Method and system for predicting load of urban gas system in heating season

Abstract

The invention discloses a heating season city gas system load prediction method and system, and relates to the technical field of gas system load prediction, and the method comprises the following steps: collecting the related original data of a heating season city gas system, the original data comprises historical data and real-time data, and carrying out the preprocessing of the collected original data, and obtaining a gas load analysis set and a demand variable of gas load analysis. According to the method, the gas consumption, the meteorological data, the demographic data and the gas price data are comprehensively analyzed, the gas load prediction model is constructed, the accuracy of gas load prediction is remarkably improved, and by analyzing historical extreme weather events, calculating the extreme weather influence index and evaluating possible risks, the gas load prediction accuracy is improved. And the risk level is quantified by combining the gas load evaluation index and the risk early warning coefficient, the early warning level is dynamically adjusted according to real-time data, prevention measures are taken in time, and the influence of extreme weather events on gas supply is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of gas system load prediction, and in particular to a method and system for predicting the load of a city gas system in a heating season. Background Art

[0002] With the substantial increase in urbanization levels, the demand for urban gas, as an important energy source, has increased significantly. During the heating season, especially in the northern region, due to the drop in temperature, the heating demand of residents and enterprises has increased sharply, resulting in a significant increase in the load of the urban gas system. In order to ensure a stable supply of gas during the heating season, it is necessary to accurately analyze the load of the gas system in order to rationally allocate resources and avoid an imbalance between supply and demand.

[0003] Gas consumption during the heating season is affected by multiple factors. Due to geographical location and climate characteristics, different cities have significant differences in gas demand in autumn and winter, especially when encountering extreme weather such as cold waves, the fluctuation of demand is particularly obvious. Differences in economic development level, population density and building insulation performance in various cities make gas companies face great challenges in procurement and supply planning. Accurately predicting the gas load during the heating season will not only help ensure the stability of gas supply, but also optimize resource allocation and reduce operating costs.

[0004] In addition, gas users also have diverse usage patterns. There are significant differences in gas usage and usage habits between household users and commercial users (such as the catering industry). Household users usually use gas for daily cooking and heating, while commercial users use more and more volatile amounts. The existing management methods are difficult to meet the personalized needs of different users, which not only limits users' understanding of gas consumption, but also affects the ability of gas companies to formulate precise marketing strategies.

[0005] In the prior art, the load of the gas system is affected by many factors such as calendar time and population density, which makes the load forecasting of urban gas in the heating season more difficult and prone to deviations. In extreme weather conditions, the forecast results will have greater risks and uncertainties. Therefore, how to improve the accuracy of the load forecasting of urban gas in the heating season and strengthen risk management and response measures is the problem we need to solve. To this end, a method and system for forecasting the load of urban gas in the heating season are proposed. Summary of the invention

[0006] The object of the present invention is to provide a method and system for predicting the load of a city gas system in the heating season, so as to solve the problems raised in the above-mentioned background technology.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0008] In a first aspect, a method for predicting load of a city gas system in a heating season comprises the following steps:

[0009] Step 1: collect relevant raw data of the city gas system in the heating season, wherein the raw data includes historical data and real-time data, and pre-process the collected raw data to obtain a gas load analysis set and demand variables for gas load analysis;

[0010] Step 2: Combine the gas load analysis set and the demand characteristics of the gas load analysis to build a gas load forecasting model, establish a gas load evaluation index, and perform load forecasting;

[0011] Step 3: Based on the real-time data of the urban gas system during the heating season and in combination with the regional historical meteorological database, analyze the risks and impacts of historical extreme weather, establish a risk assessment model, and combine it with the gas load assessment index to obtain the risk warning coefficient, conduct a quantitative assessment of the risk, and determine the impact of extreme weather on the gas load forecast;

[0012] Step 4: Analyze the risk warning coefficient and risk quantification assessment results, comprehensively predict the load of the urban gas system during the heating season, conduct early warning and monitoring of the urban gas system during the heating season, and formulate targeted emergency plans and response measures.

