Energy aggregation dispatching management platform with multi-data linkage

Abstract

The invention discloses a multi-data linked energy aggregation dispatching management platform, which relates to the field of energy management. The platform includes: a power station acquisition module for obtaining thermal power stations, photovoltaic power stations and wind power stations; an energy aggregation dispatching center construction module for pre-building an energy aggregation dispatching center; a production order information acquisition module for obtaining production order information; a production task allocation module for performing production task allocation; an energy consumption prediction module for performing energy consumption prediction; an energy aggregation supply analysis module for performing energy aggregation supply analysis; and an energy dynamic dispatching module for receiving energy dispatching parameter sequences and performing multi-cycle energy dynamic dispatching. The platform solves the technical problem of poor dispatching flexibility and low energy utilization efficiency in the existing energy dispatching management, and achieves the technical effect of improving dispatching flexibility and thus improving energy utilization efficiency.

Description

Technical Field

[0001] The present application relates to fields related to energy management, and in particular to an energy aggregation scheduling management platform with multi-data linkage. Background Art

[0002] With the continuous growth of global energy demand and the diversified development of energy structure, energy management and scheduling have become key links to ensure the stable and efficient operation of industrial production. Especially in the industrial field, facing the complex and changing production demand and energy supply environment, how to achieve efficient utilization and flexible scheduling of energy has become an important issue that needs to be solved urgently. Traditional energy management systems often rely on the centralized scheduling of a single energy type (such as thermal power generation), which is difficult to adapt to the intermittent and uncertain nature of renewable energy (such as photovoltaic and wind power), and lack the ability to coordinate and optimize multiple energy sources.

[0003] Among the current related technologies, energy scheduling management has the technical problem of poor scheduling flexibility, which leads to low energy utilization efficiency. Summary of the invention

[0004] This application provides an energy aggregation scheduling management platform with multi-data linkage. By integrating multiple modules such as power station acquisition, energy aggregation scheduling center construction, production order information acquisition, production task allocation, energy consumption forecasting, energy aggregation supply analysis and energy dynamic scheduling, it realizes the coordinated optimization and dynamic scheduling of various energy sources such as thermal power generation, photovoltaic power generation and wind power generation, and achieves the technical effect of improving scheduling flexibility and thus improving energy utilization efficiency.

[0005] This application provides a multi-data-linked energy aggregation dispatch management platform, including:

[0006] A power station acquisition module, the power station acquisition module is used to interactively obtain the thermal power station, photovoltaic power station and wind power station used to supply energy for the target industrial zone; an energy aggregation dispatching center construction module, the energy aggregation dispatching center construction module is used to pre-build the energy aggregation dispatching center, and after connecting the thermal power station, photovoltaic power station and wind power station to the energy aggregation dispatching center, authorize the energy aggregation dispatching center to perform energy dispatching operations of the thermal power station, photovoltaic power station and wind power station; a production order information acquisition module, the production order information acquisition module is used to interactively obtain the production order information of the target industrial zone; a production task allocation module, the production task allocation module is used to allocate production tasks according to the production order information, and obtain production A task sequence, wherein the production task sequence includes multiple production task information and multiple production windows; an energy consumption prediction module, wherein the energy consumption prediction module is used to perform energy consumption prediction based on the multiple production task information to obtain an electric energy consumption sequence; an energy aggregation supply analysis module, wherein the energy aggregation supply analysis module is used to collect environmental data based on the multiple production windows, and perform energy aggregation supply analysis based on the collection results and the electric energy consumption sequence to obtain an energy scheduling parameter sequence; an energy dynamic scheduling module, wherein the energy dynamic scheduling module is used for the energy aggregation scheduling center to receive the energy scheduling parameter sequence, and perform multi-cycle energy dynamic scheduling on the thermal power station, photovoltaic power station and wind power station according to the energy scheduling parameter sequence within the multiple production windows.

[0007] In a possible implementation, the production task allocation module is used to:

[0008] Decompose the production order information to obtain multiple production task information; use the multiple production task information to traverse the production log of the target industrial zone to obtain multiple production resource requirements; use the multiple production task information to traverse the production log to obtain multiple historical production quantities and multiple historical production times, and calculate and obtain the multiple production windows based on the multiple historical production quantities, multiple historical production times and the multiple production task information; use the multiple production window mappings to perform identification processing on the multiple production task information; interactively obtain the production resource information of the target industrial zone, and sort the multiple production task information according to the production resource information and the multiple production resource requirements to obtain the production task sequence.

[0009] In a possible implementation, the water supply station acquisition module is used to:

[0010] Interactively obtain a water supply station used for production water supply to the target industrial area; after connecting the water supply station to the energy aggregation dispatching center, authorize the energy aggregation dispatching center to perform energy dispatching operations of the water supply station.

[0011] In a possible implementation, the energy consumption prediction module is further used for:

[0012] Interactively obtain historical production consumption data, wherein the historical production consumption data includes multiple historical task electricity consumption and multiple historical task water energy consumption of multiple historical production tasks; perform multi-dimensional energy consumption regression analysis based on the historical production consumption data, and construct and generate an energy consumption analysis model based on the analysis results; synchronize the multiple production task information to the energy consumption analysis model to obtain the water energy consumption sequence and the electricity consumption sequence.

