A distributed energy pipeline natural gas demand management method, system and medium

Abstract

The present invention relates to the field of natural gas management technology, and in particular provides a distributed energy pipeline natural gas demand management method, system and medium, the method comprising: determining a commercial change sequence; determining a civil change sequence; determining a demand sequence based on the civil change sequence, the commercial change sequence and historical usage data; constructing a micro-pipeline network map; determining a gas storage coverage rate and a gas supply priority; determining a gas storage adjustment parameter based on the gas storage coverage rate and the gas supply priority; and generating a gas storage adjustment instruction based on the gas storage adjustment parameter. The system comprises a distributed energy perception control platform, a distributed energy sensor network platform, a distributed energy demand management platform, a distributed energy service platform and a distributed energy user platform. The method can be run after being read by a computer instruction stored in a computer-readable storage medium. The method can ensure the normal supply of gas in the gas supply area without affecting the normal production and life of gas users.

Description

Technical Field

[0001] The present invention relates to the field of natural gas management technology, and in particular to a method, system and medium for managing natural gas demand in a distributed energy pipeline. Background Art

[0002] In some remote areas (such as towns) that have not yet been covered by natural gas pipelines, gas is usually supplied through gas micro-pipelines. Gas can be connected by building natural gas facilities such as low-pressure pipelines in the village, which reduces the gas connection costs of rural users and is also of great significance to improving the rural living environment. Therefore, it is necessary to keep abreast of changes in gas demand in various regions and deliver sufficient gas to storage tanks in a timely manner.

[0003] Therefore, it is desirable to provide a distributed energy pipeline natural gas demand management method, system and medium that can determine the gas demand of each area and adjust the gas storage capacity of each area based on the gas demand. Summary of the invention

[0004] The invention content includes a distributed energy pipeline natural gas demand management method, which is executed by a distributed energy demand management platform of a distributed energy pipeline natural gas demand management Internet of Things system, and the method includes: based on the production parameter sequence and commercial impact sequence of a factory in at least one gas supply area in a preset future time period, determining the commercial change sequence of the at least one gas supply area in the preset future time period; obtaining the gas flow data of the low-pressure transportation network of the at least one gas supply area through the distributed energy sensor network platform through the distributed energy perception control platform; obtaining the historical usage data of the at least one gas supply area based on the gas flow data; determining the commercial change sequence of the at least one gas supply area in the preset future time period based on the historical gas cost, the historical usage data, season information and the gas cost sequence of the at least one gas supply area in the preset future time period. Determine the civil change sequence of at least one gas supply area within the preset future time period; determine the demand sequence of at least one gas supply area within the preset future time period based on the civil change sequence, the commercial change sequence and the historical usage data; construct a micro-pipeline network map of at least one gas supply area based on the low-pressure transportation network of the at least one gas supply area, the current gas storage capacity of the gas station, the demand sequence and the storage scale of the gas station; determine the gas storage coverage rate and gas supply priority of at least one node based on the micro-pipeline network map; determine gas storage regulation parameters based on the gas storage coverage rate and the gas supply priority, the gas storage regulation parameters including the gas supply capacity, gas supply location and gas supply time point of the gas station; generate gas storage regulation instructions based on the gas storage regulation parameters.

[0005] The invention content includes a distributed energy pipeline natural gas demand management Internet of Things system, the system includes a distributed energy perception control platform, a distributed energy sensor network platform, a distributed energy demand management platform, a distributed energy service platform and a distributed energy user platform connected in sequence, the distributed energy demand management platform is configured to: determine the commercial change sequence of at least one gas supply area in a preset future time period based on the production parameter sequence and commercial impact sequence of the factory in at least one gas supply area in the preset future time period; obtain the gas flow data of the low-pressure transportation network of the at least one gas supply area through the distributed energy sensor network platform through the distributed energy perception control platform; obtain the historical usage data of the at least one gas supply area based on the gas flow data; obtain the historical gas cost, the historical usage data, the season information and the at least one gas supply area based on the historical gas cost, the historical usage data, the season information and the at least one gas supply area Based on the gas cost sequence of each gas supply area in the preset future time period, determine the civil change sequence of at least one gas supply area in the preset future time period; based on the civil change sequence, the commercial change sequence and the historical usage data, determine the demand sequence of at least one gas supply area in the preset future time period; based on the low-pressure transportation network of at least one gas supply area, the current gas storage capacity of the gas station, the demand sequence and the storage scale of the gas station, construct a micro-pipeline network map of the at least one gas supply area; based on the micro-pipeline network map, determine the gas storage coverage rate and gas supply priority of at least one node; based on the gas storage coverage rate and the gas supply priority, determine the gas storage regulation parameters, the gas storage regulation parameters include the gas supply capacity, gas supply location and gas supply time point of the gas station; based on the gas storage regulation parameters, generate gas storage regulation instructions.

[0006] The invention content includes a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the distributed energy pipeline natural gas demand management method.

[0007] Beneficial effects: Based on the influencing factors of gas use and historical usage data, the gas demand in the preset future period is estimated, and the obtained gas demand is closer to the actual situation. The gas storage coverage rate and gas supply priority of each gas supply area are determined based on the micro-pipeline network map, and the gas storage adjustment parameters are determined based on the gas storage coverage rate and gas supply priority, which can ensure the normal supply of gas in the gas supply area without affecting the normal production and life of gas users. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a platform structure diagram of a distributed energy pipeline natural gas demand management Internet of Things system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for managing natural gas demand in a distributed energy pipeline according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart for adjusting a commercial change sequence and a civil change sequence according to some embodiments of the present specification;

[0012] Figure 4 It is an exemplary schematic diagram of a scheduling model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0016] Figure 1 It is a platform structure diagram of the distributed energy pipeline natural gas demand management Internet of Things system shown in some embodiments of this specification.

[0017] like Figure 1 As shown, the distributed energy pipeline natural gas demand management Internet of Things system (hereinafter referred to as system 100) includes a distributed energy perception control platform 110, a distributed energy sensor network platform 120, a distributed energy demand management platform 130, a distributed energy service platform 140 and a distributed energy user platform 150 which are connected in sequence.

[0018] The distributed energy perception control platform 110 is a functional platform for generating perception information of the low-pressure transportation network and executing control information. In some embodiments, the distributed energy perception control platform 110 includes an intelligent terminal sensing control system. The intelligent terminal sensing control system refers to a system for obtaining gas flow data of the low-pressure transportation network of each gas supply area. The distributed energy perception control platform 110 is configured to obtain gas flow data of the low-pressure transportation network of at least one gas supply area based on the intelligent terminal sensing control system. The distributed energy perception control platform 110 can interact with the distributed energy sensor network platform 120 for data. For example, the distributed energy perception control platform 110 can upload the obtained gas flow data to the distributed energy sensor network platform 120.

[0019] The distributed energy sensor network platform 120 is a functional platform for managing sensor communication. In some embodiments, the distributed energy sensor network platform 120 includes a distributed energy sensor network system. The distributed energy sensor network system is a system for controlling sensors to obtain sensor data. The distributed energy sensor network platform 120 is configured to obtain gas flow data based on the distributed energy sensor network system. The distributed energy sensor network platform 120 can interact with the distributed energy demand management platform 130. For example, the distributed energy sensor network platform 120 can transmit gas flow data to the distributed energy demand management platform 130.

