting model can be constructed based on support vector machines, neural networks, etc. The training of the load forecasting model can be performed using existing supervised methods; the training process is not detailed here.

[0076] In summary, machine learning methods learn patterns and rules from historical data to provide intelligent decision support for oil fields, thereby reducing energy management costs and improving the load efficiency of oil field stations.

[0077] In other aspects of the embodiments of the present invention, the multiple equipment data includes equipment production data and wellhead production data; the correlation analysis of the multiple equipment data based on the correlation analysis method, and the determination of the operation strategy of the oilfield station based on the correlation analysis results, includes: performing correlation analysis of the equipment production data and the wellhead production data based on the grey relational analysis method or the Pearson correlation analysis method; determining the target equipment production data whose correlation with the wellhead production data is higher than a set threshold based on the correlation analysis results; and determining the operation strategy of the oilfield station based on the target equipment production data.

[0078] Oilfield station equipment production data includes key indicators such as oil-water ratio, daily fluid production, equipment energy consumption, and equipment operating status. First, it is necessary to ensure the accuracy and completeness of this data and to classify and organize it appropriately. This embodiment of the invention establishes a mathematical model based on the principles of grey relational analysis or Pearson correlation analysis to calculate the correlation between various factors and wellhead production. This embodiment of the invention substitutes the collected equipment production data and wellhead production data into the mathematical model to calculate the correlation between each factor (such as oil-water ratio, daily fluid production, equipment energy consumption, and equipment operating status) and wellhead production. According to the calculation results, if the correlation between the oil-water ratio and daily fluid production is high (i.e., higher than a set threshold), while the correlation between equipment energy consumption and equipment operating status is relatively low, this indicates that changes in the oil-water ratio and daily fluid production have a significant impact on wellhead production, while equipment energy consumption and equipment operating status, although having some influence, are relatively minor. Based on the above correlation analysis results, the following operational strategies can be formulated: optimize oil production processes and increase daily fluid production. Specific methods for optimizing oil production processes are as follows: For oil wells with high oil-water ratios, the oil-water ratio can be reduced and crude oil recovery improved by adjusting production process parameters such as water injection volume and production rate. Simultaneously, monitoring and management of oil wells should be strengthened to promptly identify and address any abnormalities in well production, ensuring stable production. Specific methods for increasing daily fluid production are as follows: Daily fluid production can be increased by increasing the water injection volume of injection wells or adjusting the water injection plan. Maintenance and upkeep of oil wells should be strengthened to ensure normal operation and efficient production. This invention's embodiments utilize a data analysis method based on correlation analysis to determine operational strategies, thereby reducing energy management costs and improving the load efficiency of oilfield stations.

[0079] In other aspects of this embodiment, the system further includes a microservice platform module 50, which manages the microservices in the IoT platform module 10, the data platform module 20, the algorithm platform module 30, and the business platform module 40. The microservices include at least one of registration, configuration, load balancing, gateway management, and circuit breaker / rate limiting. Registration refers to service registration and discovery, where service providers register their metadata information with a service registry, and service consumers obtain service instance information from the service provider by querying the service registry, enabling dynamic service invocation and loose coupling. Configuration refers to microservice configuration management, which is the process of unified management and control of configuration data for various services in a microservice architecture, including externalized configuration, dynamic configuration, version control, and auditing, to improve the system's flexibility and maintainability. The system also includes an operations and maintenance platform module 60, which uses at least one of continuous integration, container orchestration, security scanning, service disaster recovery, alerting, and performance monitoring to perform operations and maintenance monitoring on the IoT platform module 10, the data platform module 20, the algorithm platform module 30, and the business platform module 40.

[0080] It should be noted that the energy regulation system of this invention can also be divided using an architectural approach. Please refer to... Figure 2 The energy control system is designed according to the cloud, edge, and terminal architecture. This architecture diagram describes an enterprise-level cloud platform that achieves comprehensive monitoring and management from hardware devices to cloud services through a multi-layered structure. The application layer provides alarm, project management, and intelligent reporting functions; the cloud layer is responsible for the log system, operation and maintenance monitoring, resource scheduling, and storage management; the IoT layer supports device access and data acquisition through various protocols; the edge layer contains intelligent devices for data collection and preliminary processing; and the hardware layer consists of physical devices that perform energy conversion and environmental monitoring tasks. Furthermore, a large-screen display provides a multi-dimensional visual monitoring interface, while the gateway and service layers ensure secure data transmission, reasonable service scheduling, and stable system operation. The entire architecture aims to build an efficient, scalable, and secure monitoring and management environment. The cloud layer is mainly implemented through the business platform module 40, data platform module 20, and algorithm platform module 30. The edge layer is implemented through the IoT platform module 10.

