Fuel gas conveying intelligent scheduling method and system based on Internet of Things

Abstract

The invention relates to the technical field of fuel gas scheduling, in particular to an intelligent scheduling method and system for fuel gas delivery based on the Internet of Things, and the method comprises the steps: S1, obtaining a user set corresponding to fuel gas scheduling during the fuel gas scheduling, and determining the fuel gas consumption in the user set; s2, identifying gas consumption changes of the user set at different time lines and positions, and drawing a gas consumption curve changing along with time; s3, analyzing the gas consumption curve, and determining main influence factors of the gas consumption; s4, according to the main influence factors of the gas consumption and the gas consumption curve, the distribution conditions of the gas consumption at different positions are calculated, and a gas scheduling scheme is determined; s5, according to the gas scheduling scheme, obtaining a relationship between gas scheduling and a position, identifying a scheduling frequent area, and adjusting the gas scheduling scheme according to the characteristics of the scheduling frequent area; the accuracy and efficiency of gas scheduling are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of gas dispatching, and in particular to a method and system for intelligent dispatching of gas transportation based on the Internet of Things. Background Art

[0002] City gas dispatching is the centralized monitoring and command of the city gas supply system. In order to achieve a balance between gas supply and demand, ensure safe supply, maintain optimal working conditions and economic operation, the city gas gate station collects information on gas sources, transmission and distribution, and application, and then transmits it to the gas dispatching center, which organizes, analyzes, predicts and judges, and issues instructions for production, transmission and distribution, and operation.

[0003] For example, Chinese patent publication number CN111126859A discloses a digital acquisition system and method based on the industrial Internet. The digital acquisition system includes a data measurement module, a data receiving module and a data analysis module. The data measurement module is used to measure the gas data on the gas pipeline. The data receiving module includes a gas gate station receiving module and a gas dispatching center receiving module. The gas gate station receiving module is used for the gas gate station to receive the gas data transmitted by the gas pipeline. The gas dispatching center receiving module is used for the gas dispatching center to receive the gas data transmitted by the gas gate station. The data analysis module is used for the gas dispatching center to dispatch and allocate the gas supply according to the gas data.

[0004] The existing technology sets marks on gas pipelines and gas gate stations and determines the corresponding gas distribution based on the marks and measured data. However, when analyzing gas scheduling, it is necessary to determine the relevant trends of users' gas consumption and identify the relevant parameters during scheduling based on these trends to determine whether the current scheduling plan can be executed normally, so as to achieve stability and efficiency in gas scheduling, supply and transportation. Summary of the invention

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a gas transmission intelligent scheduling method based on the Internet of Things, including: S1, when obtaining gas scheduling, the user set corresponding to the gas scheduling is determined, and the gas consumption in the user set is determined.

[0006] S2, identifies the changes in gas consumption of user sets at different timelines and locations, and draws a gas consumption curve that changes over time.

[0007] S3, analyze the gas consumption curve and determine the main influencing factors of gas consumption.

[0008] S4, according to the main influencing factors of gas consumption and the gas consumption curve, calculate the distribution of gas consumption in different locations and determine the gas scheduling plan.

[0009] S5, according to the gas scheduling plan, obtain the relationship between gas scheduling and location, identify the frequent scheduling area, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling area.

[0010] A gas transmission intelligent adjustment system based on the Internet of Things includes: a gas consumption data acquisition module: used to collect users' gas consumption data in real time through Internet of Things devices, and associate the data with users' location information to form a structured data set.

[0011] Gas consumption curve drawing module: used to process the structured data set using the autoregressive moving average model, output the gas consumption curve, and determine the change trend of the gas consumption curve through the maximum likelihood estimation method.

[0012] Gas consumption analysis module: used to identify seasonal factors, gas usage habits and gas pipeline network factors among the main factors affecting gas consumption by screening the changing trend of the gas consumption curve.

[0013] Gas scheduling calculation module: used to calculate the distribution of gas consumption in different locations and determine the gas scheduling plan based on the main influencing factors of gas consumption and the gas consumption curve.

[0014] Gas scheduling adjustment module: used to obtain the relationship between gas scheduling and location according to the gas scheduling plan, identify the frequent scheduling areas, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling areas.