[0013] In a possible implementation, the energy consumption prediction module is further used for:

[0014] Aggregate the historical production and consumption data based on task type to obtain M groups of historical production tasks, M groups of historical task electricity consumption and M groups of historical task water energy consumption of M types of sample production tasks; extract output from the M groups of historical production tasks to obtain M groups of production output; perform regression analysis on the M groups of production output and the M groups of historical task electricity consumption to obtain M electricity consumption functions; perform regression analysis on the M groups of production output and the M groups of historical task water energy consumption to obtain M water energy consumption functions; complete the construction of an electricity consumption analysis branch by associating and storing the M types of sample production tasks and the M electricity consumption functions based on the knowledge graph; complete the construction of a water energy consumption analysis branch by associating and storing the M types of sample production tasks and the M water energy consumption functions based on the knowledge graph; connect the electricity consumption analysis branch and the water energy consumption analysis branch in parallel to complete the pre-construction of the energy consumption analysis model.

[0015] In a possible implementation, the energy aggregation supply analysis module is further used to:

[0016] Extracting the first production task information from the production task sequence in sequence, wherein the first production task information is identified by the first production window; extracting the first electric energy demand and the first water energy demand from the water energy consumption sequence and the electric energy consumption sequence according to the first production task information; collecting environmental data with the first production window as a constraint to obtain the first energy-related data, wherein the first energy-related data includes the first photovoltaic-related data and the first wind power-related data; performing power generation prediction according to the first energy-related data to obtain the first real-time power generation; calculating the first real-time power generation gap according to the first electric energy demand and the first real-time power generation; the first real-time power generation gap and the first water energy demand constitute the first energy scheduling parameter, wherein the energy aggregation scheduling center performs distributed energy scheduling on the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy scheduling parameter within the first production window; and so on, obtaining multiple energy scheduling parameters of the multiple production windows, splicing the multiple energy scheduling parameters according to the production task sequence to constitute the energy scheduling parameter sequence.

[0017] In a possible implementation, the energy aggregation supply analysis module is further used to:

[0018] A standard energy consumption update node is preset, and a first data update node is located in the first production window according to the standard energy consumption update node; second production task information is sequentially extracted from the production task sequence, wherein the second production task information adopts the second production window identifier; when the energy aggregation dispatching center performs distributed energy dispatching to the first data update node for the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy dispatching parameter within the first production window; environmental data is collected with the second production window as a constraint to obtain second update associated data, wherein the second update associated data includes second photovoltaic update data and second wind power update data; second energy associated data of the second production window is extracted from the collection result, and it is determined whether the second photovoltaic update data and the second wind power update data are consistent with the mapping of the second photovoltaic associated data and the second wind power associated data; if the second photovoltaic update data is inconsistent with the second photovoltaic associated data, and / or the second wind power update data is inconsistent with the second wind power associated data, the second energy dispatching parameter in the energy dispatching parameter sequence is locally updated at the first data update node.

[0019] In a possible implementation, the energy aggregation supply analysis module is further used to:

[0020] Extract and obtain multiple real-time power generation gaps based on the multiple energy scheduling parameters; synchronize the multiple real-time power generation gaps to a pre-built fuel demand analysis model to reverse the fuel demand and obtain multiple real-time fuel demand amounts; add the multiple real-time fuel demand amounts to obtain a fuel usage benchmark; interact with the thermal power station to obtain real-time fuel storage; and obtain fuel scheduling instructions based on the real-time fuel storage and fuel usage benchmark analysis.

[0021] It is planned to use the multi-data linked energy aggregation dispatching management platform proposed in this application, interactively obtain the thermal power station, photovoltaic power station and wind power station used for the target industrial zone production energy supply through the power station acquisition module, pre-build the energy aggregation dispatching center through the energy aggregation dispatching center construction module, and after connecting the thermal power station, photovoltaic power station and wind power station to the energy aggregation dispatching center, authorize the energy aggregation dispatching center to perform energy dispatching operations of the thermal power station, photovoltaic power station and wind power station, interactively obtain the production order information of the target industrial zone through the production order information acquisition module, and perform production task allocation according to the production order information through the production task allocation module to obtain the production task sequence, Among them, the production task sequence includes multiple production task information and multiple production windows. The energy consumption prediction module is used to perform energy consumption prediction based on multiple production task information to obtain an electric energy consumption sequence. The energy aggregation supply analysis module is used to collect environmental data based on multiple production windows, and energy aggregation supply analysis is performed based on the collection results and the electric energy consumption sequence to obtain an energy scheduling parameter sequence. Through the energy dynamic scheduling module, the energy aggregation scheduling center receives the energy scheduling parameter sequence, and executes multi-cycle energy dynamic scheduling for thermal power stations, photovoltaic power stations and wind power stations according to the energy scheduling parameter sequence within multiple production windows, thereby achieving the technical effect of improving scheduling flexibility and thereby improving energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A schematic diagram of the structure of a multi-data linked energy aggregation scheduling management platform provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the process of obtaining a production task sequence in the multi-data linked energy aggregation scheduling management platform provided in an embodiment of the present application.