[0081] Please refer to Figure 3The energy control system of this invention is divided into technical architectures, with core components including a registry center (Nacos), a configuration center, a message center, scheduled tasks (QuartzJob), service assurance (Sentinel), and front-end, access, and gateway services. The energy control system adopts the Spring Boot framework, achieving rapid service iteration and elastic scaling through automated deployment tools (such as Jenkins) and container technologies (Docker and Kubernetes). Monitoring services (including Skywalking and Prometheus) ensure system stability and performance. Furthermore, the energy control system integrates a MySQL database, a Redis caching service, NGeNX as a reverse proxy server, as well as large-screen services and cloud platform services, supporting monitoring from mobile devices. The entire energy control system is designed to achieve high availability, maintainability, and scalability.

[0082] Please refer to Figure 4 The energy regulation system of this invention is divided according to a data architecture, including 10 parts as follows:

[0083] 1. Data Application Layer

[0084] BI analytics: Business intelligence analytics, used to provide decision support.

[0085] Data dashboard: A data visualization tool used to monitor and display key metrics.

[0086] Business analytics: Analyzing business data to optimize business processes and decision-making.

[0087] 2. Data Service Layer

[0088] Data Development Management: Manage the data development process to ensure data quality and consistency.

[0089] API services: Provide application programming interfaces that enable external systems to access and manipulate data.

[0090] Authentication management: Controls data access permissions to ensure data security.

[0091] Online query: Supports real-time data query.

[0092] Ad-hoc queries: allow users to execute non-pre-planned queries.

[0093] Metadata management: Managing descriptive information about data, such as data structure and source.

[0094] 3. Data Management

[0095] Data lineage: Tracking the source and flow of data to understand its lifecycle.

[0096] Data assets: Managing and maintaining data assets, including data classification and value assessment.

[0097] Data development components: tools and processes for data extraction, transformation, and loading (ETL).

[0098] 4. Safety and Operations Management

[0099] Security: Ensure data security, including access control and data encryption.

[0100] Operations: Routine operational activities involving data, such as monitoring and maintenance.

[0101] 5. Data storage and processing

[0102] ODS (Operational Data Store): Stores operational data used for daily business operations. DWD (Data Warehouse Detail Layer): Stores cleaned and integrated detailed data. DWS (Data Warehouse Service Layer): Provides data services such as data summarization and reporting. ADS (Application Data Store): Stores application-layer data used for specific applications.

[0103] 6. Data Quality Management

[0104] Data quality: Ensure the accuracy, completeness, and consistency of data.

[0105] Scheduling and management: Arranging and monitoring the execution of data processing tasks.

[0106] 7. Data aggregation and lifecycle management

[0107] Data aggregation: centralizing data from different sources.

[0108] Oilfield load data: Data specific to a particular field, such as the load data of an oilfield.

[0109] Lifecycle management: Managing the entire lifecycle of data from creation to destruction.

[0110] Small file merging: Optimizes storage by merging multiple small files into a large file.

[0111] Real-time access: Supports the access and processing of real-time data.

[0112] Offline synchronization: Regularly synchronize data to ensure data consistency.

[0113] Heterogeneous data sources: Processing data from different types of data sources.

[0114] 8. Data Visualization and Configuration

[0115] Visual configuration: Configure data display and reporting through a graphical interface.

[0116] Load data center: A management and analysis center specifically for load data.

[0117] 9. Technological Infrastructure

[0118] Computing and storage: Provides resources for data computation and storage.

[0119] MySQL: A relational database management system.

[0120] TDengine: A database designed specifically for time series data.

[0121] MPP: Massively Parallel Processing Database.

[0122] HDFS: Distributed File System, used to store large amounts of data.

[0123] 10. Data access for specific fields

[0124] Oilfield Data Center: Manages and analyzes oilfield-related data.

[0125] Data access: This includes data processing from devices such as inverters, environmental monitoring instruments, integrated photovoltaic and energy storage systems, load controllers, and smart meters.