[0015] The beneficial effects of the present invention are as follows: 1. The present invention uses the Internet of Things technology and the autoregressive moving average model to achieve accurate prediction of gas consumption and improve the accuracy of the scheduling plan.

[0016] 2. The present invention comprehensively analyzes the factors affecting gas consumption, formulates a more scientific and reasonable scheduling plan, and improves the stability and efficiency of gas supply.

[0017] 3. The present invention timely discovers and solves safety problems in the gas transportation process through real-time monitoring and intelligent scheduling, thereby ensuring the safety of gas supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0019] Figure 1 It is a flow chart of an intelligent dispatching method for gas transmission based on the Internet of Things.

[0020] Figure 2 The present invention is a flow chart of step S2 of a method for intelligent scheduling of gas transportation based on the Internet of Things.

[0021] Figure 3 The present invention is a flow chart of step S4 of a method for intelligent scheduling of gas transportation based on the Internet of Things.

[0022] Figure 4 It is a system diagram of a gas transmission intelligent dispatching system based on the Internet of Things. DETAILED DESCRIPTION

[0023] The embodiments of the present invention are described in detail below. The embodiments described below are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. If no specific techniques or conditions are specified in the embodiments, the techniques or conditions described in the literature in the art or the product specifications are used.

[0024] See also Figure 1 ,A method for intelligent scheduling of gas transmission based on the Internet of Things, including: S1, when obtaining the gas scheduling, the user set corresponding to the gas scheduling, and determining the gas consumption in the user set.

[0025] S2, identifies the changes in gas consumption of user sets at different timelines and locations, and draws a gas consumption curve that changes over time.

[0026] S3, analyze the gas consumption curve and determine the main influencing factors of gas consumption.

[0027] S4, according to the main influencing factors of gas consumption and the gas consumption curve, calculate the distribution of gas consumption in different locations and determine the gas scheduling plan.

[0028] S5, according to the gas scheduling plan, obtain the relationship between gas scheduling and location, identify the frequent scheduling area, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling area.

[0029] The user set includes different types of gas consumers such as residential users, commercial users, and industrial users.

[0030] like Figure 2 As shown, step S2 includes the following implementation methods: S21, obtaining the gas consumption of the user set at each time point and the user's geographical location information, and arranging the collected data according to the timeline and location to obtain a structured data set.

[0031] S22, drawing a gas consumption curve according to a preset period based on the structured data set, and determining a change trend of the gas consumption curve.

[0032] The preset cycle lengths are 1 day, 1 week, 1 month, and 1 year to quantify users' demand for gas consumption.

[0033] The gas consumption in step S21 is obtained by obtaining the gas consumption of the corresponding user from the user set, wherein the set user set includes not only the corresponding type of gas consumers but also the corresponding gas consumption information, as well as the user-related location and the time when the gas is consumed.

[0034] The method of drawing the gas consumption curve is to input the structured data set into the autoregressive moving average model, and the autoregressive moving average model outputs the gas consumption curve. The gas consumption curve is represented as shown below.

[0035] Y t =c+φ1Y t-1 +φ2Y t-2 +,,,+φ p Y t-p +θ1ε t-1 +θ2ε t-2 +,,,+θ q ε t-q +ε t ; Among them, Y t ,Y t-1 ,,,Y t-p express

[0036] The gas consumption from time point t to time point tp, c represents the constant term, φ1, φ2,,, φ p represents the autoregressive parameter, p represents the number of autoregressive parameters, θ1,θ2,,,θ q represents the moving average parameter, q represents the number of moving average parameters, ε t ,ε t-1 ,,,ε t-q Represents the error term from time point t to time point tq. The value ranges of p and q are both smaller than the value at the current time point t.

[0037] The autoregressive parameters and moving average parameters set at this time can identify the currently set gas consumption curve and determine the maximum likelihood value of the current gas consumption curve to determine the change value that will occur in the current gas consumption curve within the expected time.

[0038] The processing method of the autoregressive moving average model also includes obtaining a likelihood function of the gas consumption curve based on the gas consumption curve output by the autoregressive moving average model, determining a maximum likelihood value of the output according to the obtained likelihood function, and determining a change trend of the current gas consumption curve according to the maximum likelihood value.