[0020] The distributed energy demand management platform 130 is a platform that coordinates and coordinates the connection and collaboration between the functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system. In some embodiments, the distributed energy demand management platform 130 includes a distributed energy demand comprehensive management system. The distributed energy demand comprehensive management system refers to a system that manages the gas demand of each gas supply area. The distributed energy demand management platform 130 is configured to execute a distributed energy pipeline natural gas demand management method. The distributed energy demand management platform 130 is configured to perform energy demand big data analysis based on the energy demand database in the distributed energy demand comprehensive management system. The energy demand database refers to a database containing the gas demand of each gas supply area. Energy demand big data analysis refers to big data analysis of the gas demand of each gas supply area based on historical data.

[0021] The distributed energy service platform 140 is a platform for communicating user needs and control information. In some embodiments, the distributed energy service platform 140 can interact with the distributed energy user platform 150. For example, the distributed energy service platform 140 can receive the production plan uploaded by the distributed energy user platform 150.

[0022] The distributed energy user platform 150 is a platform for interacting with users. In some embodiments, the distributed energy user platform 150 may include a terminal and a server.

[0023] In some embodiments, the system 100 may further include a processor. The above-mentioned platforms may be arranged on the processor and connected via network communication. The processor may process information and / or data related to the system 100 to perform one or more functions described in the present application. The processor may process data and / or information obtained from the above-mentioned platforms.

[0024] In some embodiments, the processor may be a computer, a user console, a single processor, a processor group, etc. The processor group may be centralized or distributed. The processor is implemented on a cloud platform.

[0025] For detailed description of the above, please refer to Figures 2 to 4 Related description.

[0026] Based on the distributed energy pipeline natural gas demand management Internet of Things system, an information operation closed loop can be formed between various functional platforms, coordinated and regular operation can be carried out, and the informatization and intelligence of smart gas pipeline network transformation can be realized. It is conducive to the construction of village and town micro-pipeline networks and can realize the platform management of natural gas distributed energy.

[0027] Figure 2 is an exemplary flow chart of a method for managing natural gas demand in a distributed energy pipeline according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps: The process 200 is executed by the distributed energy demand management platform 130 of the system 100 .

[0028] Step 210, determining a commercial change sequence of at least one gas supply area within a preset future period based on a production parameter sequence and a commercial impact sequence of a factory in at least one gas supply area within a preset future period.

[0029] The gas supply area refers to the area where gas is supplied to users. In some embodiments, at least one gas supply area is one or more towns within a preset range. For example, each gas supply area corresponds to one of the towns.

[0030] The gas station is used to receive and store gas from upstream and supply gas to the gas supply area. The preset range can be determined based on administrative divisions.

[0031] The preset future time period refers to a period of time after the current time. For example, the preset future time period is one hour or one day after the current time.

[0032] In some embodiments, the distributed energy demand management platform divides the preset future period into multiple small time periods. For example, when the preset future period is one hour after the current moment, each small time period may be ten minutes.

[0033] The production parameter sequence refers to a sequence of production parameters of a factory. For example, the production parameter sequence includes production parameters of the factory corresponding to multiple small time periods. Each production parameter includes the production scale of the factory, etc.

[0034] The production scale refers to the total number of products produced by at least one factory in a small time period. In some embodiments, the staff of at least one factory uploads the production plan through the distributed energy user platform, and the distributed energy demand management platform can interact with the distributed energy user platform through the distributed energy service platform to obtain the production plan, and determine the production scale of the factory based on the production plan.

[0035] The commercial impact sequence refers to a sequence composed of commercial gas impact factors. For example, the commercial impact sequence includes commercial gas impact factors corresponding to multiple small time periods. Each commercial gas impact factor can be represented by the sales volume of the products produced by the factory in the corresponding small time period.

[0036] In some embodiments, factory staff count the sales volume of products in each same small time period in historical data, obtain a commercial impact sequence, and upload it to the distributed energy user platform.

[0037] The commercial gas change sequence refers to a sequence composed of commercial gas change coefficients. For example, the commercial gas change sequence includes commercial gas change coefficients corresponding to multiple small time periods. Each commercial gas change coefficient reflects the commercial gas usage rate in the corresponding small time period.

[0038] In some embodiments, the distributed energy demand management platform can determine the commercial gas change coefficient corresponding to each small time period based on the production parameters and commercial gas influencing factors corresponding to each small time period by querying the first preset table, and then obtain the commercial change sequence.

[0039] The first preset table includes the correspondence between production parameters, commercial gas influencing factors and commercial gas variation coefficients. The distributed energy demand management platform can calculate the average commercial gas usage rate corresponding to a certain production parameter and commercial gas influencing factor in historical data, and determine the average commercial gas usage rate as the commercial gas variation coefficient corresponding to the production parameter and commercial gas influencing factor.

[0040] Step 220, obtaining gas flow data of a low-pressure transportation network of at least one gas supply area via a distributed energy sensor network platform through a distributed energy perception control platform.

[0041] The low-pressure transportation network refers to a transportation network composed of low-pressure gas pipelines. For example, the low-pressure transportation network includes the transportation path of the gas in the gas supply area and the corresponding gas flow data. The pressure corresponding to the low-pressure transportation network can be between 0.1MPa and 0.3MPa. The pressure corresponding to the low-pressure transportation network can also be preset according to actual needs.

[0042] Gas flow data refers to the gas flow through low-pressure gas pipelines. Gas flow data includes commercial gas flow data and residential gas flow data. Commercial gas flow data refers to the gas flow through low-pressure gas pipelines leading to factories. Residential gas flow data refers to the gas flow through low-pressure gas pipelines leading to residential areas.

[0043] In some embodiments, the distributed energy sensing control platform measures gas flow data through a gas flow meter installed on a low-pressure gas pipeline, and uploads the gas flow data to the distributed energy demand management platform.

[0044] Step 230: Based on the gas flow data, obtain historical usage data of at least one gas supply area.

[0045] Historical usage data refers to the amount of gas used in a small time period before the current time. Historical usage data includes historical civil data and historical commercial data.

[0046] In some embodiments, the distributed energy demand management platform calculates the change in commercial gas flow data in a small time period before the current moment to obtain historical commercial data, and calculates the change in civil gas flow data in a small time period before the current moment to obtain historical civil data.

[0047] Step 240, determining a civil change sequence of at least one gas supply area in a preset future time period based on historical gas costs, historical usage data, season information and a gas cost sequence of at least one gas supply area in a preset future time period.

[0048] Season information refers to the seasons related to agricultural production, for example, the season information is the twenty-four solar terms, etc.

[0049] In some embodiments, the distributed energy demand management platform determines season information based on the current time.

[0050] The gas cost series refers to the series of costs of residents using gas. For example, the gas cost series includes the costs of residents using gas corresponding to multiple small time periods.

[0051] In some embodiments, the distributed energy demand management platform may obtain a gas cost series based on government-issued notifications and / or policies.

[0052] Historical gas cost refers to the cost of gas used by residents in a small period of time before the current moment.

[0053] The civil change sequence refers to a sequence composed of multiple civil gas change coefficients. For example, the civil change sequence includes civil gas change coefficients corresponding to multiple small time periods. Each civil gas change coefficient is the ratio of the civil gas usage in the corresponding small time period to the civil gas usage in the previous small time period.

[0054] In some embodiments, the distributed energy demand management platform determines the civil gas change coefficient corresponding to the next small time period by querying a second preset table based on the gas cost of the previous small time period, the gas cost of the next small time period and the season information.