[0013] A further improvement of the technical solution of the present invention is that in step 1, the process of obtaining the gas load analysis set and the demand variables of the gas load analysis is as follows:

[0014] Step 101, collecting historical and real-time raw data related to the city gas system during the heating season, including gas usage data, meteorological data, calendar data, demographic data, and gas price data;

[0015] Step 102, obtaining gas usage data during the historical heating season from the database, including weekly and monthly gas consumption data, and obtaining current gas consumption data for analysis and prediction, extracting historical meteorological data from the regional historical meteorological database, including temperature, humidity, wind speed, rainfall, sunshine duration, and collecting current meteorological data, collecting demographic data on the total population and population density of the region, and collecting historical data and current prices of gas prices;

[0016] Step 103, pre-processing operations such as data cleaning, data conversion and data integration are performed on the raw data, outliers in the data are checked and removed, the data is converted into a time series format to facilitate the analysis of time trends and seasonal patterns, and the data collected from different sources are aligned and integrated according to timestamps to establish a gas load analysis set;

[0017] Step 104, determining demand variables for gas load analysis in the gas load analysis set, and classifying and marking the demand variables, wherein the demand variables include multiple variables such as gas usage, weather, population, and gas price.

[0018] A further improvement of the technical solution of the present invention is that in step 2, the process of obtaining the gas load evaluation index is:

[0019] Step 201, performing data analysis on the gas load analysis set, extracting features from gas usage, meteorological data, demographic data and gas price data to obtain a feature data set, and dividing the feature data set into a training set and a test set;

[0020] Step 202, select a neural network model, use the historical data of the training set to train the model, build a gas load prediction model, and use the relevant data of the test set to test and evaluate the gas load prediction model;

[0021] Step 203, use the trained gas load prediction model to predict the gas load, and combine with real-time data to analyze the deviation rate, change rate and stability of the gas load, establish a gas load evaluation index, evaluate the fluctuation of the gas load, and then analyze the change trend of the gas load.

[0022] A further improvement of the technical solution of the present invention is that the calculation formula of the gas load evaluation index is:

[0023]

[0024] M i =w1·(T i -T base )+w2·H i +w3·W i +w4·RH i ;

[0025]

[0026] Among them, GI is the gas load assessment index, G i is the gas usage on the i-th day, M i is the meteorological impact factor, n is the number of days in the evaluation period, T max and T min are the highest and lowest temperatures during the evaluation period, respectively, and D p is the demographic data during the evaluation period, P is the average population threshold for regional gas use, R is the average gas price during the evaluation period, and T i is the average temperature of the i-th day, T base is the preset reference temperature, which is used to calculate the degree of temperature deviation from the reference. iis the sunshine duration of the i-th day, W i is the wind speed on the i-th day, RH i is the relative humidity of the i-th day, (w1, w2, w3, w4) are the weight coefficients of temperature, sunshine, wind speed and relative humidity respectively, D p，j is the demographic data of the jth region, U j is the unit amount of gas used in the jth region, and m is the total number of regions.

[0027] A further improvement of the technical solution of the present invention is that in step 3, the process of obtaining the risk warning coefficient is:

[0028] Step 301, extracting historical meteorological data from a regional historical meteorological database, extracting records of extreme weather events, including occurrence time, duration, impact range, and intensity, where extreme weather refers to severe weather such as cold waves, blizzards, and strong winds;

[0029] Step 302, analyzing historical heating season gas load data and historical meteorological data, determining the main extreme weather types that affect the gas load, identifying past extreme weather events and their historical impact on the gas load, determining the impact value of extreme weather based on the severity and frequency of extreme weather events, analyzing the impact values ​​of all extreme weather conditions, and obtaining an extreme weather impact index;

[0030] Step 303, using historical meteorological data, gas load data and extreme weather risk assessment index as input variables, building a risk assessment model, establishing a correlation between extreme weather and gas load, combining the gas load assessment index and the risk assessment model, defining a risk warning coefficient, and quantifying the risk level;

[0031] Step 304, dividing different load warning levels based on the risk warning coefficient into low load warning level, medium load warning level and high load warning level, and setting corresponding warning thresholds for the load warning levels;

[0032] Step 305: When the risk warning coefficient exceeds the preset warning threshold, the corresponding load warning level is output and the corresponding risk warning mechanism is triggered.