[0025] Explanation of the accompanying drawings: power plant acquisition module 10, energy aggregation scheduling center construction module 20, production order information acquisition module 30, production task allocation module 40, energy consumption prediction module 50, energy aggregation supply analysis module 60, energy dynamic scheduling module 70. DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, platforms, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The embodiment of the present application provides a multi-data linked energy aggregation scheduling management platform, such as Figure 1 As shown, the platform includes:

[0030] The power station acquisition module 10 is used to interactively obtain the thermal power station, photovoltaic power station and wind power station used to supply energy for the target industrial zone. Specifically, after the platform is started, the power station acquisition module 10 first initializes the connection parameters, such as IP address, port number, etc., to establish communication with different types of power stations (thermal, photovoltaic, wind) in or around the target industrial zone (a place dedicated to industrial production activities), and obtains real-time power generation data, status information and historical data from each power station regularly or on demand, and stores the acquired data in a local database or cloud platform. Among them, a thermal power station is a power station that uses fossil fuels such as coal, oil or natural gas to generate electricity; a photovoltaic power station is a power station that uses solar panels to convert solar energy into electricity; a wind power station is a power station that uses wind turbines to convert wind energy into electricity.

[0031] The energy aggregation dispatching center construction module 20 is used to pre-build the energy aggregation dispatching center, and after the thermal power station, photovoltaic power station, and wind power station are connected to the energy aggregation dispatching center, the energy aggregation dispatching center is authorized to perform energy dispatching operations of the thermal power station, photovoltaic power station, and wind power station. Specifically, the energy demand of the target industrial zone is analyzed, including energy type, demand, demand time, etc., to determine the functions and performance requirements that the energy aggregation dispatching center needs to support. The energy aggregation dispatching center is a dispatching system that centrally manages multiple energy sources (such as thermal power, photovoltaic power, wind power, etc.), which is used to formulate and implement the optimal energy dispatching plan according to the energy demand of the target industrial zone and the power generation capacity of the power station. Design the overall architecture of the energy aggregation dispatching center, including hardware platforms (servers, storage devices, etc.), software platforms (operating systems, databases, middleware, etc.) and application systems (energy dispatching software), determine the interfaces and communication protocols between the components, design a database for storing power station information, production order information, production task information, energy consumption forecast data, environmental data, etc., set data table structure, index, view, etc. to optimize data query and storage efficiency. Develop interfaces with thermal power stations, photovoltaic power stations, and wind power stations (including data transmission protocols, data formats, etc.) to obtain data such as the power generation capacity and power generation status of the power station in real time; develop interfaces with the production order system and production task allocation system to obtain production order information and production task information. Develop an energy dispatching algorithm that can calculate the optimal energy dispatching plan based on multiple data sources such as production task information, energy consumption forecast data, and environmental data. Integrate the energy dispatching algorithm into the software system of the energy aggregation dispatching center and conduct system testing, including unit testing, integration testing, and system testing, to ensure that the modules can work together and the system can run stably.

[0032] Connect thermal power stations, photovoltaic power stations, and wind power stations to the energy aggregation dispatch center through interfaces, conduct access tests, and verify that the data of each power station can be correctly transmitted to the energy aggregation dispatch center, and that the energy aggregation dispatch center can correctly parse and process these data. Set user roles and permissions for the energy aggregation dispatch center to ensure that only authorized users can perform energy dispatch operations, and manage permissions for each power station to ensure that each power station can only receive and execute dispatch instructions from the energy aggregation dispatch center.

[0033] In one possible implementation, the platform also includes a water supply station acquisition module, which is used to: interactively obtain a water supply station used for production water supply to a target industrial area; after connecting the water supply station to the energy aggregation scheduling center, authorize the energy aggregation scheduling center to perform energy scheduling operations on the water supply station.

[0034] Specifically, when the platform is initialized, the water supply station acquisition module is activated. The module first determines the list of target water supply stations that need to be connected. These water supply stations are responsible for providing the target industrial zone with the water resources required for production. The water supply station acquisition module interacts with the water supply station through the network or other communication means to obtain its basic information (such as location, capacity, current operating status, etc.). After obtaining the water supply station information, the water supply station acquisition module passes this information to the energy aggregation dispatching center. The energy aggregation dispatching center configures the corresponding interface and protocol based on the received information to transmit and control data with the water supply station. After the water supply station is officially connected to the energy aggregation dispatching center, the energy aggregation dispatching center obtains the energy dispatching operation authority for the water supply station, that is, the energy aggregation dispatching center can dispatch and optimize the energy use of the water supply station according to the overall energy and resource demand. This implementation method realizes the centralized integration and optimized dispatching of multiple resources by incorporating the water supply station into the management scope of the energy aggregation dispatching center, and achieves the technical effect of improving resource utilization efficiency.

[0035] The production order information acquisition module 30 is used to interactively obtain the production order information of the target industrial zone. Specifically, according to the preset time interval or trigger condition (such as receiving a specific signal), the production order information acquisition module 30 is connected with the production order system (a software system for managing and tracking production orders, including order creation, approval, scheduling, tracking and other functions), and sends a data request to the production order system. The request contains filtering conditions such as time range, factory ID, product type, etc. to obtain production order information within a specific range. Receive response data from the production order system and perform data parsing, including verifying data integrity, parsing data formats (such as JSON, XML, etc.), and extracting key information (such as order number, product name, production quantity, delivery date, etc.).