[0055] The second preset table includes the gas cost of the previous small time period, the gas cost of the next small time period, and the corresponding relationship between the season information and the civil gas change coefficient corresponding to the next small time period. The distributed energy demand management platform can obtain the civil gas usage and gas cost of the small time period before a certain historical moment, the civil gas usage and gas cost of the small time period after the historical moment, and the season information in the historical data, calculate the ratio of the civil gas usage of the two small time periods before and after the historical moment, and construct the second preset table based on the ratio.

[0056] In some embodiments, the distributed energy demand management platform can calculate the commercial gas demand corresponding to each small time period based on the commercial change sequence. For example, the distributed energy demand management platform determines the commercial gas demand of a small time period as the product of the commercial gas change coefficient of a small time period and the length of the small time period.

[0057] In some embodiments, the distributed energy demand management platform iteratively determines the civil change sequence of each gas supply area in the preset future time period based on historical gas costs, historical usage data, season information, and the gas cost sequence of each gas supply area in the preset future time period. For example, the distributed energy demand management platform can obtain the civil gas change coefficient corresponding to the first small time period by querying the second preset table based on the historical gas cost, season information, and the gas cost corresponding to the first small time period, and determine the civil gas demand corresponding to the first small time period by the product of the civil gas change coefficient corresponding to the first small time period and the historical civil data; based on the gas cost corresponding to the first small time period, season information, and the gas cost corresponding to the second small time period, obtain the civil gas change coefficient corresponding to the second small time period by querying the second preset table, and determine the civil gas demand corresponding to the second small time period by the product of the civil gas change coefficient corresponding to the second small time period and the civil gas demand corresponding to the first small time period; ... and so on, to obtain the civil change sequence of each gas supply area in the preset future time period.

[0058] Step 250, based on the civil change sequence, the commercial change sequence and the historical usage data, determine the demand sequence of at least one gas supply area in a preset future time period.

[0059] The demand sequence refers to the sequence of gas demand required by users in each small time period in the gas supply area within the preset future period. Gas demand includes residential gas demand and commercial gas demand.

[0060] In some embodiments, the distributed energy demand management platform sums the commercial gas demand and the domestic gas demand in each small time period determined in step 240 to obtain the gas demand in each small time period, and then obtains the demand sequence of each gas supply area in a preset future time period.

[0061] In some embodiments, the distributed energy demand management platform can iteratively calculate the demand sequence based on the civil change sequence, the commercial change sequence and the historical usage data. For example, the distributed energy demand management platform can calculate the product of the historical civil data and the first civil change coefficient in the civil change sequence to obtain the civil gas demand corresponding to the first small time period, calculate the product of the historical commercial data and the first commercial change coefficient in the commercial change sequence to obtain the commercial gas demand corresponding to the first small time period, and determine the sum of the civil gas demand corresponding to the first small time period and the commercial gas demand as the gas demand corresponding to the first small time period. The distributed energy demand management platform calculates the product of the civil gas demand corresponding to the first small time period and the second civil change coefficient in the civil change sequence to obtain the civil gas demand corresponding to the second small time period, calculates the product of the commercial gas demand corresponding to the first small time period and the second commercial change coefficient in the commercial change sequence to obtain the commercial gas demand corresponding to the second small time period, and determines the sum of the civil gas demand corresponding to the second small time period and the commercial gas demand as the gas demand corresponding to the second small time period, and so on, iteratively obtains the demand sequence.

[0062] In some embodiments, the distributed energy demand management platform adjusts the commercial change sequence and the civil change sequence. For more information on how to adjust the commercial change sequence and the civil change sequence, see Figure 3 Related instructions.

[0063] Step 260, constructing a micro-pipeline network map of at least one gas supply area based on the low-pressure transportation network of at least one gas supply area, the current gas storage capacity of the gas station, the demand sequence and the storage scale of the gas station.

[0064] The current gas storage capacity refers to the total amount of gas currently stored in the gas station.

[0065] In some embodiments, the distributed energy perception control platform measures the gas flow rate of the gas station input and output by installing gas flow meters at the gas station's air inlet and outlet, calculates the current gas storage capacity of the gas station, and uploads the current gas storage capacity to the distributed energy demand management platform. The distributed energy perception control platform can also measure the pressure of the gas station through a pressure gauge installed on the gas station, and calculate the current gas storage capacity of the gas station based on the pressure and volume of the gas station.

[0066] The storage capacity of a gas station refers to the maximum amount of gas that the gas station can store.

[0067] In some embodiments, the distributed energy demand management platform can obtain the storage scale of the gas station based on the product parameters of the gas station.

[0068] The micro-pipeline network map is a map used to reflect the gas supply situation of at least one gas supply area. The micro-pipeline network map includes relevant data of at least one gas supply area and the association relationship between at least one gas supply area.

[0069] In some embodiments, Figure 4 As shown, the micro-pipeline network map 411 includes multiple nodes 411-1, each of which corresponds to a gas supply area. Each node also has corresponding node characteristics, which include the low-pressure transportation network of the gas supply area corresponding to the node, the current gas storage capacity of the gas station in the gas supply area, the storage scale of the gas station, and the demand sequence of the gas supply area in a preset future period.

[0070] For example, node 1 in the micro-pipeline network map corresponds to gas supply area A, and the node characteristics of node 1 are the low-pressure transportation network of gas supply area A, the current gas storage capacity of the gas station in gas supply area A, the storage scale of the gas station and the demand sequence of gas supply area A in the preset future time period, etc.

[0071] In some embodiments, the micro-pipeline network graph also includes multiple edges 411-2 connecting nodes, each edge corresponding to a tanker transport path between two gas supply areas. Each edge also has a corresponding edge feature, which is the path distance and path flatness corresponding to the tanker transport path.

[0072] For example, node 1 and node 2 are connected by an edge, node 1 corresponds to gas supply area A, and node 2 corresponds to gas supply area B. Then the edge between node 1 and node 2 is the tank truck transportation path between gas supply area A and gas supply area B, and the corresponding edge features are the path distance and path flatness corresponding to the tank truck transportation path between gas supply area A and gas supply area B.

[0073] The gas transportation between different gas supply areas is carried out by transporting gas storage tanks by tank trucks, and the distributed energy demand management platform can determine the tank truck transportation route based on the transportation network. The transportation network refers to the transportation network between various gas supply areas. In some embodiments, the distributed energy demand management platform determines the transportation network based on a map.

[0074] Path roughness refers to the smoothness of the tank truck transportation path. Path roughness can reflect the convenience of tank truck transportation. Path roughness is expressed by the International Roughness Index (IRI).

[0075] In some embodiments, after the tank truck transportation is completed, the transportation personnel update the path flatness of the tank truck transportation path in real time based on the actual transportation conditions.

[0076] In some embodiments, the distributed energy demand management platform updates the data in the micro-pipeline network map according to the update frequency. The update frequency can be a system preset value. The distributed energy demand management platform can update the micro-pipeline network map once every preset future time period. The update frequency is inversely proportional to the length of the preset future time period.

[0077] In some embodiments, the distributed energy demand management platform adjusts the update frequency of the micro-pipeline network map based on the fluctuation range of the gas demand in the micro-pipeline network map.

[0078] The fluctuation amplitude can be expressed in a variety of ways, for example, the fluctuation amplitude is expressed by the variance or standard deviation of the demand sequence. In some embodiments, the distributed energy demand management platform calculates the variance or standard deviation of the gas demand in each small time period in the preset future period for the gas supply area corresponding to each node in the micro-pipeline network map, and determines the variance or standard deviation as the fluctuation amplitude corresponding to the node, and determines the average value of the fluctuation amplitudes of all nodes as the fluctuation amplitude of the gas demand in the micro-pipeline network map.