[0126] In summary, the energy control system of this invention is deployed at a well site in the Hainan region. Phase I focuses on providing new energy sources and assisting microgrid control, completing the construction of a microgrid monitoring cloud platform and data access capabilities. It also utilizes a data monitoring platform integrating web and mobile terminals to achieve intelligent comprehensive energy management. Phase II builds upon Phase I, further enhancing the energy control system's functionality. This aims to help the zero-carbon well site achieve more refined comprehensive energy control management. The completed zero-carbon well site energy control system is a three-dimensional system integrating operational functions, monitoring, and load control. It possesses the ability to economically control energy within the well site, outputting energy control plans and intelligent reports. Data is interconnected with various cloud platforms, supporting the well site's green electricity ratio and dual-carbon related auxiliary capabilities. It also incorporates the promotional capabilities of demonstration sites, assisting in the energy transformation of oilfield well sites.

[0127] This invention utilizes next-generation digital technologies such as cloud computing, big data, the Internet of Things, mobile internet, and artificial intelligence to integrate elements such as products, demands, interactions, data, and tools, thereby optimizing operational processes and business models and providing strong support for the comprehensive energy management of zero-carbon oilfield stations.

[0128] This invention, through the construction of an energy control system for oilfield well sites, achieves integrated management and complementary utilization of different energy forms such as electricity, natural gas, and petroleum products. This intelligent energy coordination not only improves energy efficiency but also effectively reduces overall energy management costs. Furthermore, through risk control mechanisms, it enhances the resilience of the energy supply system in the face of extreme natural disasters, reducing potential economic losses.

[0129] By utilizing the energy control system at oilfield well sites, multi-dimensional analysis and decision-making support for regional energy consumption can help optimize and adjust the energy structure towards a low-carbon and environmentally friendly direction. This not only helps reduce energy consumption costs but also promotes the development of a low-carbon economy, providing a solid foundation for achieving green GDP growth and supporting sustainable economic development.

[0130] By aggregating refined energy data and combining it with urban operational data and other cross-domain data, intelligent energy management platforms for oilfield well sites can enhance the value of energy data assets. This data-driven approach can provide deeper insights into energy management and optimize energy usage strategies.

[0131] The energy control system at oilfield well sites has achieved cross-regional and cross-departmental information sharing and business collaboration by integrating existing resources. This integration not only improves the efficiency of energy management, but also enhances the level of refined management of regional energy supply and consumption through digitalization, grid-based management, intelligentization, and standardization, thereby increasing the work efficiency of various functional departments.

[0132] The energy regulation system at oilfield well sites promotes a green, low-carbon, and circular economy by reducing the use of high-carbon energy sources and lowering greenhouse gas emissions. This not only helps achieve a win-win situation for economic development and environmental protection, but also enhances well-being by reducing pollution and improving quality of life, resulting in significant social and environmental benefits.

[0133] The energy control system includes a processor and a memory. The IoT platform module 10, data platform module 20, algorithm platform module 30, and business platform module 40 are all stored in the memory as program units. The processor executes the program units stored in the memory to achieve the corresponding functions.

[0134] A processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured.

[0135] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0136] Method Implementation Examples

[0137] On the other hand, please refer to Figure 5 This invention also provides an energy regulation method applied to the aforementioned energy regulation system, the method comprising:

[0138] Step 100: Collect data from various equipment at the oilfield station.

[0139] Step 200: Perform data preprocessing on the data from the various devices.

[0140] Step 300: Utilize operations research optimization algorithms or machine learning methods to perform energy regulation based on the preprocessed data from the various devices.

[0141] Step 400: Perform correlation analysis on the data of the various equipment based on the correlation analysis method, and determine the operation strategy of the oilfield station based on the correlation analysis results.

[0142] For example, in an oilfield well site scenario, equipment at the well site is regulated to achieve the goal of source following load. Through the overall system architecture design, over 1000 pieces of reported equipment data are received per second via the IoT platform module 10 within the system architecture. After receiving the data, a rule engine performs structured processing on the equipment data. The data platform module 20 cleans, classifies, and aggregates the data before handing it over to the algorithm platform module 30. This data is then processed using operations research optimization algorithms and machine learning methods to derive a more economical energy dispatching scheme (e.g., storing electricity when electricity prices are low, and controlling power output during peak hours to achieve better peak-valley arbitrage and save on grid electricity usage costs). In addition, the energy regulation system also performs correlation analysis on the operational data at the well site through the business platform module 40. The results of this correlation analysis identify equipment data that significantly impacts oilfield well site production, enabling the formulation of comprehensive operational strategies. Based on these strategies, precise regulation of power generation and load equipment at the well site is implemented, increasing the proportion of green electricity by 30%.