[0036] The production task allocation module 40 is used to allocate production tasks according to the production order information and obtain a production task sequence, wherein the production task sequence includes multiple production task information and multiple production windows. Specifically, the production order information is parsed to extract key fields related to the production task allocation, such as product type, production quantity, etc. According to the production capacity of the target industrial zone (including equipment, personnel, process, etc.), it is evaluated whether all production orders can be completed on time. Each production order is decomposed into specific production tasks, and each production task corresponds to a specific execution unit, which contains clear production goals (such as production quantity, quality standards), required resources (such as equipment, raw materials, personnel) and expected completion time. According to the delivery date of the production order, the priority of the production task, the availability of production equipment and other factors, a production task sequence is formulated. The production task sequence is used to optimize resource utilization and production efficiency under the premise of meeting the delivery date. One or more production windows are allocated to each production task, and the production window refers to the time period when the production task can start to be executed. The production task sequence and the production window are integrated into a production task plan to determine the specific execution time, required resources and responsible person of each production task.

[0037] like Figure 2 As shown, in a possible implementation, the production task allocation module is used to: decompose the production order information to obtain multiple production task information; use the multiple production task information to traverse the production log of the target industrial zone to obtain multiple production resource requirements; use the multiple production task information to traverse the production log to obtain multiple historical production quantities and multiple historical production times, and calculate the multiple production windows based on the multiple historical production quantities, multiple historical production times and the multiple production task information; use the multiple production window mappings to perform identification processing on the multiple production task information; interactively obtain the production resource information of the target industrial zone, and sort the multiple production task information according to the production resource information and the multiple production resource requirements to obtain the production task sequence.

[0038] Specifically, the order data is parsed to identify key information such as product type, production quantity, and delivery date. According to the product type and production quantity, each order is decomposed into multiple specific production tasks, each of which corresponds to the production of a product or a part of the quantity. The production log database of the target industrial zone is accessed, and each production task information is used as the query condition. The production log is traversed to find the historical resource consumption records of similar production tasks, and all relevant records are summarized to calculate the quantity and type of various production resources (such as equipment, manpower, raw materials, etc.) required for each production task. The production log is traversed again to find historical production records similar to the current production task, and key data such as historical production volume and historical production time are extracted. According to the unit production task time (estimated or set by historical data) and the production volume of the current production task, the estimated production time of each task is calculated, and the production window of each production task is determined in combination with the available time of production equipment, the shift arrangement of personnel, and other factors. One or more production windows are assigned to each production task and recorded in the production task information. The production task is identified using the production window information for subsequent scheduling and monitoring. Interactively obtain real-time production resource information (such as equipment status, personnel scheduling, etc.) of the target industrial zone, evaluate the production feasibility of each production task based on production resource information and production resource demand, sort production tasks that meet resource requirements according to factors such as delivery date and production urgency, and schedule production resources (such as adjusting production plans, seeking external resources, etc.) for production tasks that do not meet resource requirements, and finally generate a production task sequence sorted by priority. This implementation method combines production order information, historical production data, and production resource status, and performs reasonable decomposition of production tasks, accurate evaluation of resource requirements, scientific calculation of production windows, and priority sorting of production tasks, achieving the technical effect of optimizing resource utilization and production efficiency.

[0039] The energy consumption prediction module 50 is used to perform energy consumption prediction based on the multiple production task information to obtain an electric energy consumption sequence. Specifically, the energy consumption prediction module 50 receives the production task sequence from the production task allocation module 40, including multiple production task information, and also collects data related to energy consumption from other data sources (such as historical energy consumption database, equipment performance database, etc.), such as historical energy consumption records, equipment efficiency curves, etc. The collected production task information is parsed to extract key parameters related to energy consumption prediction, such as production type, production quantity, production time, etc.

[0040] Clean and preprocess the historical energy consumption data to remove outliers and noise, use the historical energy consumption data to train the energy consumption prediction model (time series analysis model, machine learning model, etc.), adjust the model parameters, and enable the model to accurately predict future energy consumption. Input the processed production task information into the trained energy consumption prediction model to perform energy consumption prediction. The model calculates the estimated power consumption of each production task based on the input production task information and historical data, and sorts the estimated power consumption of all production tasks according to the time series to form a power consumption sequence.

[0041] In a possible implementation, the energy consumption prediction module 50 is also used to: interactively obtain historical production consumption data, wherein the historical production consumption data includes multiple historical task electricity consumption and multiple historical task water energy consumption of multiple historical production tasks; perform multi-dimensional energy consumption regression analysis based on the historical production consumption data, and construct an energy consumption analysis model based on the analysis results; synchronize the multiple production task information to the energy consumption analysis model to obtain the water energy consumption sequence and the electricity consumption sequence.