[0079] In some embodiments, the update frequency of the micro-pipeline network map is positively correlated with the fluctuation amplitude. When the fluctuation amplitude is large, the update frequency of the micro-pipeline network map is high, and the length of the preset future period is reduced. When the fluctuation amplitude is small, the update frequency of the micro-pipeline network map is low, and the length of the preset future period is increased.

[0080] In some embodiments, the distributed energy demand management platform reduces the update frequency of the micro-pipeline network map in response to the fluctuation amplitude of the gas demand in the micro-pipeline network map being less than the second preset threshold, and increases the update frequency of the micro-pipeline network map in response to the fluctuation amplitude of the gas demand in the micro-pipeline network map being not less than the second preset threshold. The second preset threshold can be set based on experience.

[0081] In some embodiments, the second preset threshold is related to the gas usage period. When the gas usage period is a gas usage peak period, the second preset threshold is lower, otherwise, the second preset threshold is higher.

[0082] During the peak gas consumption period, the gas usage is large and the corresponding fluctuation range is also large. At this time, increasing the update frequency of the micro-pipeline network map can timely predict the latest gas demand.

[0083] In some embodiments of the present specification, when the fluctuation range of gas demand is small, it means that the change of gas usage is not large at this time. At this time, the updating frequency of the micro-pipeline network map is reduced to save computing resources.

[0084] Step 270, based on the micro-pipeline network map, determine the gas storage coverage rate and gas supply priority of at least one node.

[0085] The gas storage coverage rate refers to the ratio of the current gas storage capacity to the gas demand. In some embodiments, the gas storage coverage rate is positively correlated with the current gas storage capacity and negatively correlated with the gas demand. The distributed energy demand management platform can calculate the duration for which the gas currently stored in the gas supply area corresponding to a node can meet the gas demand based on the current gas storage capacity and gas demand of the gas supply area corresponding to the node, and determine the ratio of the duration to the preset future time period as the gas storage coverage rate of the node.

[0086] Gas supply priority refers to the priority of delivering gas to each node.

[0087] In some embodiments, the gas supply priority of a node is positively correlated with the total gas demand of the gas supply area corresponding to the node in a preset future period, and negatively correlated with the gas storage coverage rate of the node. The distributed energy demand management platform can calculate the gas supply priority corresponding to the node based on the total gas demand of the gas supply area corresponding to the node in a preset future period and the gas storage coverage rate of the node. The coefficients corresponding to the gas demand and the gas storage coverage rate can be preset based on experience.

[0088] Step 280, determining gas storage adjustment parameters based on the gas storage coverage rate and the gas supply priority.

[0089] Gas storage adjustment parameters refer to parameters related to gas transportation. In some embodiments, the gas storage adjustment parameters include the gas supply volume, gas supply location, and gas supply time of the gas station.

[0090] In some embodiments, gas storage regulation can be achieved only through gas supply from gas stations. For example, in response to the number of nodes with a gas storage coverage rate less than 100% being greater than a first preset threshold, the distributed energy demand management platform determines the corresponding gas supply based on the gas storage amount of each node with a gas storage coverage rate less than 100% and the gas demand in a preset future period, and delivers gas from the gas station to the node with a gas storage coverage rate less than 100% according to the gas supply priority. The first preset threshold can be set based on historical experience.

[0091] In some embodiments, gas storage regulation can be achieved through internal regulation of the gas station. For example, in response to the number of nodes with a gas storage coverage rate less than 100% being not greater than a first preset threshold, the distributed energy demand management platform transports gas to nodes with a gas storage coverage rate less than 100% through nodes with a gas storage coverage rate greater than 100% and gas stations. Exemplarily, the distributed energy demand management platform can determine the gas storage regulation parameters corresponding to each node in turn based on the gas supply priority of the node. For example, the distributed energy demand management platform generates multiple gas storage regulation strategies through a dynamic programming algorithm, determines the gas transportation cost corresponding to the gas storage regulation strategy based on the edge characteristics between the starting point and the end point of the gas transportation, and determines the gas storage regulation parameters based on the gas storage regulation strategy with the lowest gas transportation cost. The dynamic programming algorithm refers to a related algorithm preset in advance.

[0092] In some embodiments, if the sum of the gas storage amounts of all nodes is less than the sum of the gas demand amounts in a preset future period, the distributed energy demand management platform can add gas stations to the dynamic programming algorithm, and determine the gas storage regulation parameters according to the gas supply priority and based on the gas storage regulation strategy with the lowest gas transportation cost.

[0093] In some embodiments, the distributed energy demand management platform can also determine the expected completion degree and expected completion efficiency of candidate adjustment parameters through the scheduling model based on the micro-pipeline network map and gas storage coverage, and determine the gas storage adjustment parameters based on the expected completion degree and expected completion efficiency. For more information, please refer to Figure 4 Related instructions.

[0094] Step 290, generating a gas storage adjustment instruction based on the gas storage adjustment parameter.

[0095] The gas storage regulation instruction is an instruction for controlling gas transportation. In some embodiments, the distributed energy demand management platform can generate a gas storage regulation instruction based on the gas storage regulation parameter and send it to the gas station for regulation.

[0096] In some embodiments, in response to the current period being a peak gas consumption period, the distributed energy demand management platform reduces the sampling frequency of the gas cost sequence, production parameter sequence, and commercial impact sequence of the preset future period. The sampling frequency refers to the frequency of obtaining the gas cost sequence, production parameter sequence, and commercial impact sequence, etc. in the preset future period. The distributed energy demand management platform can perform sampling once every interval of the length of each small time period in the preset future period. The sampling frequency is inversely proportional to the length of each small time period in the preset future period.

[0097] The peak gas usage period refers to the period when gas is used more. In some embodiments, the distributed energy demand management platform determines the period that meets the first preset condition as the peak gas usage period. The first preset condition may be that the gas flow data is greater than a preset flow threshold. The preset flow threshold may be set based on historical experience. The peak gas usage period may also be preset.

[0098] In some embodiments, the distributed energy demand management platform increases the length of each small time period in the preset future time period to reduce the sampling frequency.

[0099] During peak gas usage periods, reducing the sampling frequency in the preset future time period can more quickly build a micro-pipeline network map, thereby increasing the response speed of providing gas to gas-deficient gas supply areas and ensuring smooth gas output during peak gas usage periods.

[0100] Based on the influencing factors of gas use and historical usage data, the gas demand in the preset future period is estimated, and the obtained gas demand is closer to the actual situation. Based on the micro-pipeline network map, the gas storage coverage rate and gas supply priority of each gas supply area are determined, and based on the gas storage coverage rate and gas supply priority, the gas storage adjustment parameters are determined to ensure the normal supply of gas in the gas supply area without affecting the normal production and life of gas users.

[0101] Figure 3 It is an exemplary flowchart for adjusting commercial change sequences and civil change sequences according to some embodiments of this specification.

[0102] like Figure 3 As shown, the process 300 includes the following steps: In some embodiments, the process 300 is executed by the distributed energy demand management platform 130 of the system 100 .

[0103] In some embodiments, Figure 2 In the iteration, the distributed energy demand management platform can adjust the commercial change sequence and the civil change sequence corresponding to the iteration. The distributed energy demand management platform can make adjustments in the iteration through the following process 300. For details about iteration, commercial change sequence, civil change sequence, etc., please refer to Figure 2 Related description.