[0039] The likelihood function L is expressed as:

[0040] The obtained likelihood function is log-maximized.

[0041] Where L represents the likelihood function, ln(L) represents the logarithmic likelihood function, p represents the number of autoregressive parameters, q represents the number of moving average parameters, T represents the number of time points, σ ​​represents the standard deviation of the error term, π represents the circumference, e represents the exponential constant, and Y t represents the gas consumption at time point t, Represents the expected value of gas consumption, t=p+q+1,p+q+2,,,T.

[0042] When determining the maximum likelihood value, the autoregressive parameter, error term, moving average parameter and constant term are iterated until the value of the current gas consumption curve at the next time point can be calculated by the most similar value after these calculations, and the autoregressive parameter, error term, moving average parameter and constant term at this time are recorded as the change trend of the currently identified gas consumption curve.

[0043] The likelihood function obtained at this time can output the current change trend of the gas consumption curve, and predict the change of the corresponding gas consumption curve under different times and scheduling based on the obtained trend; the change trend output at this time can extract the corresponding influencing factors and related parameters when the gas consumption curve changes, so that the relevant data can be quantitatively analyzed based on these parameters separated in the trend.

[0044] In step S3, the gas consumption curve is analyzed to determine the main influencing factors of gas consumption, which includes: according to the changing trend of the gas consumption curve, the time when each changing trend occurs and the indicator value corresponding to the changing trend, the relevant factors of the current changing trend are screened out, and the relevant factors include seasonal factors, gas usage habits and gas pipeline network factors; the weight of each relevant factor in the current changing trend is determined in turn, and the data with the largest weight among seasonal factors, gas usage habits and gas pipeline network factors is taken as the main influencing factor of gas consumption.

[0045] For the weight of each relevant factor in the current changing trend, the weight of each relevant factor is determined by extracting the value of the corresponding trend quantity from the currently calculated changing trend and according to the type of the current trend quantity. The weight set at this time is obtained according to the pre-set value corresponding to the type of the current trend quantity to obtain the weight of each relevant factor.

[0046] like Figure 3 As shown, step S4 calculates the distribution of gas consumption at different locations based on the main influencing factors of gas consumption and the gas consumption curve, and the processing method for determining the gas scheduling plan also includes, S41, obtaining each pipeline node at each location, and determining the scheduling time and scheduling parameters during gas scheduling according to the location of each pipeline node and the main influencing factors.

[0047] S42, determining the throughput of each pipeline node during scheduling according to the scheduling time and scheduling parameters; and determining the current gas scheduling plan according to the throughput of each pipeline node.

[0048] The scheduling time indicates the time when the gas is scheduled, and the scheduling parameters include the pressure, flow and flow distribution ratio of the pipeline nodes during scheduling to determine the implementation method of the current scheduling.

[0049] For the amount of gas that can pass through each pipeline node, it is necessary to determine the scheduling parameters and the trend shown by the gas consumption curve to select the current scheduled amount, such as controlling the flow of each pipeline node during scheduling to determine the current scheduling plan.

[0050] For each pipeline node, a pressure sensor is used to measure each pipeline node to obtain the pressure of each pipeline node; the flow of each pipeline node can be determined by obtaining the flow between each pipeline node. For example, if there is a pipeline at one end, flowing from section 1 to section 2, the pressure, height, cross-sectional area, and gas density of sections 1 and 2 are obtained at this time, and the speed of gas flow is calculated by applying the Bernoulli equation. The flow rate of gas flowing in the current pipeline is obtained according to the product of the cross-sectional area and the speed. The parameters of the leakage alarm can identify whether there is a leakage risk in the current pipeline by obtaining the number and type of pipelines in historical alarms, so as to verify whether the current pipeline is stable during scheduling.

[0051] For the scheduling time, according to the main influencing factors corresponding to the gas consumption curve, the time point corresponding to the part with the largest value among the current main influencing factors is selected as the scheduling time. At this time, the processing of the main influencing factors also includes: determining the time when the scheduling time is affected by seasonal factors, gas usage habits and the main influencing factors corresponding to the gas pipeline network, determining the proportion value of each main influencing factor in turn, and adjusting the scheduling time proportionally according to the calculated proportion value.