[0033] A further improvement of the technical solution of the present invention is that the calculation formula of the risk warning coefficient is:

[0034]

[0035] Among them, RAC is the risk warning coefficient, which is used to quantify the risk level of gas load, GI is the current gas load assessment index, which reflects the comprehensive status of the current gas load, and baseis the baseline gas load assessment index, selecting the GI value under normal conditions, and E is the extreme weather impact index, which measures the potential impact of extreme weather on gas load. max is the maximum value of the historical extreme weather impact index, T d The current temperature deviates from the base temperature, which is a long-term average. d，max is the maximum degree of temperature deviation from the base temperature in history, w j is the weight of the extreme weather event, k is the total number of extreme weather event types, e j is the impact value of the jth extreme weather event, G ev is the actual gas usage during the extreme weather event, G ep is the expected gas usage in the absence of extreme weather events.

[0036] A further improvement of the technical solution of the present invention is that: a plurality of the load warning levels correspond to a plurality of the warning thresholds, wherein the warning thresholds include an upper threshold and a lower threshold;

[0037] The multiple load warning levels and the multiple warning thresholds satisfy the following relationship:

[0038] Low load warning level RAC <RAC l ; Indicates that the current gas system load is at a normal or low level, the risk is small, and no immediate action is required, but attention should be paid;

[0039] Medium load warning level RAC l ≤RAC <RAC h ; It means that the load of the gas system begins to rise, approaching or exceeding the historical average level. There are certain risks, which require close attention and preparation of countermeasures;

[0040] High load warning level RAC ≥ RAC h ; Indicates that the gas system is under high load and the risk is extremely high, and immediate action is required to ensure system stability and safety;

[0041] Among them, RAC is the risk warning coefficient, RAC l is the lower threshold corresponding to the medium load warning level and the upper threshold corresponding to the low load warning level, RAC h It is the lower threshold corresponding to the high load warning level and the upper threshold corresponding to the medium load warning level.

[0042] A further improvement of the technical solution of the present invention is that in step 4, the early warning and monitoring process of the city gas system in the heating season is:

[0043] Step 401, comprehensively analyzing the impact of historical extreme weather events, current meteorological conditions and changes in gas load, predicting the overall trend of gas load in the heating season, and determining the risk level faced by the gas system in the current heating season;

[0044] Step 402, based on historical data and current weather forecasts, predict the load demand of the city gas system in the future heating season, analyze the prediction results, identify the peak period, valley period and potential fluctuation range of the gas load in the heating season, and draw a predicted gas load demand curve;

[0045] Step 403, continuously monitor the deviation between the actual gas load and the predicted load, and monitor the changes in the current meteorological conditions and the risk warning coefficient. According to the warning and monitoring results, formulate corresponding emergency plans and response measures for the risks and load pressures of different load warning levels. Low load warning requires supply chain optimization and resource allocation, and high load warning requires the activation of backup supply, adjustment of gas production or the introduction of temporary measures.

[0046] In a second aspect, a heating season city gas system load prediction system is used to implement a heating season city gas system load prediction method, including a gas load supervision center, wherein the gas load supervision center is communicatively connected to a data acquisition and processing module, a prediction model building module, an extreme weather analysis module, a risk assessment and early warning module, an emergency plan response module, and a monitoring feedback module, wherein electrical signals are connected between the modules;

[0047] The data acquisition and processing module is used to collect data related to the gas system load from multiple data sources, including gas load data, meteorological data, demographic data and gas price data, and pre-process the collected data to ensure the accuracy and consistency of the data;

[0048] The forecast model building module builds a forecast model based on historical data and current conditions to forecast the city gas load demand in the future heating season, provides a forecast load curve, helps plan and adjust gas supply, optimizes supply chain management and resource allocation to cope with different load conditions;

[0049] The extreme weather analysis module identifies extreme weather events from meteorological data based on a preset extreme weather definition, and records their occurrence time, duration, impact range, and intensity information, analyzes the historical impact of extreme weather events on gas load, determines the main extreme weather types that affect gas load, and calculates the impact value of extreme weather;

[0050] The risk assessment and early warning module is used to combine the extreme weather impact and load forecast results to build a risk assessment model, calculate the risk early warning coefficient and quantify the risk assessment results, assess the risk level faced by the gas system during the heating season, provide risk assessment reports and early warning information, and support decision makers in formulating emergency plans and response strategies to deal with possible extreme weather events and load fluctuations;