[0042] Specifically, a data request is sent to the production management system, energy management system, etc., requesting to obtain detailed information of historical production tasks, including the electricity consumption and water energy consumption of each task. The received data is verified to ensure the integrity and accuracy of the data, including checking the data format, missing value processing, outlier detection, etc. The historical production consumption data refers to the energy data consumed by various production tasks in the past period of time, such as electricity, water energy, etc. The key factors affecting energy consumption are extracted from the collected data as features, such as the type, scale, time, environmental conditions, etc. of the production task, and regression analysis techniques (such as linear regression, polynomial regression, ridge regression, etc.) are used to explore the relationship between energy consumption and specific features, and the regression model is trained using historical data. The model parameters are adjusted to minimize the prediction error, and the optimized model is deployed in the energy consumption prediction module 50. The new production task information (such as task type, scale, time, etc.) is input into the energy consumption analysis model, and the model calculates and outputs the corresponding water energy consumption sequence and electricity energy consumption sequence according to the input task information. This implementation method more accurately reflects the energy consumption law in the actual production process by constructing a prediction model using historical data, and achieves the technical effect of improving the accuracy of energy consumption prediction.

[0043] In a possible implementation, the energy consumption prediction module 50 is also used to: aggregate the historical production consumption data based on task type to obtain M groups of historical production tasks, M groups of historical task electricity consumption and M groups of historical task water energy consumption of M types of sample production tasks; extract output from the M groups of historical production tasks to obtain M groups of production output; perform regression analysis on the M groups of production output and the M groups of historical task electricity consumption to obtain M electricity consumption functions; perform regression analysis on the M groups of production output and the M groups of historical task water energy consumption to obtain M water energy consumption functions; complete the construction of an electricity consumption analysis branch by associating and storing the M types of sample production tasks and the M electricity consumption functions based on the knowledge graph; complete the construction of a water energy consumption analysis branch by associating and storing the M types of sample production tasks and the M water energy consumption functions based on the knowledge graph; and connect the electricity consumption analysis branch and the water energy consumption analysis branch in parallel to complete the pre-construction of the energy consumption analysis model.

[0044] Specifically, the task type is identified for the historical production consumption data, that is, the production tasks are classified according to the classification standards such as product type, production process, and production scale, and the data with the same attributes are merged together, such as dividing the production tasks into Class A, Class B, ... Class M, etc. For each task type, the corresponding historical production tasks, historical task power consumption, and historical task water consumption are respectively aggregated together to form M groups of data. The corresponding production output data (the number or value of products obtained after the production task is completed) is extracted from each group of historical production tasks, and the extracted output data is sorted according to the task type to form M groups of production output data. Regression analysis is performed on the M groups of production output and the M groups of historical task power consumption, respectively, to obtain M power consumption functions; similarly, regression analysis is performed on the M groups of production output and the M groups of historical task water consumption, to obtain M water consumption functions. According to the results of the regression analysis, the specific form of each consumption function (such as linear, polynomial, exponential, etc.) is determined, and the consumption function is a mathematical expression that describes the relationship between production output and energy consumption. Using knowledge graph technology, a graph containing the relationship between production task types, power consumption functions and water consumption functions is constructed, and each production task type is associated with its corresponding power consumption function and water consumption function in the knowledge graph for storage. Based on the association relationship in the knowledge graph, power consumption analysis branches and water consumption analysis branches are constructed respectively, and the power consumption analysis branches and water consumption analysis branches are connected in parallel to form a complete energy consumption analysis model framework. This implementation method simplifies complex production consumption data into representative samples through the aggregation of task types, establishes an accurate consumption function through regression analysis between output and energy consumption, and forms a comprehensive energy consumption analysis model by connecting power and water consumption analysis branches in parallel, which can meet the prediction needs of different types of production tasks for different energy consumption, achieving the technical effect of not only improving the accuracy and efficiency of energy consumption prediction, but also enhancing the flexibility and scalability of the model.

[0045] The energy aggregation supply analysis module 60 is used to collect environmental data based on the multiple production windows, and to perform energy aggregation supply analysis based on the collection results and the electric energy consumption sequence to obtain an energy scheduling parameter sequence. Specifically, before each production window starts or during the duration, the energy aggregation supply analysis module 60 triggers the environmental data collection process, and the collected data includes but is not limited to weather conditions (such as light intensity, wind speed, temperature, etc.), grid load conditions, and real-time operating status of each power station. Data collection is achieved through interfaces with external systems such as sensor networks, weather forecast systems, and power grid monitoring systems. The collected environmental data is cleaned and preprocessed to remove unfavorable factors such as outliers and noise to improve data quality and the accuracy of subsequent analysis, and the data is formatted so as to match and analyze with the electric energy consumption sequence and other related data. Based on the preprocessed environmental data and electric energy consumption sequence, an energy supply and demand matching analysis is performed to analyze the matching degree between the current and predicted future energy supply capabilities (such as the power generation potential of photovoltaic power stations, the wind energy utilization of wind power stations, the fuel reserves and power generation efficiency of thermal power stations, etc.) and industrial production needs. According to the results of energy supply and demand matching analysis, the energy dispatch parameters of each power station in each production window are calculated, including power generation, power generation priority, power generation time, etc., to optimize energy utilization, reduce production costs and meet production needs. The calculated energy dispatch parameters of each power station in each production window are sorted and integrated according to the time series to form an energy dispatch parameter sequence.