[0052] Therefore, the method for processing the scheduling time is to obtain the impact value of seasonal factors, the impact value of gas usage habits and the impact value of the gas pipeline network in turn, and obtain the time that needs to be adjusted corresponding to the impact value of seasonal factors, the impact value of gas usage habits and the impact value of the gas pipeline network to obtain the adjustment time.

[0053] The seasonal factor impact value is expressed as: obtaining the current temperature and the reference temperature, determining the temperature change value of the gas caused by the season, and this value is the obtained seasonal factor impact value; the reference temperature set at this time represents the temperature of the gas during normal transportation. At this time, determining the difference between the reference temperature and the current temperature is to verify whether the gas has a temperature change during transportation. At the same time, the relevant temperature of the gas can be identified by setting a temperature sensor on the pipeline node.

[0054] Among them, S represents the seasonal factor impact value, Tem represents the current temperature, Tem0 represents the reference temperature, β S Indicates the seasonal factor.

[0055] The gas usage habit impact value is expressed as follows: the gas consumption in the current time period and the gas consumption in the reference time period are obtained to determine the gas usage habit impact value; the reference time period is represented as a preset time period under normal gas use, and this time period is used to differentiate the gas consumption in the form of time periods, and the gas consumption set in the reference time period is a verified normal consumption value, so that it can be identified whether the current gas consumption is excessive or insufficient.

[0056] Among them, U represents the impact value of gas usage habits, C represents the gas consumption in the current time period, C0 represents the gas consumption in the reference time period, β U Indicates the factors affecting gas usage habits.

[0057] The gas network impact value is expressed as obtaining the current network pressure and the target network pressure. The current network pressure here refers to the pressure of the network set in the corresponding area during gas scheduling, and the target network is the network that needs to be passed through during gas scheduling. At this time, determining the pressure of the passing network can determine the actual amount of gas that can flow during scheduling.

[0058] Among them, P represents the impact value of the gas pipeline network, P current Indicates the current network pressure, P target Indicates the target network pressure, β P Indicates the influencing factor of the gas pipeline network.

[0059] At this time, the calculated seasonal factor impact value, gas usage habit impact value and gas pipeline network impact value are all values ​​of the same dimension, and the corresponding values ​​are normalized to determine the proportion of each impact value in the overall impact value.

[0060] Therefore, the scheduling time is expressed as obtaining the adjustment time corresponding to the seasonal factor impact value, the gas usage habit impact value and the gas pipeline network impact value and the corresponding proportional values ​​of the seasonal factor, the gas usage habit and the gas pipeline network to obtain the scheduling time; for the method of obtaining the adjustment time corresponding to the seasonal factor impact value, the gas usage habit impact value and the gas pipeline network impact value, a time period corresponding to the current value is selected from the historical data, and the difference between this time period and the current set time is verified. The average value of these calculated differences is added to the normally set basic value to obtain the corresponding adjustment time.

[0061] D=WS ×D S +W U ×D U +W P ×D P ;That

[0062] In the above example, D represents the scheduling time, W represents the S Indicates the proportion value corresponding to the seasonal factor, W U Indicates the proportional value corresponding to gas usage habits, W P Indicates the proportional value corresponding to the gas network, D S Indicates the adjustment time of seasonal factor impact value, D U Indicates the time of adjustment corresponding to the impact value of gas usage habits, D P Indicates the time corresponding to the adjustment of the gas network impact value.

[0063] The processing method for the scheduling parameters is to obtain the position between each pipeline node, calculate the maximum allowable flow of each pipeline node, and determine the flow distribution ratio of each pipeline node during scheduling based on the maximum allowable flow of each pipeline node; according to the obtained flow distribution ratio, adjust the current pressure regulating valve opening, and determine whether the gas flow after adjusting the current pressure regulating valve opening meets the changing trend of the gas consumption curve, and use the relevant parameters that meet the changing trend of the gas consumption curve as the current scheduling parameters; the relevant parameters described at this time are expressed as the maximum allowable flow, flow distribution ratio and pressure regulating valve opening; at the same time, meeting the changing trend of the gas consumption curve is expressed as the current supply of each pipeline node meets the user set corresponding to each pipeline node, that is, the scenario where the supply and demand are balanced, and the parameters under this scenario are used as the required scheduling parameters.