[0051] The emergency plan response module is used to formulate corresponding emergency plans for different load warning levels, including emergency response processes, resource allocation plans, and personnel responsibilities. When the warning signal is triggered, the emergency plan is quickly activated and corresponding response measures are implemented to ensure the stable and safe operation of the gas system;

[0052] The monitoring feedback module is used to monitor the operating status, load conditions and external environmental changes of the gas system in real time to ensure the timeliness and accuracy of the data. According to the real-time monitoring results and the implementation of the emergency plan, the system is adjusted for feedback, the prediction model, risk assessment model and emergency plan are optimized, and the overall performance and response capabilities of the system are improved.

[0053] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0054] 1. The present invention provides a method and system for predicting the load of a city gas system in the heating season. By comprehensively analyzing gas usage, meteorological data, demographic data and gas price data, a gas load prediction model is constructed, which significantly improves the accuracy of gas load prediction. By analyzing historical extreme weather events, the extreme weather impact index is calculated, and possible risks are evaluated. Then, the gas load evaluation index and the risk warning coefficient are combined to quantify the risk level, and the warning level is dynamically adjusted according to real-time data. Precautions are taken in a timely manner to reduce the impact of extreme weather events on gas supply.

[0055] 2. The present invention provides a method and system for predicting the load of a city gas system during the heating season, establishes a dynamic risk warning and graded response mechanism, automatically divides the load warning level according to the risk warning coefficient, and triggers corresponding warning signals and emergency plans. By setting three warning levels of low, medium and high and corresponding thresholds, accurate classification and differentiated response of risks can be achieved, potential risks can be discovered in advance, and time can be gained for emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0057] Figure 1 is a flow chart of the method of the present invention;

[0058] Figure 2 A flow chart for obtaining a gas load evaluation index according to the present invention;

[0059] Figure 3 This is a flow chart for obtaining the risk warning coefficient of the present invention;

[0060] Figure 4 It is a module diagram of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Embodiment 1, as Figure 1-3 As shown, the present invention provides a method for predicting the load of a city gas system in a heating season, comprising the following steps:

[0063] Step 1: Collect the relevant raw data of the urban gas system in the heating season, where the raw data includes historical data and real-time data, and pre-process the collected raw data to obtain the gas load analysis set and the demand variables of the gas load analysis. Collect the relevant raw data of the urban gas system in the historical and real-time heating season, including gas usage data, meteorological data, calendar data, demographic data and gas price data. Obtain the gas usage data during the historical heating season from the database, including weekly and monthly gas consumption data, and obtain the current gas consumption data for analysis and prediction. Extract historical meteorological data from the regional historical meteorological database, including temperature, humidity, Wind speed, rainfall, sunshine duration, and current meteorological data; demographic data on the total population and population density of the region; historical and current gas price data; pre-processing operations such as data cleaning, data conversion, and data integration on the raw data; check and remove outliers in the data; convert the data into a time series format to facilitate the analysis of time trends and seasonal patterns; align and integrate data collected from different sources by timestamp; establish a gas load analysis set; determine the demand variables for gas load analysis in the gas load analysis set; and classify and label the demand variables, which include multiple variables such as gas use, meteorology, population, and gas prices;

[0064] Step 2: Combine the gas load analysis set and the demand characteristics of the gas load analysis to build a gas load prediction model, establish a gas load evaluation index, perform load prediction, perform data analysis on the gas load analysis set, extract features from gas usage, meteorological data, demographic data, and gas price data to obtain a feature data set, divide the feature data set into a training set and a test set, select a neural network model, and use the historical data of the training set to train the model, build a gas load prediction model, use the relevant data of the test set to test and evaluate the gas load prediction model, use the trained gas load prediction model to predict the gas load, and combine the real-time data to analyze the deviation rate, change rate, and stability of the gas load, establish a gas load evaluation index, evaluate the fluctuation of the gas load, and then analyze the change trend of the gas load;

[0065] Furthermore, the calculation formula of the gas load assessment index is:

[0066]

[0067] M i =w1·(T i -T base )+w2·H i +w3·W i +w4·RH i ;

[0068]