[0046] In a possible implementation, the energy aggregation supply analysis module 60 is further used to: sequentially extract and obtain first production task information from the production task sequence, wherein the first production task information is identified by the first production window; extract and obtain first electric energy demand and first water energy demand from the water energy consumption sequence and the electric energy consumption sequence according to the first production task information; collect environmental data with the first production window as a constraint to obtain first energy-related data, wherein the first energy-related data includes first photovoltaic-related data and first wind power-related data; perform power generation prediction according to the first energy-related data to obtain a first real-time power generation; calculate and obtain a first real-time power generation gap according to the first electric energy demand and the first real-time power generation; the first real-time power generation gap and the first water energy demand constitute a first energy scheduling parameter, wherein the energy aggregation scheduling center performs distributed energy scheduling on the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy scheduling parameter within the first production window; and so on, obtain multiple energy scheduling parameters of the multiple production windows, splice the multiple energy scheduling parameters according to the production task sequence to constitute the energy scheduling parameter sequence.

[0047] Specifically, the production task sequence is parsed, and the first production task is sequentially extracted from the production task sequence as the current processing object, and its production window identifier (i.e., the start and end time) is obtained. According to the production window identifier in the first production task information, the corresponding power demand and water demand are searched in the power consumption sequence and the water consumption sequence, and the first power demand and the first water demand are extracted from the found sequence. According to the start and end time of the first production window, the time range for environmental data collection is determined, and environmental data related to photovoltaic power generation and wind power generation, such as light intensity, wind speed, etc., are collected within the specified time range. According to the collected environmental data, the first photovoltaic-related data and the first wind power-related data are obtained, and the first photovoltaic-related data are environmental data related to photovoltaic power generation, and the first wind power-related data are environmental data related to wind power generation. Using the established power generation prediction model (a mathematical model for predicting future power generation based on historical data and environmental data), the first photovoltaic-related data and the first wind power-related data are used as input, and the model outputs the real-time power generation that can be generated by the photovoltaic power station and the wind power station within the first production window. The first power demand is compared with the first real-time power generation. If the first real-time power generation is less than the first power demand, the difference between the two is calculated as the first real-time power generation gap, that is, the first real-time power generation gap is the difference when the power generation by wind and photovoltaic power alone cannot meet the power demand. The first real-time power generation gap and the first hydropower demand are combined into the first energy dispatching parameter. The energy aggregation dispatching center performs distributed energy dispatching for thermal power stations, photovoltaic power stations, wind power stations and hydropower stations according to the first energy dispatching parameter to meet the energy demand of the production task. The same method as above is used to process each production task information to obtain multiple energy dispatching parameters, which are then spliced ​​to obtain an energy dispatching parameter sequence.

[0048] In this implementation, when a production task sequence is received, the required electric and hydropower will first be predicted based on the production task information, and then the real-time power generation of photovoltaic power stations and wind power stations will be predicted based on the current environmental conditions (such as light intensity and wind speed). If the predicted power generation can meet the power demand, there is no need to start the thermal power station; if the power generation is insufficient, the supplementary power required by the thermal power station is calculated based on the power generation gap, and the corresponding energy scheduling is carried out. This scheduling strategy ensures the priority use of wind power and photovoltaic power, and supplements them with thermal power when necessary, achieving the technical effect of achieving reliability and economy of energy supply.

[0049] In a possible implementation, the energy aggregation supply analysis module 60 is also used to: preset a standard energy consumption update node, and locate the first data update node in the first production window according to the standard energy consumption update node; sequentially extract and obtain the second production task information from the production task sequence, wherein the second production task information uses the second production window identifier; when the energy aggregation dispatching center performs distributed energy dispatching to the first data update node for the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy dispatching parameter within the first production window; collect environmental data with the second production window as a constraint to obtain second update associated data, wherein the second update associated data includes second photovoltaic update data and second wind power update data; extract and obtain the second energy associated data of the second production window from the collection result, and determine whether the second photovoltaic update data and the second wind power update data are consistent with the mapping of the second photovoltaic associated data and the second wind power associated data; if the second photovoltaic update data is inconsistent with the second photovoltaic associated data, and / or the second wind power update data is inconsistent with the second wind power associated data, then locally update the second energy dispatching parameter in the energy dispatching parameter sequence at the first data update node.

[0050] Specifically, according to the cycle of the production task, the volatility of energy supply and the frequency of changes in environmental factors, the standard energy consumption update node is preset, and the standard energy consumption update node is set before the key stage of the production task, such as a certain time before the beginning, middle or end of each production cycle. The standard energy consumption update node is a time point for triggering the update of energy consumption data and the adjustment of energy scheduling parameters. According to the current production task sequence and the preset standard energy consumption update node, the first data update node is located within the first production window (i.e., the time range of the currently executed production task), that is, the specific time point at which the energy consumption data needs to be updated. The information of the next production task (the second production task information, i.e., the details of the production task immediately following the current production task) is sequentially extracted from the production task sequence. This information includes the start and end time of the production task, and is identified using the second production window. In the first production window, according to the first energy scheduling parameter, the energy aggregation scheduling center performs energy scheduling for thermal power stations, photovoltaic power stations, wind power stations and hydropower stations until the first data update node is reached. With the second production window as the time constraint, environmental data (such as light intensity, wind speed, etc.) are collected. These data will directly affect the power generation of photovoltaic power generation and wind power generation. According to the collection results, the second photovoltaic update data and the second wind power update data are generated. The second updated associated data are environmental parameters related to the prediction of photovoltaic and wind power generation based on the newly collected data. The newly obtained second photovoltaic update data and the second wind power update data are compared with the previous second photovoltaic associated data and the second wind power associated data. If inconsistencies are found (i.e., changes in environmental conditions lead to changes in power generation forecasts), the second energy scheduling parameters are locally adjusted at the first data update node to adapt to the new energy production capacity. This implementation method ensures that the actual situation of energy production is accurately reflected by presetting standard energy consumption update nodes, regularly evaluating and adjusting energy scheduling strategies, and achieving the technical effect of ensuring the reliability of power supply.