[0064] For the maximum allowable flow rate, the capacity of the current pipeline is obtained by calculating the product of the cross-sectional area and the actual volume in the current pipeline node, and a flow meter is set in the current pipeline node to count the actual amount of gas passing through the current pipeline node at different times, and the maximum value of the actual amount of gas passing through the current pipeline node at different times is used as the maximum allowable flow rate of the current pipeline node; if the current pipeline is a newly established pipeline, the average value of the adjacent pipeline nodes connected to the current pipeline node is used as the maximum allowable flow rate of the current pipeline node.

[0065] For the flow distribution ratio, the proportion of the current pipeline node in the historical flow distribution is obtained to determine it. The flow distribution ratio is obtained by comparing the flow of the current pipeline node with the flow of the entire pipeline. At this time, the change value of the current pipeline node in the historical flow distribution is compared. If the change value of the flow distribution ratio in the current preset period exceeds the preset change value, the average value of the flow distribution ratio in the previous preset period will be used as the value of the current flow distribution ratio; if the change value of the flow distribution ratio in the current preset period is less than the preset change value, the median value of the current flow distribution ratio will be used as the value of the current flow distribution ratio.

[0066] The opening of the pressure regulating valve is expressed as the product of the difference between the current pipeline network pressure and the target pipeline network pressure and the pressure coefficient, that is, the pressure value most relevant to the current gas flow rate during gas scheduling is determined, and the opening of the pressure regulating valve is calculated; at this time, the processing method for the opening of the pressure regulating valve is to determine the pressure deviation between the current pipeline network pressure and the target pipeline network pressure, and determine the pressure deviation curve of the pressure deviation under the corresponding gas scheduling. If there are extreme points in the pressure deviation curve, the moving average of the extreme points of the pressure deviation curve is used as the current pressure deviation, and the current pipeline pressure is adjusted according to the current pressure deviation; if there are no extreme points in the pressure deviation curve, the average value of the pressure deviation curve is used as the current pressure deviation, and the current pipeline pressure is adjusted according to the current pressure deviation.

[0067] At this time, the maximum allowable flow rate, flow distribution ratio and pressure regulating valve opening are adjusted and selected. Under the condition of satisfying the gas supply and demand balance, the corresponding maximum allowable flow rate, flow distribution ratio and pressure regulating valve opening are used as output adjustment parameters.

[0068] At this time, according to the scheduling time and scheduling parameters, the method for determining the throughput of each pipeline node during scheduling is to obtain the overall required scheduling volume by calculating the product of the maximum allowable flow of the current pipeline node and the scheduling time, and obtain the throughput of each pipeline node according to the flow distribution ratio of each pipeline.

[0069] According to the throughput of each pipeline node, the current gas scheduling plan is determined by comparing the scheduling time and scheduling parameters of each pipeline node with the scheduling plan, and taking the scheduling plan with the greatest similarity to the current scheduling time and scheduling parameters as the current gas scheduling plan.

[0070] The processing method of the frequent scheduling area in step S5 includes clustering all the scheduling locations during gas scheduling to determine the frequent scheduling area. The clustering method used at this time is the K-means algorithm to determine the relevant clusters of all scheduling locations in terms of location, and the largest number of clusters are used as the currently identified frequent scheduling areas.

[0071] Adjusting the gas scheduling plan according to the characteristics of the frequent scheduling area is expressed as obtaining the layout relationship and layout method of each pipeline node. At this time, the layout relationship and layout method of each pipeline node are expressed as identifying the topological structure of the current pipeline node. For example, if the current pipeline node is in the form of a branch, ring, or grid, then the corresponding layout relationship and layout method indicate the shape in which the pipelines are combined.

[0072] According to the layout relationship and layout method of each pipeline node, determine the pressure stability analysis and capacity assessment analysis of each pipeline node, and obtain comprehensive analysis results based on the pressure stability analysis and capacity assessment analysis. Based on the obtained comprehensive analysis results, adjust the gas scheduling plan.

[0073] The pressure stability analysis is expressed as obtaining the length, diameter, friction coefficient and gas flow velocity of the pipeline node to obtain the pressure loss coefficient.