[0069] Among them, GI is the gas load assessment index, G i is the gas usage on the i-th day, M i is the meteorological impact factor, n is the number of days in the evaluation period, T max and T min are the highest and lowest temperatures during the evaluation period, respectively, and D p is the demographic data during the evaluation period, P is the average population threshold for regional gas use, R is the average gas price during the evaluation period, and T i is the average temperature of the i-th day, T base is the preset reference temperature, which is used to calculate the degree of temperature deviation from the reference. i is the sunshine duration of the i-th day, W i is the wind speed on the i-th day, RH i is the relative humidity of the i-th day, (w1, w2, w3, w4) are the weight coefficients of temperature, sunshine, wind speed and relative humidity respectively, D p，j is the demographic data of the jth region, U jis the unit gas usage of the jth region, m is the total number of regions. It should be noted that the value of P reflects the average gas usage per capita after the gas usage in different regions. i The value of changes with meteorological conditions. Different combinations of temperature, sunshine, wind speed and relative humidity will have different effects on gas usage. The greater the temperature deviates from the reference temperature, the greater the impact factor M. i The larger the value, the more significant the impact of meteorological conditions on gas demand. When gas usage increases, GI rises. Extreme changes in temperature can cause changes in GI. Population growth or density increases can cause GI to rise without a corresponding decrease in gas usage. A decrease in gas prices can increase GI, and lower prices can increase gas usage.

[0070] Step 3: Based on the real-time data of the urban gas system during the heating season and in combination with the regional historical meteorological database, analyze the risks and impacts of historical extreme weather, establish a risk assessment model, and combine it with the gas load assessment index to obtain the risk warning coefficient, conduct a quantitative assessment of the risk, and judge the impact of extreme weather on the gas load forecast. Extract historical meteorological data from the regional historical meteorological database and extract records of extreme weather time, including the time of occurrence, duration, impact range, and intensity. Extreme weather refers to severe weather such as cold waves, blizzards, and strong winds. Analyze the historical heating season gas load data and historical meteorological data, determine the main extreme weather types that affect the gas load, identify past extreme weather events and their historical impact on the gas load, and based on extreme weather events The severity and frequency determine the impact value of extreme weather, analyze the impact values ​​of all extreme weather conditions, and obtain the extreme weather impact index. The historical meteorological data, gas load data, and extreme weather risk assessment index are used as input variables. By building a risk assessment model, the correlation between extreme weather and gas load is established. The risk warning coefficient is defined in combination with the gas load assessment index and the risk assessment model, and the risk level is quantified. Different load warning levels are divided based on the risk warning coefficient, namely low load warning level, medium load warning level, and high load warning level, and corresponding warning thresholds are set for the load warning levels. When the risk warning coefficient exceeds the preset warning threshold, the corresponding load warning level is output and the corresponding risk warning mechanism is triggered;

[0071] Furthermore, the calculation formula of the risk warning coefficient is:

[0072]

[0073] Among them, RAC is the risk warning coefficient, which is used to quantify the risk level of gas load, GI is the current gas load assessment index, which reflects the comprehensive status of the current gas load, and baseis the baseline gas load assessment index, selecting the GI value under normal conditions, and E is the extreme weather impact index, which measures the potential impact of extreme weather on gas load. max is the maximum value of the historical extreme weather impact index, T d The current temperature deviates from the base temperature, which is a long-term average. d，max is the maximum degree of temperature deviation from the base temperature in history, w j is the weight of the extreme weather event, k is the total number of extreme weather event types, e j is the impact value of the jth extreme weather event, G ev is the actual gas usage during the extreme weather event, G ep It is the expected gas consumption in the absence of extreme weather events. It should be noted that the larger the value of E, the more severe the impact of extreme weather events. The value trend of E is proportional to the severity and frequency of extreme weather events. The larger the value of E, the greater the potential impact of extreme weather events on gas load. With climate change and the increase of extreme weather events, E shows an upward trend. When GI increases or E increases, RAC increases, indicating an increase in the risk level.