[0143] Therefore, embodiments of the present invention utilize operations research optimization algorithms or machine learning methods to perform energy regulation based on preprocessed data from various equipment; and perform correlation analysis on the data from these various equipment using correlation analysis methods, and determine the operation strategy of the oilfield station based on the correlation analysis results. These embodiments of the present invention reduce energy management costs and improve the load efficiency of oilfield stations by using operations research optimization algorithms or machine learning for energy regulation and determining operation strategies based on correlation analysis data analysis methods.

[0144] Furthermore, the energy regulation using operations research optimization algorithms based on the preprocessed data of various equipment includes: determining the various equipment data as decision variables; constructing an objective function based on the decision variables, wherein the objective function characterizes minimizing the operating cost of the equipment at the oilfield station; constructing constraints based on the energy utilization rate of the equipment at the oilfield station; solving the objective function that satisfies the constraints to obtain the optimal equipment dataset; and performing energy regulation on the oilfield station based on the optimal equipment dataset.

[0145] This invention can determine the usage time and unit time operating cost of various devices (inverters, converters, etc.) as decision variables. Based on these decision variables, this invention constructs an objective function as follows:

[0146]

[0147] Where C represents the operating cost of equipment at the oilfield station, x i c is the usage time of device i; i Let be the unit time operating cost of device i; n is the total number of devices.

[0148] The constraints for energy utilization based on the equipment at the oilfield station in this embodiment of the invention are as follows:

[0149]

[0150] Among them, g i e represents the power generation efficiency of device i; i x represents the energy consumption of device i per unit time. i η is the usage time of device i; target This represents the desired energy efficiency; n is the total number of devices.

[0151] It should be noted that, in addition to the constraint on energy utilization rate, other possible constraints need to be considered, such as: equipment capacity constraint: the power generation of each piece of equipment cannot exceed its maximum capacity; energy supply constraint: total energy consumption cannot exceed the available energy supply; and time or period constraint: if the differences in electricity prices or changes in energy demand during different time periods (such as peak, normal, and off-peak hours) are considered, time or period constraints also need to be introduced. These constraints can be expressed as linear inequalities or equations and added to the linear programming model.

[0152] Through the above steps, we can construct a linear programming model that represents the objective function of minimizing the operating cost of oilfield stations and the constraints of energy utilization efficiency. Then, a linear programming solver (such as MATLAB or Python's SciPy library) can be used to solve this model to find the optimal equipment dataset representing the optimal equipment usage scheme. Energy regulation of the oilfield stations can then be implemented based on this optimal equipment dataset. These schemes ensure that energy utilization is maximized and costs are minimized while meeting the oilfield's production needs.

[0153] Furthermore, the various equipment data include operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed various equipment data using machine learning methods includes: using the operating data of the power generation equipment as input data for a load prediction model, using the load data of the load equipment as label data for the operating data of the power generation equipment, and training the load prediction model; inputting the operating data of the power generation equipment to be predicted into the trained load prediction model to perform load prediction, and obtaining the load prediction result of the load equipment; and performing energy regulation based on the load prediction result.

[0154] In this embodiment of the invention, the operating data of the power generation equipment (which may be historical operating data) is used as input data for the load forecasting model, and the load data of the load equipment is used as label data for the operating data of the power generation equipment. The load forecasting model is trained by this method. Through training, the correlation and influence patterns between the power generation equipment and the load equipment can be obtained. These patterns can be used to predict future energy demand. Based on these prediction results, more precise energy regulation schemes can be formulated. For example, when the electricity demand of the load equipment (peak grid load) is predicted to arrive, the output power of the power generation equipment can be adjusted in advance to meet the load demand and avoid grid fluctuations. Alternatively, during peak electricity demand, the power output of energy storage devices can be regulated to achieve better peak-valley arbitrage and save on grid electricity usage costs. The load forecasting model can be constructed based on support vector machines, neural networks, etc. The training of the load forecasting model can be performed using existing supervised methods; the training process is not detailed here.