[0051] In a possible implementation, the energy aggregation supply analysis module 60 is also used to: extract and obtain multiple real-time power generation gaps based on the multiple energy scheduling parameters; synchronize the multiple real-time power generation gaps to a pre-built fuel demand analysis model to reverse the fuel demand and obtain multiple real-time fuel demand amounts; add the multiple real-time fuel demand amounts to obtain a fuel usage benchmark; interact with the thermal power station to obtain real-time fuel storage; and obtain fuel scheduling instructions based on the real-time fuel storage and fuel usage benchmark analysis.

[0052] Specifically, the multiple real-time power generation gaps refer to the difference caused by the inability of wind power stations and photovoltaic power stations to meet the corresponding production task requirements in each production window. The real-time power generation gap is input into the pre-built fuel demand analysis model. This model is based on the power generation efficiency, fuel consumption rate and other parameters of the thermal power station, and calculates the amount of fuel required to make up for the power generation gap by reverse calculation. The real-time fuel demand corresponding to these power generation gaps is added to obtain a total fuel usage benchmark, which represents the minimum amount of fuel that the thermal power station needs to prepare in order to meet the current and near-term production task requirements. Interact with the thermal power station through a communication mechanism (such as API call, message queue, etc.) to obtain its current real-time fuel storage, which reflects the fuel resources currently available to the thermal power station. Compare the real-time fuel storage and the fuel usage benchmark. If the storage is lower than the benchmark, a fuel scheduling instruction is generated to instruct the thermal power station to purchase, allocate or replenish fuel. This implementation method provides accurate fuel usage forecasts for thermal power plants by calculating the power generation gap in real time and reversely calculating the fuel demand, thus avoiding the occurrence of fuel shortages and achieving the technical effect of ensuring the continuity and stability of industrial production.

[0053] Energy dynamic scheduling module 70, the energy dynamic scheduling module 70 is used for the energy aggregation scheduling center to receive the energy scheduling parameter sequence, and perform multi-cycle energy dynamic scheduling on the thermal power station, photovoltaic power station and wind power station according to the energy scheduling parameter sequence within the multiple production windows. Specifically, the energy aggregation scheduling center parses the received energy scheduling parameter sequence, understands the specific meaning of each parameter and the corresponding power station, and generates specific scheduling instructions for each power station within the production window according to the parsed scheduling parameters, including starting / stopping power generation, adjusting power generation, optimizing power generation time, etc. The generated scheduling instructions are sent to the corresponding power station through the interface with the power station control system. During the execution of the scheduling instructions, the energy dynamic scheduling module 70 continuously monitors the operating status and energy supply of each power station, such as actual power generation, equipment status, etc. If abnormal conditions or deviations are found, timely adjustments or alarms are issued. The embodiment of the present application realizes the coordinated optimization and dynamic scheduling of multiple energy sources such as thermal power generation, photovoltaic power generation and wind power generation by integrating multiple modules such as power station acquisition, energy aggregation scheduling center construction, production order information acquisition, production task allocation, energy consumption forecasting, energy aggregation supply analysis and energy dynamic scheduling, thereby achieving the technical effect of improving scheduling flexibility and further improving energy utilization efficiency.

[0054] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0055] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The multi-data-linked energy aggregation dispatching management platform is characterized by: The platform includes: A power station acquisition module, the power station acquisition module is used to interactively obtain a thermal power station, a photovoltaic power station and a wind power station for supplying energy to a target industrial zone; An energy aggregation dispatch center construction module, which is used to pre-construct an energy aggregation dispatch center and, after the thermal power station, photovoltaic power station, and wind power station are connected to the energy aggregation dispatch center, authorize the energy aggregation dispatch center to perform energy dispatch operations of the thermal power station, photovoltaic power station, and wind power station; A production order information acquisition module, wherein the production order information acquisition module is used to interactively obtain production order information of a target industrial zone; A production task allocation module, the production task allocation module is used to allocate production tasks according to the production order information to obtain a production task sequence, wherein the production task sequence includes a plurality of production task information and a plurality of production windows; An energy consumption prediction module, the energy consumption prediction module is used to perform energy consumption prediction based on the multiple production task information to obtain an electric energy consumption sequence; An energy aggregation supply analysis module, the energy aggregation supply analysis module is used to collect environmental data based on the multiple production windows, and perform energy aggregation supply analysis based on the collection results and the electric energy consumption sequence to obtain an energy scheduling parameter sequence; An energy dynamic scheduling module, wherein the energy dynamic scheduling module is used for the energy aggregation scheduling center to receive the energy scheduling parameter sequence and perform multi-period energy dynamic scheduling on the thermal power station, photovoltaic power station and wind power station according to the energy scheduling parameter sequence within the multiple production windows; The production task allocation module is used for: Decomposing the production order information to obtain a plurality of production task information; Using the multiple production task information to traverse the production log of the target industrial zone, obtaining multiple production resource requirements; Using the multiple production task information to traverse the production log, obtain multiple historical production quantities and multiple historical production times, and calculate and obtain the multiple production windows based on the multiple historical production quantities, multiple historical production times and the multiple production task information; Using the multiple production window mappings to perform identification processing on the multiple production task information; Interactively obtain the production resource information of the target industrial zone, and perform production priority sorting on the multiple production task information according to the production resource information and the multiple production resource requirements to obtain the production task sequence; A water supply station acquisition module, wherein the water supply station acquisition module is used to: Interactively obtain water supply stations for production water supply to target industrial areas; After the water supply station is connected to the energy aggregation dispatching center, the energy aggregation dispatching center is authorized to perform energy dispatching operations of the water supply station.