[0074] Furthermore, the multiple load warning levels correspond to multiple warning thresholds, wherein the warning threshold includes an upper threshold and a lower threshold;

[0075] Multiple load warning levels and multiple warning thresholds satisfy the following relationship:

[0076] Low load warning level RAC <RAC l ; Indicates that the current gas system load is at a normal or low level, the risk is small, and no immediate action is required, but attention should be paid;

[0077] Medium load warning level RAC l ≤RAC <RAC h ; It means that the load of the gas system begins to rise, approaching or exceeding the historical average level. There are certain risks, which require close attention and preparation of countermeasures;

[0078] High load warning level RAC ≥ RAC h ; Indicates that the gas system is under high load and the risk is extremely high, and immediate action is required to ensure system stability and safety;

[0079] Among them, RAC is the risk warning coefficient, RAC l is the lower threshold corresponding to the medium load warning level and the upper threshold corresponding to the low load warning level, RAC h The lower threshold corresponding to the high load warning level and the upper threshold corresponding to the medium load warning level;

[0080] Step 4: Analyze the risk warning coefficient and risk quantification assessment results, comprehensively predict the load of the urban gas system in the heating season, conduct early warning and monitoring of the urban gas system in the heating season, formulate targeted emergency plans and response measures, comprehensively analyze the impact of historical extreme weather events, current meteorological conditions and changes in gas load, predict the overall trend of gas load in the heating season, judge the risk level faced by the gas system in the current heating season, predict the load demand of the urban gas system in the future heating season based on historical data and current meteorological forecasts, analyze the forecast results, identify the peak period, trough period and potential fluctuation range of gas load in the heating season, and draw the predicted gas load demand curve, continuously monitor the deviation between the actual gas load and the predicted load, and monitor the changes in current meteorological conditions and risk warning coefficients. According to the warning and monitoring results, formulate corresponding emergency plans and response measures for the risks and load pressures of different load warning levels. Low load warning requires supply chain optimization and resource allocation, and high load warning requires the activation of backup supply, adjustment of gas production or introduction of temporary measures.

[0081] Embodiment 2, as Figure 4 As shown, on the basis of Example 1, the present invention further provides a heating season city gas system load prediction system, which is used to implement a heating season city gas system load prediction method, including a gas load supervision center, wherein the gas load supervision center is communicatively connected with a data acquisition and processing module, a prediction model building module, an extreme weather analysis module, a risk assessment and early warning module, an emergency plan response module, and a monitoring feedback module, wherein electrical signals are connected between the modules;

[0082] The data acquisition and processing module is used to collect data related to the gas system load from multiple data sources, including gas load data, meteorological data, demographic data and gas price data, and pre-process the collected data to ensure the accuracy and consistency of the data;

[0083] The forecast model building module builds a forecast model based on historical data and current conditions to forecast the city gas load demand in the future heating season, provides a forecast load curve, helps plan and adjust gas supply, optimizes supply chain management and resource allocation to cope with different load conditions;

[0084] The extreme weather analysis module identifies extreme weather events from meteorological data based on a preset extreme weather definition, and records their occurrence time, duration, impact range, and intensity information, analyzes the historical impact of extreme weather events on gas load, determines the main extreme weather types that affect gas load, and calculates the impact value of extreme weather;

[0085] The risk assessment and early warning module is used to combine the extreme weather impact and load forecast results to build a risk assessment model, calculate the risk early warning coefficient and quantify the risk assessment results, assess the risk level faced by the gas system during the heating season, provide risk assessment reports and early warning information, and support decision makers in formulating emergency plans and response strategies to deal with possible extreme weather events and load fluctuations;

[0086] The emergency plan response module is used to formulate corresponding emergency plans for different load warning levels, including emergency response processes, resource allocation plans, and personnel responsibilities. When the warning signal is triggered, the emergency plan is quickly activated and corresponding response measures are implemented to ensure the stable and safe operation of the gas system;