[0104] Step 310: Determine the impact matching degree based on the historical commercial sequence and the historical commercial data.

[0105] For more information about historical commercial data, see Figure 2 Related description.

[0106] The historical commercial sequence refers to the product sales at multiple time points within a preset historical period. The preset historical period can be a small time period before the current moment. The historical commercial sequence is directly obtained from the market.

[0107] Impact matching refers to the degree of influence of historical commercial sequences on historical commercial data.

[0108] In some embodiments, the distributed energy demand management platform can determine the impact matching degree in a variety of ways based on the historical commercial sequence and historical commercial data. For example, the impact matching degree is positively correlated with the change in product sales volume within a preset historical period, and negatively correlated with the change in commercial gas usage. Exemplarily, the impact matching degree can be calculated by the following formula (1):

[0109] (1)

[0110] in, X To influence the matching degree, n is the total number of time points in the preset historical period, M k For time point k of product sales, P k For time point k of commercial gas usage.

[0111] Step 320: Adjust the commercial change sequence based on the impact matching degree.

[0112] In some embodiments, the commercial change sequence is adjusted based on the impact matching degree. For example, the distributed energy demand management platform can adjust the commercial change sequence in a variety of ways. The commercial change sequence is positively correlated with the impact matching degree, and the distributed energy demand management platform can multiply the commercial change sequence by the impact matching degree to obtain an adjusted commercial change sequence.

[0113] Step 330, determining agricultural interference factors based on historical agricultural cycles, historical weather data, and historical civil data.

[0114] For more information on historical civilian data, see Figure 2 Related description.

[0115] The historical agricultural cycle refers to the planting and harvesting cycle of agricultural products in historical data. For example, the historical agricultural cycle includes the planting cycle of wheat, the harvesting cycle of wheat, and the planting cycle of rice. In some embodiments, the historical agricultural cycle is stored in the energy demand database, and the distributed energy demand management platform obtains the historical agricultural cycle based on the energy demand database.

[0116] Historical weather data refers to weather data in historical data. For example, historical weather data includes ambient temperature and ambient humidity. In some embodiments, historical weather data is acquired based on the temperature sensor and humidity sensor of the distributed energy sensing control platform and stored in the energy demand database. The distributed energy demand management platform acquires historical weather data based on the energy demand database.

[0117] The agricultural interference factor refers to the degree of influence of historical agricultural cycles and historical weather data on historical civil data. The agricultural interference factor can be obtained by statistically analyzing the differences between historical agricultural cycles, historical weather data and corresponding historical civil data in multiple historical data and standard agricultural cycles, standard weather data and standard civil data. Among them, the standard agricultural cycle, standard weather data and standard civil data can be preset based on experience.

[0118] In some embodiments, the distributed energy demand management platform can determine the agricultural interference factor in a variety of ways based on historical agricultural cycles, historical weather data, and corresponding historical civil data. For example, the agricultural interference factor is positively correlated with the absolute value of the change in the first civil data, the agricultural interference factor is positively correlated with the absolute value of the difference between the historical agricultural cycle and the standard agricultural cycle and the ratio of the standard agricultural cycle, and the agricultural interference factor is positively correlated with the absolute value of the difference between the historical weather data and the standard weather data and the ratio of the standard weather data. The agricultural interference factor can be calculated using the following formula (2):

[0119] (2)

[0120] in, Agricultural disturbance factors, b 2 is the change in the first civil data, c For the historical agricultural cycle, c 0 is the standard agricultural cycle, d For historical weather data, d 0 is standard weather data.

[0121] In some embodiments, the first civil data variation reflects the variation of civil data under the premise of agricultural cycle and weather data variation. The first civil data variation is the difference between historical civil data and standard civil data.

[0122] In some embodiments, the difference between the historical weather data and the standard weather data refers to the sum of the absolute values ​​of the differences between the historical ambient temperature and the standard ambient temperature, and between the historical ambient humidity and the standard ambient humidity.

[0123] Step 340, adjusting the civil change sequence based on the agricultural disturbance factor, the current agricultural cycle, the current weather data and the historical civil data.

[0124] The current agricultural cycle refers to the planting and harvesting cycle of agricultural products in the period corresponding to the current iteration. In some embodiments, the current agricultural cycle can be obtained based on the types of crops currently planted in each area, and the types of crops can be obtained based on image recognition by a camera of a drone.

[0125] The current weather data refers to the ambient temperature and humidity of the current period, etc. The current weather data can be obtained based on the temperature sensor device and humidity sensor device of the distributed energy perception control platform.

[0126] In some embodiments, the distributed energy demand management platform can adjust the civil change sequence in a variety of ways based on the agricultural interference factor, the current agricultural cycle, the current weather data, and the historical civil data. For example, the adjusted civil change sequence is positively correlated with the agricultural interference factor, negatively correlated with the historical civil data, positively correlated with the absolute value of the difference between the current agricultural cycle and the standard agricultural cycle, and positively correlated with the absolute value of the difference between the current weather data and the standard weather data. The adjusted civil change sequence can be calculated by the following formula (3):

[0127] (3)

[0128] in, y is the adjusted civil change sequence, y 0 is the civil change sequence before adjustment, a Agricultural disturbance factors, c 1 is the current agricultural cycle, c 0 is the standard agricultural cycle, d 1 is the current weather data, d 0 is standard weather data, b For historical civilian data. k 3 and k 4 refers to the weight coefficient, which can be preset based on experience.

[0129] In some embodiments, k 3 and k The magnitude relationship of 4 can be determined based on the magnitude relationship between the civil change sequence and the agricultural interference factor. For example, when the civil change sequence is greater than the agricultural interference factor, k 3 is greater than k 4. On the contrary k 3 is less than k 4.

[0130] The civil change sequence and agricultural interference factor actually reflect the degree of influence of certain factors on civil use data. The larger the civil change sequence and / or agricultural interference factor, the greater the influence on civil data. Therefore, the size relationship between the civil change sequence and agricultural interference factor can be used to determine the size relationship of their weights. The greater the influence, the greater the weight of the factor, to ensure the credibility of the adjusted civil change sequence.

[0131] In some embodiments, the distributed energy demand management platform obtains the harvest forecast of at least one gas supply area in a preset future time period; and adjusts the civil change sequence based on the agricultural product scale, planting method, harvest forecast and historical civil data of at least one gas supply area.

[0132] The harvest forecast refers to the estimated harvest of agricultural products in the time corresponding to the preset future period. In some embodiments, the distributed energy demand management platform determines the harvest forecast based on historical data. For example, when the preset future period is September, the distributed energy demand management platform calculates the average of the actual harvest of agricultural products in September of each year in the historical data as the harvest forecast.

[0133] In some embodiments, the distributed energy demand management platform may also adjust the harvest forecast based on standard civil data and historical civil data for historical future periods in the historical data.

[0134] The standard civil data refers to the usage of civil gas in the time corresponding to the preset future period in the historical data. In some embodiments, the standard civil data is stored in the energy demand database, and the distributed energy demand management platform obtains the standard civil data based on the energy demand database.

[0135] In some embodiments, the distributed energy demand management platform can adjust the harvest forecast in a variety of ways based on the standard civil data and the historical civil data. For example, the absolute value of the difference between the adjusted harvest forecast and the historical civil data and the standard civil data is positively correlated with the ratio of the standard civil data. The adjusted harvest forecast can be calculated by the following formula (4):

[0136] (4)

[0137] in, z is the adjusted harvest forecast, z 0 is the harvest forecast before adjustment. b 0 is standard civilian data, b For historical civilian data.