[0074] Where ΔP loss represents the pressure loss coefficient, f represents the friction coefficient, L represents the pipeline length, PD represents the pipeline diameter, v represents the gas flow velocity, and ρ represents the gas density.

[0075] The capacity assessment analysis is expressed as obtaining the maximum allowable flow and theoretical maximum flow of the current pipeline node, and determining the capacity factor. The capacity factor is expressed as the ratio of the maximum allowable flow and the theoretical maximum flow of the current pipeline node.

[0076] The calculation method for the comprehensive analysis results is to normalize the pressure loss coefficient and capacity factor and then take the weighted average to obtain the comprehensive analysis results.

[0077] Based on the comprehensive analysis results obtained, the processing method for adjusting the gas scheduling plan is to determine the operating status of the current pipeline node based on the comprehensive evaluation results obtained. At this time, the operating status of the pipeline node is expressed as related pressure loss and capacity evaluation to determine whether the pipeline node can operate stably. If the operating status of the current pipeline node is abnormal, the scheduling plan with the largest correlation coefficient with the abnormal operating status of the current pipeline node is obtained as the scheduling plan for adjusting the gas. If the operating status of the current pipeline node is normal, the scheduling plan with the greatest similarity to the indicator value of the comprehensive analysis result is used as the scheduling plan for adjusting the gas.

[0078] If the operating status identified at this time is normal, the pressure loss coefficient and capacity factor in the current comprehensive analysis results are selected, and the scheme with the highest similarity to the pressure loss coefficient and capacity factor of the current pipeline node is selected from the set scheduling scheme to adjust the current scheduling scheme. At the same time, the similarity calculated at this time is to compare the data corresponding to the pressure loss coefficient and capacity factor with the corresponding data in the set scheduling scheme to determine whether the data corresponding to the pressure loss coefficient and capacity factor are completely included in the set scheduling scheme, so as to make further adjustments to the current gas scheduling, so that the overall dynamic adjustment can be achieved, thereby improving the applicability of gas scheduling.

[0079] The operating status anomalies identified at this time include flow anomalies and pressure anomalies; flow anomalies are indicated by a sudden increase or decrease in the flow of a pipeline node, causing the flow of the pipeline node to exceed the normal range; pressure anomalies indicate that the pressure of some nodes in the pipeline node suddenly increases or decreases, causing the pressure of the corresponding pipeline node to exceed the normal range; the processing method for operating status anomalies is to determine the distance distribution of abnormal points where abnormalities occur in the current pipeline node and the number of occurrences of abnormal points, find at least one emergency processing point corresponding to the current abnormal point from the set scheduling plan, determine the location, scheduling time and scheduling parameters of the emergency processing point, and judge the changes in the amount of gas received by the corresponding user set after using the emergency processing point. If the emergency processing point is used, the adjusted scheduling time and scheduling parameters will be adjusted accordingly. When the correlation coefficient between the scheduling parameters and the original scheduling plan is greater than the preset correlation coefficient value, the scheduling plan corresponding to the emergency processing point will be used as the scheduling plan for adjusting the gas; at this time, the correlation coefficient is calculated by calculating the Pearson correlation coefficient between the adjusted scheduling time and the scheduling parameters and the parameters in the original scheduling plan to determine whether there is a linear correlation between the current parameters and the adjusted parameters. The correlation coefficient at this time ranges from 0 to 1, and the preset correlation coefficient value is set to 0.8, so as to select the scheduling plan that is most suitable for the current plan. If there are multiple scheduling plans with a value greater than the preset correlation coefficient, the scheduling plan with the largest correlation coefficient value is selected for adjustment. If there is no scheduling plan with a value greater than the preset correlation coefficient, the relevant pipeline nodes are closed and the corresponding situation is uploaded to the external terminal.

[0080] like Figure 4 As shown, the present invention also provides a gas transmission intelligent scheduling system based on the Internet of Things, including: a gas consumption data acquisition module, a gas consumption curve drawing module, a gas consumption analysis module, a gas scheduling calculation module, and a gas scheduling adjustment module.

[0081] Gas consumption data collection module: used to collect users' gas consumption data in real time through IoT devices, and associate the data with users' location information to form a structured data set.