[0087] The monitoring feedback module is used to monitor the operating status, load conditions and external environmental changes of the gas system in real time to ensure the timeliness and accuracy of the data. According to the real-time monitoring results and the implementation of the emergency plan, the system is adjusted for feedback, the prediction model, risk assessment model and emergency plan are optimized, and the overall performance and response capabilities of the system are improved.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting the load of a city gas system in the heating season, characterized in that: The following steps are involved: Step 1: collect relevant raw data of the city gas system in the heating season, wherein the raw data includes historical data and real-time data, and pre-process the collected raw data to obtain a gas load analysis set and demand variables for gas load analysis; Step 2: Combine the gas load analysis set and the demand characteristics of the gas load analysis to build a gas load forecasting model, establish a gas load evaluation index, and perform load forecasting; Step 3: Based on the real-time data of the urban gas system during the heating season and in combination with the regional historical meteorological database, analyze the risks and impacts of historical extreme weather, establish a risk assessment model, and combine it with the gas load assessment index to obtain the risk warning coefficient, conduct a quantitative assessment of the risk, and determine the impact of extreme weather on the gas load forecast; Step 4: Analyze the risk warning coefficient and risk quantification assessment results, comprehensively predict the load of the urban gas system during the heating season, conduct early warning and monitoring of the urban gas system during the heating season, and formulate targeted emergency plans and response measures.

2. A method for predicting urban gas system load in heating season according to claim 1, characterized in that: In step 1, the process of obtaining the gas load analysis set and the demand variables of the gas load analysis is as follows: Step 101, collecting historical and real-time raw data related to the city gas system during the heating season, including gas usage data, meteorological data, calendar data, demographic data, and gas price data; Step 102, obtaining gas usage data during the historical heating season from the database, including weekly and monthly gas consumption data, and obtaining current gas consumption data, extracting historical meteorological data from the regional historical meteorological database, including temperature, humidity, wind speed, rainfall, sunshine duration, and collecting current meteorological data, collecting demographic data on the total population and population density of the region, and collecting historical data and current prices of gas prices; Step 103, performing pre-processing operations of data cleaning, data conversion and data integration on the original data, and aligning and integrating the data collected from different sources according to timestamps to establish a gas load analysis set; Step 104, determining demand variables for gas load analysis in the gas load analysis set, and classifying and marking the demand variables, wherein the demand variables include multiple variables such as gas usage, weather, population, and gas price.

3. A method for predicting urban gas system load in heating season according to claim 2, characterized in that: In step 2, the process of obtaining the gas load evaluation index is as follows: Step 201, performing data analysis on the gas load analysis set, extracting features from gas usage, meteorological data, demographic data and gas price data to obtain a feature data set, and dividing the feature data set into a training set and a test set; Step 202, select a neural network model, use the historical data of the training set to train the model, build a gas load prediction model, and use the relevant data of the test set to test and evaluate the gas load prediction model; Step 203, use the trained gas load prediction model to predict the gas load, and combine with real-time data to analyze the deviation rate, change rate and stability of the gas load, establish a gas load evaluation index, evaluate the fluctuation of the gas load, and then analyze the change trend of the gas load.

4. A method for predicting urban gas system load in heating season according to claim 3, characterized in that: The calculation formula of the gas load assessment index is: M i =w1·(T i -T base )+w2·H i +w3·W i +w4·RH i ; Among them, GI is the gas load assessment index, G i is the gas usage on the i-th day, M i is the meteorological impact factor, n is the number of days in the evaluation period, T max and T min are the highest and lowest temperatures during the evaluation period, respectively, and D p is the demographic data during the evaluation period, P is the average population threshold for regional gas use, R is the average gas price during the evaluation period, and T i is the average temperature of the i-th day, T base is the preset reference temperature, which is used to calculate the degree of temperature deviation from the reference. i is the sunshine duration of the i-th day, W i is the wind speed on the i-th day, RH i is the relative humidity of the i-th day, (w1, w2, w3, w4) are the weight coefficients of temperature, sunshine, wind speed and relative humidity respectively, D p，j is the demographic data of the jth region, U j is the unit amount of gas used in the jth region, and m is the total number of regions.

5. A method for predicting load of a city gas system in heating season according to claim 4, characterized in that: In step 3, the process of obtaining the risk warning coefficient is as follows: Step 301, extracting historical meteorological data from a regional historical meteorological database, extracting records of extreme weather events, including occurrence time, duration, impact range, and intensity; Step 302, analyzing historical heating season gas load data and historical meteorological data, determining the main extreme weather types that affect the gas load, identifying past extreme weather events and their historical impact on the gas load, determining the impact value of extreme weather based on the severity and frequency of extreme weather events, analyzing the impact values ​​of all extreme weather conditions, and obtaining an extreme weather impact index; Step 303, using historical meteorological data, gas load data and extreme weather risk assessment index as input variables, building a risk assessment model, establishing a correlation between extreme weather and gas load, combining the gas load assessment index and the risk assessment model, defining a risk warning coefficient, and quantifying the risk level; Step 304, dividing different load warning levels based on the risk warning coefficient into low load warning level, medium load warning level and high load warning level, and setting corresponding warning thresholds for the load warning levels; Step 305: When the risk warning coefficient exceeds the preset warning threshold, the corresponding load warning level is output and the corresponding risk warning mechanism is triggered.