2. The multi-data-linked energy aggregation scheduling management platform according to claim 1, characterized in that: The energy consumption prediction module is also used for: Interactively obtain historical production consumption data, wherein the historical production consumption data includes multiple historical task electricity consumption and multiple historical task water consumption of multiple historical production tasks; Performing a multi-dimensional energy consumption regression analysis based on the historical production and consumption data, and constructing an energy consumption analysis model based on the analysis results; The multiple production task information is synchronized to the energy consumption analysis model to obtain the water energy consumption sequence and the electric energy consumption sequence.

3. The multi-data-linked energy aggregation scheduling management platform according to claim 2 is characterized in that: The energy consumption prediction module is also used for: Aggregate the historical production and consumption data based on task types to obtain M groups of historical production tasks, M groups of historical task electricity consumption, and M groups of historical task water energy consumption of M types of sample production tasks; Extracting the output of the M groups of historical production tasks to obtain the production output of the M groups; Performing regression analysis on the M groups of production outputs and the M groups of historical task power consumption to obtain M power consumption functions; Performing regression analysis on the M groups of production outputs and the M groups of historical task water energy consumption to obtain M water energy consumption functions; The M sample production tasks and the M power consumption functions are stored in association with the knowledge graph to complete the construction of the power consumption analysis branch; The M sample production tasks and the M water energy consumption functions are stored in association with the knowledge graph to complete the construction of the water energy consumption analysis branch; The electric energy consumption analysis branch and the water energy consumption analysis branch are connected in parallel to complete the pre-construction of the energy consumption analysis model.

4. The multi-data-linked energy aggregation scheduling management platform according to claim 2, characterized in that: The energy aggregation supply analysis module is also used to: Sequentially extracting and obtaining first production task information from the production task sequence, wherein the first production task information is identified by a first production window; Extracting a first electric energy demand and a first water energy demand from the water energy consumption sequence and the electric energy consumption sequence according to the first production task information; Collecting environmental data with the first production window as a constraint to obtain first energy-related data, wherein the first energy-related data includes first photovoltaic-related data and first wind power-related data; Perform power generation prediction based on the first energy-related data to obtain a first real-time power generation; Calculate a first real-time power generation gap according to the first electric energy demand and the first real-time power generation; The first real-time power generation gap and the first water energy demand constitute a first energy dispatch parameter, wherein the energy aggregation dispatch center performs distributed energy dispatch on the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy dispatch parameter within the first production window; By analogy, a plurality of energy scheduling parameters of the plurality of production windows are obtained, and the plurality of energy scheduling parameters are spliced ​​together according to the production task sequence to form the energy scheduling parameter sequence.

5. The multi-data-linked energy aggregation scheduling management platform according to claim 4 is characterized in that: The energy aggregation supply analysis module is also used to: Presetting a standard energy consumption update node, and locating a first data update node in the first production window according to the standard energy consumption update node; Sequentially extracting and obtaining second production task information from the production task sequence, wherein the second production task information is identified by a second production window; When the energy aggregation dispatching center performs distributed energy dispatching to the first data update node for the thermal power station, photovoltaic power station, wind power station and hydropower station according to the first energy dispatching parameter within the first production window; Collecting environmental data with the second production window as a constraint to obtain second updated associated data, wherein the second updated associated data includes second photovoltaic updated data and second wind power updated data; Extracting the second energy-related data of the second production window from the collection results, and determining whether the second photovoltaic update data and the second wind power update data are consistent with the mapping of the second photovoltaic-related data and the second wind power-related data; If the second photovoltaic update data is inconsistent with the second photovoltaic associated data, and / or the second wind power update data is inconsistent with the second wind power associated data, the second energy scheduling parameter in the energy scheduling parameter sequence is locally updated at the first data update node.

6. The multi-data-linked energy aggregation scheduling management platform according to claim 4, characterized in that: The energy aggregation supply analysis module is also used to: Extract and obtain multiple real-time power generation gaps based on the multiple energy scheduling parameters; Synchronizing the multiple real-time power generation gaps to a pre-built fuel demand analysis model to reversely calculate the fuel demand to obtain multiple real-time fuel demand amounts; Adding the multiple real-time fuel requirements to obtain a fuel usage benchmark; Interacting with the thermal power station to obtain real-time fuel storage; Fuel scheduling instructions are obtained based on the real-time fuel storage and fuel usage benchmark analysis.

Images