[0138] Adjusting the harvest forecast through standard usage data for historical future periods and historical usage data in historical data will help further ensure the credibility of adjusting the civil change sequence based on the harvest forecast.

[0139] The scale of agricultural products refers to the area and quantity of agricultural products planted. In some embodiments, the scale of agricultural products is stored in an energy demand database, and the distributed energy demand management platform obtains the scale of agricultural products based on the energy demand database.

[0140] The planting method refers to the method used for planting agricultural products in the gas supply area. For example, the planting method may include greenhouse planting and / or farmland planting. In some embodiments, the planting method is stored in the energy demand database, and the distributed energy demand management platform obtains the planting method based on the energy demand database.

[0141] In some embodiments, the distributed energy demand management platform determines the second civil data change amount based on the vector database, wherein the second civil data change amount refers to the change amount of civil gas usage under the influence of agricultural product scale, planting method and agricultural product harvest.

[0142] In some embodiments, the vector database includes multiple feature vectors and corresponding labels, and the elements of the feature vectors include agricultural product scale, planting method, and harvest forecast in historical data, etc. The label corresponding to the feature vector is the change amount of the historical civil data corresponding to the feature vector.

[0143] The distributed energy demand management platform can select multiple feature vectors whose similarity with the target vector is greater than a preset similarity threshold, and use the average value of the first labels corresponding to the multiple feature vectors as the second civilian data change. The elements of the target vector include agricultural product scale, planting method, and harvest forecast, etc. The preset similarity threshold can be preset based on experience or manually set.

[0144] In some embodiments, the distributed energy demand management platform can also adjust the civil change sequence in a variety of ways based on the second civil data change amount and the historical civil data. For example, the adjusted civil change sequence is positively correlated with the second civil data change amount and negatively correlated with the historical civil data. The adjusted civil change sequence can be calculated by the following formula (5):

[0145] (5)

[0146] in, y is the adjusted civil change sequence, y 0 is the civil change sequence before adjustment, b 3 is the change of the second civil data, b For historical civilian data. k 5 and k 6 refers to the weight coefficient, which can be preset based on experience.

[0147] In some embodiments, the adjustment of the civil change sequence may also be determined by any other feasible manner.

[0148] Adjusting the civil change sequence through harvest forecasts is helpful in guiding the planting of agricultural products in each gas supply area.

[0149] By influencing the matching degree to adjust the commercial change sequence, and adjusting the civil change sequence by agricultural interference factors, current agricultural cycle, current weather data and historical usage data, it is beneficial to ensure the credibility of commercial change sequence and civil change sequence, and further guide the delivery of commercial and civil gas.

[0150] Figure 4 is an exemplary schematic diagram of a scheduling model according to some embodiments of this specification. In some embodiments, the distributed energy demand management platform can determine the expected completion degree 431 and expected completion efficiency 432 of the candidate adjustment parameters through the scheduling model 420 based on the micro-pipeline network map 411 and the gas storage coverage rate 412 of each node in the micro-pipeline network map; based on the expected completion degree 431 and the expected completion efficiency 432, determine the gas storage adjustment parameter 440. For more information about the micro-pipeline network map, gas storage coverage rate and gas storage adjustment parameters, see Figure 2 Related instructions.

[0151] In some embodiments, the distributed energy demand management platform can downsample the demand sequence before inputting the micro-pipeline network map into the scheduling model in response to the current period being a gas consumption peak period. For more information about the demand sequence, see Figure 2 Related instructions.

[0152] In some embodiments, the distributed energy demand management platform can reduce the amount of data in the demand sequence based on the downsampling ratio. The downsampling ratio refers to the ratio of the amount of data in the demand sequence before downsampling to the amount of data in the demand sequence after downsampling. For example, when the downsampling ratio is 2, the distributed energy demand management platform determines the average of the gas demand in two consecutive small time periods as one gas demand, and the length of the time period corresponding to the new gas demand is twice that of the small time period. At this time, the amount of data in the demand sequence is 1 / 2 of the original.

[0153] In some embodiments, the downsampling ratio of the downsampling is related to the duration of the preset future period, for example, the downsampling ratio is positively correlated with the duration of the preset future period. For more information about the preset future period, see Figure 2 Related instructions.

[0154] When the preset future period is long, the micro-pipeline network map tends to focus more on the changing trend of gas demand. At this time, a higher sampling ratio can be used to reduce the amount of data, but still retain information related to the changing trend of gas demand.

[0155] In some embodiments of the present specification, during the peak gas consumption period, the demand sequence is downsampled, which reduces the amount of data contained in the micro-pipeline network map and improves the calculation efficiency of the scheduling model.

[0156] The scheduling model is a model used to determine the expected completion degree and expected completion efficiency. The scheduling model is a machine learning model, for example, the scheduling model is a Graph Neural Networks (GNN) model.

[0157] In some embodiments, the input of the scheduling model includes a micro-pipeline network map 411 and a gas storage coverage rate 412 of each node in the micro-pipeline network map, and the output is an expected completion degree 431 and an expected completion efficiency 432 of the candidate adjustment parameters.

[0158] The candidate adjustment parameters refer to selectable gas storage adjustment parameters. The scheduling model may include a plurality of pre-stored candidate adjustment parameters.

[0159] The expected completion rate refers to the estimated proportion of gas demand that can be met after gas storage regulation. In some embodiments, the expected completion rate is the average value of the gas storage coverage rate of all nodes in the micro-pipeline network map after gas storage regulation is completed.

[0160] The expected completion efficiency is the inverse of the estimated time required to complete the gas storage adjustment.

[0161] In some embodiments, the distributed energy demand management platform can obtain a scheduling model based on a training sample set. The training sample set may include multiple first training samples with a first label. For example, the distributed energy demand management platform may input multiple first training samples into an initial scheduling model, construct a first loss function based on the output of the initial scheduling model and the first label, iteratively update the parameters of the initial scheduling model based on the first loss function, and terminate the iteration when the iteration completion condition is met to obtain a trained scheduling model. Among them, the iterative update method includes but is not limited to the gradient descent method, and the iteration completion condition may be that the first loss function converges or the number of iterations reaches a threshold.

[0162] The first training sample includes a sample micro-pipeline network map and a sample gas storage coverage rate of each node in the sample micro-pipeline network map, and the first label is a sample expected completion degree and a sample expected completion efficiency corresponding to a sample candidate adjustment parameter corresponding to the first training sample. The first training sample and the first label can be obtained based on historical data.

[0163] In some embodiments, Figure 4 As shown, the scheduling model may include a priority evaluation layer 421 , a candidate parameter generation layer 422 , and a completion expectation estimation layer 423 .

[0164] The priority evaluation layer 421 is used to determine the gas supply priority of each node in the micro-pipeline network map. The input of the priority evaluation layer is the micro-pipeline network map 411, and the output is the gas supply priority 421-1 of each node in the micro-pipeline network map. For more information about gas supply priority, see Figure 2 Related instructions.