[0082] Gas consumption curve drawing module: used to process the structured data set using the autoregressive moving average model, output the gas consumption curve, and determine the change trend of the gas consumption curve through the maximum likelihood estimation method.

[0083] Gas consumption analysis module: used to identify seasonal factors, gas usage habits and gas pipeline network factors among the main factors affecting gas consumption by screening the changing trend of the gas consumption curve.

[0084] Gas scheduling calculation module: used to calculate the distribution of gas consumption in different locations and determine the gas scheduling plan based on the main influencing factors of gas consumption and the gas consumption curve.

[0085] Gas scheduling adjustment module: used to obtain the relationship between gas scheduling and location according to the gas scheduling plan, identify the frequent scheduling areas, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling areas.

[0086] In summary, the system realizes intelligent scheduling of gas transportation by integrating multiple functional modules.

[0087] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. A gas transmission intelligent scheduling method based on the Internet of Things, characterized in that: include: S1, when obtaining gas scheduling, the user set corresponding to the gas scheduling is determined, and the gas consumption in the user set is determined; S2, identify the changes in gas consumption of user sets at different timelines and locations, and draw a gas consumption curve that changes over time; S3, analyzing the gas consumption curve and determining the main factors affecting the gas consumption; S4, according to the main influencing factors of gas consumption and the gas consumption curve, calculate the distribution of gas consumption at different locations and determine the gas scheduling plan; S5, according to the gas scheduling plan, obtain the relationship between gas scheduling and location, identify the frequent scheduling area, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling area.

2. According to the method of intelligent scheduling of gas transportation based on the Internet of Things in claim 1, it is characterized in that: Step S2 includes the following implementations: S21, obtaining the gas consumption of the user set at each time point and the user's geographical location information, and arranging the collected data according to the timeline and location to obtain a structured data set; S22, according to the structured data set, a gas consumption curve is drawn according to a preset period, and a change trend of the gas consumption curve is determined.

3. According to claim 2, a method for intelligent dispatching of gas transportation based on the Internet of Things is characterized in that: The method of drawing the gas consumption curve is to input the structured data set into the autoregressive moving average model, and the autoregressive moving average model outputs the gas consumption curve. The gas consumption curve is expressed as: Y t =c+φ1Y t-1 +φ2Y t-2 +,,,+f p Y t-p +θ1ε t-1 +θ2ε t-2 +,,,+θ q e t-q +e t ; Among them, Y t ,Y t-1 ,,,Y t-p represents the gas consumption from time point t to time point tp, c represents the constant term, φ1, φ2,,, φ p represents the autoregressive parameter, p represents the number of autoregressive parameters, θ1,θ2,,,θ q represents the moving average parameter, q represents the number of moving average parameters, ε t ,ε t-1 ,,,ε t-q Represents the error term from time point t to time point tq.

4. According to claim 3, a method for intelligent dispatching of gas transportation based on the Internet of Things is characterized in that: The processing method of the autoregressive moving average model also includes obtaining a likelihood function of the gas consumption curve based on the gas consumption curve output by the autoregressive moving average model, determining a maximum likelihood value of the output according to the obtained likelihood function, and determining a change trend of the current gas consumption curve according to the maximum likelihood value; The likelihood function L is expressed as: The obtained likelihood function is logarithmized; Where L represents the likelihood function, ln(L) represents the logarithmic likelihood function, p represents the number of autoregressive parameters, q represents the number of moving average parameters, T represents the number of time points, σ ​​represents the standard deviation of the error term, π represents the circumference, e represents the exponential constant, and Y t represents the gas consumption at time point t, Represents the expected value of gas consumption, t=p+q+1,p+q+2,,,T.

5. The method for intelligent dispatching of gas transportation based on the Internet of Things according to claim 1 is characterized in that: In step S3, the gas consumption curve is analyzed to determine the main factors affecting the gas consumption, including: According to the changing trend of the gas consumption curve and the time of occurrence of each changing trend and the indicator value corresponding to the changing trend, the relevant factors of the current changing trend are screened out, and the relevant factors include seasonal factors, gas usage habits and gas pipeline network factors; the weight of each relevant factor in the current changing trend is determined in turn, and the data with the largest weight among seasonal factors, gas usage habits and gas pipeline network factors is taken as the main influencing factor of gas consumption.