[0155] In summary, machine learning methods learn patterns and rules from historical data to provide intelligent decision support for oil fields, thereby reducing energy management costs and improving the load efficiency of oil field stations.

[0156] Furthermore, the multiple equipment data packages include equipment production data and wellhead production data; the correlation analysis of the multiple equipment data based on the correlation analysis method, and the determination of the oilfield station's operation strategy based on the correlation analysis results, includes: performing correlation analysis on the equipment production data and the wellhead production data based on the grey relational analysis method or the Pearson correlation analysis method; determining target equipment production data whose correlation with the wellhead production data is higher than a set threshold based on the correlation analysis results; and determining the oilfield station's operation strategy based on the target equipment production data.

[0157] Oilfield station equipment production data includes key indicators such as oil-water ratio, daily fluid production, equipment energy consumption, and equipment operating status. First, it is necessary to ensure the accuracy and completeness of this data and to classify and organize it appropriately. This embodiment of the invention establishes a mathematical model based on the principles of grey relational analysis or Pearson correlation analysis to calculate the correlation between various factors and wellhead production. This embodiment of the invention substitutes the collected equipment production data and wellhead production data into the mathematical model to calculate the correlation between each factor (such as oil-water ratio, daily fluid production, equipment energy consumption, and equipment operating status) and wellhead production. According to the calculation results, if the correlation between the oil-water ratio and daily fluid production is high (i.e., higher than a set threshold), while the correlation between equipment energy consumption and equipment operating status is relatively low, this indicates that changes in the oil-water ratio and daily fluid production have a significant impact on wellhead production, while equipment energy consumption and equipment operating status, although having some influence, are relatively minor. Based on the above correlation analysis results, the following operational strategies can be formulated: optimize oil production processes and increase daily fluid production. Specific methods for optimizing oil production processes are as follows: For oil wells with high oil-water ratios, the oil-water ratio can be reduced and crude oil recovery improved by adjusting production process parameters such as water injection volume and production rate. Simultaneously, monitoring and management of oil wells should be strengthened to promptly identify and address any abnormalities in well production, ensuring stable production. Specific methods for increasing daily fluid production are as follows: Daily fluid production can be increased by increasing the water injection volume of injection wells or adjusting the water injection plan. Maintenance and upkeep of oil wells should be strengthened to ensure normal operation and efficient production. This invention's embodiments utilize a data analysis method based on correlation analysis to determine operational strategies, thereby reducing energy management costs and improving the load efficiency of oilfield stations.

[0158] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute an energy regulation method. This method includes: collecting various equipment data from an oilfield station; preprocessing the various equipment data; using operations research optimization algorithms or machine learning methods to perform energy regulation based on the preprocessed equipment data; performing correlation analysis on the various equipment data based on a correlation analysis method; and determining the oilfield station's operation strategy based on the correlation analysis results.

[0159] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a machine-readable storage medium. When the computer program is executed by a processor, the computer is able to execute an energy regulation method, which includes: collecting various equipment data from an oilfield station; performing data preprocessing on the various equipment data; performing energy regulation based on the preprocessed various equipment data using operations research optimization algorithms or machine learning methods; performing correlation analysis on the various equipment data based on a correlation analysis method; and determining the operation strategy of the oilfield station based on the correlation analysis results.

[0161] In another aspect, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform an energy regulation method, the method comprising: collecting various equipment data from an oilfield station; performing data preprocessing on the various equipment data; performing energy regulation based on the data preprocessed using operations research optimization algorithms or machine learning methods; performing correlation analysis on the various equipment data based on a correlation analysis method; and determining the operation strategy of the oilfield station based on the correlation analysis results.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these modifications or substitutions do 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. An energy regulation system, characterized in that, include: The Internet of Things (IoT) platform module is used to collect data from various equipment at oilfield stations; The data platform module is used to preprocess the data from the various devices. The algorithm platform module is used to perform energy regulation based on the preprocessed data from the various devices using operations research optimization algorithms or machine learning methods. The business platform module is used to perform correlation analysis on the data of the various equipment based on the correlation analysis method, and to determine the operation strategy of the oilfield station based on the correlation analysis results.