[0165] In some embodiments, the distributed energy demand management platform can obtain a priority assessment layer based on training sample sets. The training sample set may include multiple second training samples with second labels. The second training sample includes a sample micro-pipeline network map, and the second label is the gas supply priority of each node in the sample micro-pipeline network map corresponding to the second training sample. The distributed energy demand management platform may determine the historical micro-pipeline network map in the historical data, in which the actual completion degree is greater than the preset completion degree threshold after the gas storage adjustment is completed, as the second training sample, and determine the gas supply priority of each node in the historical micro-pipeline network map as the second label. The training process of the priority assessment layer is similar to Figure 4 The training process of the scheduling model is the same.

[0166] The candidate parameter generation layer 422 is used to generate candidate adjustment parameters. The input of the candidate parameter generation layer is the micro-pipeline network map 411, the gas storage coverage rate 412 of each node in the micro-pipeline network map, and the gas supply priority 421-1 of each node in the micro-pipeline network map, and the output is multiple candidate adjustment parameters 422-1.

[0167] In some embodiments, the distributed energy demand management platform can generate candidate parameters based on training of a training sample set. The training sample set may include multiple third training samples with a third label. The third training sample includes a sample micro-pipeline network map, a sample gas storage coverage rate and a sample gas supply priority of each node in the sample micro-pipeline network map, and the third label is a sample candidate adjustment parameter corresponding to the third training sample. The distributed energy demand management platform can obtain the third training sample based on historical data, cluster the third training sample, obtain multiple cluster centers, and determine the historical gas storage adjustment parameters corresponding to all the third training samples included in each cluster center as the third label corresponding to each third training sample in the cluster center. For example, cluster center A includes 5 third training samples, namely a1, a2, a3, a4, and a5, and the corresponding historical gas storage adjustment parameters are b1, b2, b3, b4, and b5, respectively. Then the third label corresponding to the third training sample a1 includes b1, b2, b3, b4, and b5, with a total of 5 sample candidate adjustment parameters. The third label corresponding to the third training sample a2 includes b1, b2, b3, b4, and b5, with a total of 5 sample candidate adjustment parameters. ... The third label corresponding to the third training sample a3 includes b1, b2, b3, b4, and b5, with a total of 5 sample candidate adjustment parameters. Clustering methods include but are not limited to K-Means clustering algorithm, DBSCAN clustering algorithm, etc. The training process of the candidate parameter generation layer is the same as Figure 4 The training process of the scheduling model is the same.

[0168] The expected completion estimation layer 423 is used to determine the expected completion degree and expected completion efficiency model corresponding to the candidate adjustment parameters. The input of the expected completion estimation layer 423 includes the micro-pipeline network map 411 and the candidate adjustment parameter 422-1, and the output is the expected completion degree 431 and expected completion efficiency 432 corresponding to the candidate adjustment parameter 422-1.

[0169] In some embodiments, the distributed energy demand management platform can be trained based on the training sample set to obtain the completion expectation prediction layer. The training sample set may include a fourth training sample based on multiple fourth labels. The fourth training sample includes a sample micro-pipeline network map and a sample candidate adjustment parameter, and the fourth label is the historical completion degree and historical completion efficiency corresponding to the fourth training sample. The fourth label can be obtained based on historical data. The training process of completing the expected prediction layer is similar to Figure 4 The training process of the scheduling model is the same.

[0170] In some embodiments, the priority evaluation layer, the candidate parameter generation layer, and the completion expectation estimation layer can be obtained through joint training based on the training sample set. The training sample set includes joint training samples. The joint training samples include sample micro-pipeline network maps and sample gas storage coverage rates, and the corresponding labels are historical completion and historical completion efficiency. The distributed energy demand management platform can input the sample micro-pipeline network map into the initial priority evaluation layer to obtain the gas supply priority of each node in the sample micro-pipeline network map output by the initial priority evaluation layer. The gas supply priority, the sample micro-pipeline network map, and the sample gas storage coverage rate are input into the initial candidate parameter generation layer to obtain multiple candidate adjustment parameters output by the initial candidate parameter generation layer. Multiple candidate adjustment parameters and the sample micro-pipeline network map are input into the initial expected estimation layer to obtain the expected completion and expected completion efficiency output by the initial expected estimation layer. Based on the expected completion, expected completion efficiency, historical completion, and historical completion efficiency, a joint loss function is constructed, and the parameters are iteratively updated based on the joint loss function to obtain the trained priority evaluation layer, the candidate parameter generation layer, and the completion expectation estimation layer.

[0171] In some embodiments, in the training sample set, the number of samples in the collection period is greater than the sample size threshold, and the sample size threshold is related to the historical fluctuation range of the historical gas usage in the collection period. The sample size threshold is positively correlated with the historical fluctuation range of the historical gas usage in the collection period. The sampling period is the historical period.

[0172] In some embodiments, the distributed energy demand management platform obtains training sample sets based on historical data of multiple sampling periods, and the number of training sample sets in each sampling period is greater than the corresponding sample size threshold. The sample size threshold is positively correlated with the historical fluctuation range of historical gas usage data in the sampling period.

[0173] In some embodiments, the distributed energy demand management platform may determine the range of multiple historical gas usage data within a sampling period as the fluctuation range of the historical gas usage data within the historical period.

[0174] The greater the fluctuation of gas usage, the more drastic the change in gas usage during the collection period. At this time, the change amplitude and frequency of gas usage and micro-pipeline network map will also increase. It is necessary to increase the number of samples in the collection period to ensure the comprehensiveness of the training sample set.

[0175] In some embodiments, the input of the scheduling model also includes a time period of a preset future period. When the scheduling model is a multi-layer structure, the input of the candidate parameter generation layer also includes a time period of a preset future period.

[0176] A season period refers to a time period corresponding to a preset future period. The distributed energy demand management platform can determine the season period based on the current time and the duration of the preset future period.

[0177] In some embodiments, when the input of the scheduling model or the candidate parameter generation layer also includes a season period of a preset future period, the training sample set also includes a sample season period, and the sample season period can be acquired based on historical data.

[0178] The preset future time period may be in the peak traffic period, the winter road icy period and other periods that are not convenient for tank truck transportation. At this time, the transportation path of the tank truck needs to be considered, and the shortest path cannot be simply used as the transportation path of the tank truck. When generating candidate adjustment parameters, the season period of the preset future time period is considered, which improves the rationality and safety of determining the candidate adjustment parameters.

[0179] In some embodiments, the input of the scheduling model also includes the current agricultural cycle and agricultural product scale corresponding to at least one node. When the scheduling model is a multi-layer structure, the input of the priority evaluation layer also includes the current agricultural cycle and agricultural product scale corresponding to at least one node. For more information about agricultural cycles and agricultural product scales, see Figure 3 Related instructions.

[0180] In some embodiments, when the input of the scheduling model or priority assessment layer also includes the current agricultural production cycle and agricultural product scale, the training sample set also includes sample agricultural production cycle and sample agricultural product scale, and the sample agricultural production cycle and sample agricultural product scale can be obtained based on historical data.

[0181] The demand and importance of gas vary with different agricultural production cycles. For example, when agricultural products are in the seedling stage, they are sensitive to temperature. At this time, it is necessary to provide timely and sufficient gas supply to the temperature control equipment to stabilize the temperature within a smaller range to ensure the smooth germination of seeds. The larger the scale of agricultural products, the greater the loss of gas supply interruption. Therefore, the gas supply areas (such as towns, etc.) corresponding to nodes with larger agricultural product scales require higher gas supply priority. Therefore, considering the agricultural production cycle and the scale of agricultural products when estimating the priority of each node can ensure the rationality of the model output and improve the effect of the candidate adjustment parameters generated subsequently.