6. The method for intelligent dispatching of gas transportation based on the Internet of Things according to claim 5 is characterized in that: The processing method of step S4 also includes: S41, obtaining each pipeline node at each position, and determining the scheduling time and scheduling parameters for gas scheduling according to the position of each pipeline node and the main influencing factors; S42, determining the throughput of each pipeline node during scheduling according to the scheduling time and scheduling parameters; and determining the current gas scheduling plan according to the throughput of each pipeline node.

7. The method for intelligent dispatching of gas transportation based on the Internet of Things according to claim 6 is characterized in that: The method for processing the scheduling time is to obtain the impact value of seasonal factors, the impact value of gas usage habits and the impact value of the gas pipeline network in turn, and obtain the time that needs to be adjusted corresponding to the impact value of seasonal factors, the impact value of gas usage habits and the impact value of the gas pipeline network to obtain the adjustment time.

8. The method for intelligent dispatching of gas transportation based on the Internet of Things according to claim 6 is characterized in that: The processing method for scheduling parameters is to obtain the position between each pipeline node, calculate the maximum allowable flow of each pipeline node, and determine the flow distribution ratio of each pipeline node during scheduling according to the maximum allowable flow of each pipeline node; According to the obtained flow distribution ratio, the current pressure regulating valve opening is adjusted, and it is determined whether the gas flow after adjusting the current pressure regulating valve opening meets the changing trend of the gas consumption curve, and the relevant parameters that meet the changing trend of the gas consumption curve are used as the current scheduling parameters; According to the scheduling time and scheduling parameters, the method of determining the throughput of each pipeline node during scheduling is to obtain the overall required scheduling volume by calculating the product of the maximum allowable flow of the current pipeline node and the scheduling time, and to obtain the throughput of each pipeline node according to the flow distribution ratio of each pipeline; According to the throughput of each pipeline node, the current gas scheduling plan is determined by comparing the scheduling time and scheduling parameters of each pipeline node with the scheduling plan, and taking the scheduling plan with the greatest similarity to the current scheduling time and scheduling parameters as the current gas scheduling plan.

9. The method for intelligent dispatching of gas transportation based on the Internet of Things according to claim 1 is characterized in that: Adjusting the gas dispatching scheme according to the characteristics of the frequently dispatched area in step S5 further includes: obtaining the layout relationship and layout mode of each pipeline node, determining the pressure stability analysis and capacity evaluation analysis of each pipeline node according to the layout relationship and layout mode of each pipeline node, obtaining a comprehensive analysis result according to the pressure stability analysis and capacity evaluation analysis, and adjusting the gas dispatching scheme based on the obtained comprehensive analysis result; Based on the comprehensive analysis results obtained, the processing method for adjusting the gas scheduling plan is to determine the operating status of the current pipeline node based on the comprehensive evaluation results obtained. If the operating status of the current pipeline node is abnormal, the scheduling plan with the largest correlation coefficient with the abnormal operating status of the current pipeline node is obtained as the scheduling plan for adjusting the gas. If the operating status of the current pipeline node is normal, the scheduling plan with the greatest similarity to the indicator value of the comprehensive analysis result is used as the scheduling plan for adjusting the gas.

10. A gas transmission intelligent dispatching system based on the Internet of Things, using the gas transmission intelligent dispatching method based on the Internet of Things as claimed in claim 1, characterized in that: include: Gas consumption data collection module: used to collect users' gas consumption data in real time through IoT devices, and associate the data with users' location information to form a structured data set; Gas consumption curve drawing module: used to process the structured data set using the autoregressive moving average model, output the gas consumption curve, and determine the change trend of the gas consumption curve through the maximum likelihood estimation method; Gas consumption analysis module: used to identify seasonal factors, gas usage habits and gas pipeline network factors among the main factors affecting gas consumption by screening the changing trend of the gas consumption curve; Gas scheduling calculation module: used to calculate the distribution of gas consumption at different locations and determine the gas scheduling plan based on the main influencing factors of gas consumption and the gas consumption curve; Gas scheduling adjustment module: used to obtain the relationship between gas scheduling and location according to the gas scheduling plan, identify the frequent scheduling areas, and adjust the gas scheduling plan according to the characteristics of the frequent scheduling areas.

Images