2. The energy regulation system according to claim 1, characterized in that, The energy regulation using operations research optimization algorithms based on the preprocessed data from various devices includes: The data from these various devices were determined as decision variables; An objective function is constructed based on the decision variables, and the objective function characterizes the minimum operating cost of equipment at oilfield stations. Constraints are constructed based on the energy utilization rate of the equipment at the oilfield station; Solve the objective function that satisfies the constraints to obtain the optimal device dataset; Energy regulation is performed on the oilfield station based on the optimal equipment dataset.

3. The energy regulation system according to claim 1, characterized in that, The various equipment data include operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed various equipment data using machine learning methods includes: The operating data of the power generation equipment is used as the input data of the load forecasting model, and the load data of the load equipment is used as the label data of the operating data of the power generation equipment to train the load forecasting model. The operating data of the power generation equipment to be predicted is input into the trained load prediction model to perform load prediction and obtain the load prediction results of the load equipment. Energy regulation is carried out based on the load forecast results.

4. The energy regulation system according to claim 1, characterized in that, The data package contains equipment production data and wellhead production data; the correlation analysis method is used to perform correlation analysis on the data from the various equipment, and the operation strategy of the oilfield station is determined based on the correlation analysis results, including: Correlation analysis of the equipment production data and the wellhead production data is performed based on grey relational analysis or Pearson correlation analysis. Based on the correlation analysis results, target equipment production data with a correlation higher than a set threshold with the wellhead production data are determined, and the operation strategy of the oilfield station is determined based on the target equipment production data.

5. The energy regulation system according to claim 1, characterized in that, The system also includes a microservice platform module, which manages the microservices in the IoT platform module, the data platform module, the algorithm platform module, and the business platform module; the microservices include at least one of registration, configuration, load balancing, gateway management, and circuit breaker rate limiting.

6. The energy regulation system according to claim 1, characterized in that, The system also includes an operations and maintenance platform module, which is used to perform operations and maintenance monitoring on the IoT platform module, the data platform module, the algorithm platform module, and the business platform module using at least one of the following methods: continuous integration, container orchestration, security scanning, service disaster recovery, alarms, and performance monitoring.

7. An energy regulation method, characterized in that, The method, applied to the energy control system according to any one of claims 1 to 6, comprises: Collect data from various equipment at oilfield stations; Data preprocessing is performed on the data from the various devices; Energy regulation is performed based on the preprocessed data from the various devices using operations research optimization algorithms or machine learning methods. Correlation analysis is performed on the data of the various equipment based on the correlation analysis method, and the operation strategy of the oilfield station is determined based on the correlation analysis results.

8. The energy regulation method according to claim 7, characterized in that, The energy regulation using operations research optimization algorithms based on the preprocessed data from various devices includes: The data from these various devices were determined as decision variables; An objective function is constructed based on the decision variables, and the objective function characterizes the minimum operating cost of equipment at oilfield stations. Constraints are constructed based on the energy utilization rate of the equipment at the oilfield station; Solve the objective function that satisfies the constraints to obtain the optimal device dataset; Energy regulation is performed on the oilfield station based on the optimal equipment dataset.

9. The energy regulation method according to claim 7, characterized in that, The various equipment data include operating data of power generation equipment and load data of load equipment; the energy regulation based on the preprocessed various equipment data using machine learning methods includes: The operating data of the power generation equipment is used as the input data of the load forecasting model, and the load data of the load equipment is used as the label data of the operating data of the power generation equipment to train the load forecasting model. The operating data of the power generation equipment to be predicted is input into the trained load prediction model to perform load prediction and obtain the load prediction results of the load equipment. Energy regulation is carried out based on the load forecast results.

10. The energy regulation method according to claim 7, characterized in that, The data package contains equipment production data and wellhead production data; the correlation analysis method is used to perform correlation analysis on the data from the various equipment, and the operation strategy of the oilfield station is determined based on the correlation analysis results, including: Correlation analysis of the equipment production data and the wellhead production data is performed based on grey relational analysis or Pearson correlation analysis. Based on the correlation analysis results, target equipment production data with a correlation higher than a set threshold with the wellhead production data are determined, and the operation strategy of the oilfield station is determined based on the target equipment production data.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the energy regulation method according to any one of claims 7 to 10.

12. A machine-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the energy regulation method according to any one of claims 7 to 10.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the energy regulation method according to any one of claims 7 to 10.

Images