[0182] In some embodiments, the distributed energy demand management platform can calculate the mean and variance of the expected degree of completion and the mean and variance of the expected completion efficiency corresponding to each candidate adjustment parameter, determine the score of each candidate adjustment parameter by weighted summation, and determine the candidate adjustment parameter with the highest score as the gas storage adjustment parameter to be finally used. The weights of the weighted summation corresponding to each parameter can be set based on historical experience.

[0183] A plurality of candidate adjustment parameters are generated through the scheduling model, and the expected completion degree and expected completion efficiency of each candidate adjustment parameter are calculated respectively. The gas storage adjustment parameter to be finally used is determined based on the expected completion degree and the expected completion efficiency, and gas storage adjustment is performed based on the gas storage adjustment parameter. This can meet the gas demand of the user as much as possible in the shortest time and ensure the normal production and life of the user.

[0184] Some embodiments of the present specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the distributed energy pipeline natural gas demand management method as described in some embodiments of the present specification.

[0185] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0186] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0187] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A distributed energy pipeline natural gas demand management method, characterized in that: The method is executed by a distributed energy demand management platform of a distributed energy pipeline natural gas demand management Internet of Things system, and the method comprises: Based on the production parameter sequence and commercial influence sequence of the factory in at least one gas supply area in the preset future time period, determining the commercial change sequence of the at least one gas supply area in the preset future time period, the commercial change sequence refers to a sequence composed of commercial gas change coefficients, the commercial change sequence includes the commercial gas change coefficients corresponding to a plurality of small time periods, each of the commercial gas change coefficients reflects the commercial gas usage rate in the corresponding small time period; Obtaining gas flow data of a low-pressure transportation network of at least one gas supply area via a distributed energy sensing network platform and a distributed energy sensing control platform; Based on the gas flow data, acquiring historical usage data of the at least one gas supply area; Based on the historical gas cost, the historical usage data, the season information and the gas cost sequence of the at least one gas supply area in the preset future time period, determine the civil change sequence of the at least one gas supply area in the preset future time period, the civil change sequence refers to a sequence composed of a plurality of civil gas change coefficients, the civil change sequence includes the civil gas change coefficients corresponding to the plurality of small time periods, each of the civil gas change coefficients being the ratio of the civil gas usage in the corresponding small time period to the civil gas usage in the previous small time period; Determining a demand sequence of the at least one gas supply area in the preset future time period based on the civil change sequence, the commercial change sequence and the historical usage data; Based on the low-pressure transportation network of the at least one gas supply area, the current gas storage capacity of the gas station, the demand quantity sequence and the storage scale of the gas station, a micro-pipeline network map of the at least one gas supply area is constructed; Based on the micro-pipeline network map, determine the gas storage coverage rate and gas supply priority of at least one node, wherein the gas storage coverage rate refers to the proportion of the current gas storage capacity that can meet the gas demand; Based on the gas storage coverage rate and the gas supply priority, determining gas storage adjustment parameters, the gas storage adjustment parameters including the gas supply volume, gas supply location and gas supply time point of the gas station; Based on the gas storage adjustment parameter, a gas storage adjustment instruction is generated.

2. The method according to claim 1, characterized in that The method further comprises: Determine the impact matching degree based on historical commercial sequences and historical commercial data; Based on the impact matching degree, adjusting the commercial change sequence; Determine agricultural disturbance factors based on historical agricultural cycles, historical weather data, and historical civil data; The civil change sequence is adjusted based on the agricultural disturbance factor, the current agricultural cycle, the current weather data and the historical civil data.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining a harvest prediction sequence of the at least one gas supply area in the preset future time period; The civil change sequence is adjusted based on the agricultural product scale, planting method, the harvest forecast sequence and the historical usage data of the at least one gas supply area.

4. The method according to claim 1, characterized in that The method further comprises: Based on the micro-pipeline network map and the gas storage coverage rate, an expected degree of completion and an expected efficiency of completion of candidate adjustment parameters are determined by a scheduling model, wherein the scheduling model is a machine learning model; The gas storage adjustment parameter is determined based on the expected degree of completion and the expected completion efficiency.

5. A distributed energy pipeline natural gas demand management Internet of Things system, characterized by: The system includes a distributed energy perception control platform, a distributed energy sensor network platform, a distributed energy demand management platform, a distributed energy service platform and a distributed energy user platform connected in sequence, and the distributed energy demand management platform is configured as follows: Based on the production parameter sequence and commercial influence sequence of the factory in at least one gas supply area in the preset future time period, determining the commercial change sequence of the at least one gas supply area in the preset future time period, the commercial change sequence refers to a sequence composed of commercial gas change coefficients, the commercial change sequence includes the commercial gas change coefficients corresponding to a plurality of small time periods, each of the commercial gas change coefficients reflects the commercial gas usage rate in the corresponding small time period; Obtaining gas flow data of a low-pressure transportation network of at least one gas supply area via the distributed energy sensor network platform and the distributed energy perception control platform; Based on the gas flow data, acquiring historical usage data of the at least one gas supply area; Based on the historical gas cost, the historical usage data, the season information and the gas cost sequence of the at least one gas supply area in the preset future time period, determine the civil change sequence of the at least one gas supply area in the preset future time period, the civil change sequence refers to a sequence composed of a plurality of civil gas change coefficients, the civil change sequence includes the civil gas change coefficients corresponding to the plurality of small time periods, each of the civil gas change coefficients being the ratio of the civil gas usage in the corresponding small time period to the civil gas usage in the previous small time period; Determining a demand sequence of the at least one gas supply area in the preset future time period based on the civil change sequence, the commercial change sequence and the historical usage data; Based on the low-pressure transportation network of the at least one gas supply area, the current gas storage capacity of the gas station, the demand quantity sequence and the storage scale of the gas station, a micro-pipeline network map of the at least one gas supply area is constructed; Based on the micro-pipeline network map, determine the gas storage coverage rate and gas supply priority of at least one node, wherein the gas storage coverage rate refers to the proportion of the current gas storage capacity that can meet the gas demand; Based on the gas storage coverage rate and the gas supply priority, determining gas storage adjustment parameters, the gas storage adjustment parameters including the gas supply volume, gas supply location and gas supply time point of the gas station; Based on the gas storage adjustment parameter, a gas storage adjustment instruction is generated.

6. The system according to claim 5, characterized in that The distributed energy demand management platform is further configured as follows: Determine the impact matching degree based on historical commercial sequences and historical commercial data; Based on the impact matching degree, adjusting the commercial change sequence; Determine agricultural disturbance factors based on historical agricultural cycles, historical weather data, and historical civil data; The civil change sequence is adjusted based on the agricultural disturbance factor, the current agricultural cycle, the current weather data and the historical civil data.

7. The system according to claim 6, characterized in that The distributed energy demand management platform is further configured as follows: Obtaining a harvest prediction sequence of the at least one gas supply area in the preset future time period; The civil change sequence is adjusted based on the agricultural product scale, planting method, the harvest forecast sequence and the historical usage data of the at least one gas supply area.

8. The system according to claim 5, characterized in that The distributed energy demand management platform is further configured as follows: Based on the micro-pipeline network map and the gas storage coverage rate, an expected degree of completion and an expected efficiency of completion of candidate adjustment parameters are determined by a scheduling model, wherein the scheduling model is a machine learning model; The gas storage adjustment parameter is determined based on the expected degree of completion and the expected completion efficiency.

9. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method as claimed in any one of claims 1 to 4.

Images