6. A method for predicting load of a city gas system in heating season according to claim 5, characterized in that: The calculation formula of the risk warning coefficient is: Among them, RAC is the risk warning coefficient, GI is the current gas load assessment index, and GI base is the baseline gas load assessment index, E is the extreme weather impact index, and E max is the maximum value of the historical extreme weather impact index, T d is the degree to which the current temperature deviates from the base temperature, T d，max is the maximum degree of temperature deviation from the base temperature in history, w j is the weight of the extreme weather event, k is the total number of extreme weather event types, e j is the impact value of the jth extreme weather event, G ev is the actual gas usage during the extreme weather event, G ep is the expected gas usage in the absence of extreme weather events.

7. A method for predicting load of a city gas system in heating season according to claim 6, characterized in that: A plurality of the load warning levels correspond to a plurality of the warning thresholds, wherein the warning thresholds include an upper threshold and a lower threshold; The multiple load warning levels and the multiple warning thresholds satisfy the following relationship: Low load warning level RAC <RAC l ; Medium load warning level RAC l ≤RAC <RAC h ; High load warning level RAC ≥ RAC h ; Among them, RAC is the risk warning coefficient, RAC l is the lower threshold corresponding to the medium load warning level and the upper threshold corresponding to the low load warning level, RAC h It is the lower threshold corresponding to the high load warning level and the upper threshold corresponding to the medium load warning level.

8. A method for predicting load of a city gas system in heating season according to claim 7, characterized in that: In step 4, the early warning and monitoring process of the city gas system in the heating season is as follows: Step 401, comprehensively analyzing the impact of historical extreme weather events, current meteorological conditions and changes in gas load, predicting the overall trend of gas load in the heating season, and determining the risk level faced by the gas system in the current heating season; Step 402, based on historical data and current weather forecasts, predict the load demand of the city gas system in the future heating season, analyze the prediction results, identify the peak period, valley period and potential fluctuation range of the gas load in the heating season, and draw a predicted gas load demand curve; Step 403, continuously monitor the deviation between the actual gas load and the predicted load, and monitor the changes in the current meteorological conditions and the risk warning coefficient, and formulate corresponding emergency plans and response measures according to the warning and monitoring results, targeting the risks and load pressures of different load warning levels.

9. A heating season city gas system load forecasting system, used to implement the heating season city gas system load forecasting method according to any one of claims 1 to 8, comprising a gas load monitoring center, characterized in that: The gas load monitoring center is connected to a data acquisition and processing module, a prediction model building module, an extreme weather analysis module, a risk assessment and early warning module, an emergency plan response module, and a monitoring feedback module, wherein electrical signals are connected between the modules; The data acquisition and processing module is used to collect data related to the gas system load from multiple data sources, including gas load data, meteorological data, demographic data and gas price data, and pre-process the collected data; The prediction model building module builds a prediction model based on historical data and current conditions to predict the city gas load demand in the future heating season and provide a prediction load curve; The extreme weather analysis module identifies extreme weather events from meteorological data based on a preset extreme weather definition, and records their occurrence time, duration, impact range, and intensity information, analyzes the historical impact of extreme weather events on gas load, determines the main extreme weather types that affect gas load, and calculates the impact value of extreme weather; The risk assessment and early warning module is used to combine the extreme weather impact and load forecast results to build a risk assessment model, calculate the risk early warning coefficient and quantify the risk assessment results, and assess the risk level faced by the gas system during the heating season; The emergency plan response module is used to formulate corresponding emergency plans according to different load warning levels; The monitoring feedback module is used to monitor the operating status, load conditions and external environmental changes of the gas system in real time.

Images