A method and system for predicting the load of a city gas system during the heating season

Abstract

The application discloses a kind of heating season city gas system load prediction method and system, it is related to gas system load prediction technical field, including the following steps: collection heating season city gas system relevant raw data, wherein raw data includes historical data and real-time data, and the raw data collected is preprocessed, obtain gas load analysis set and gas load analysis demand variable.The application constructs gas load prediction model by comprehensively analyzing gas usage, meteorological data, population statistics data and gas price data, significantly improves the accuracy of gas load prediction, and by analyzing historical extreme weather events, calculating extreme weather influence index, assessing possible risks, then combining gas load assessment index and risk warning coefficient, quantifying risk level, adjusting warning level dynamically according to real-time data, timely taking preventive measures, reducing the influence of extreme weather events on gas supply.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas system load prediction, in particular to a heating season urban gas system load prediction method and system. BACKGROUND

[0002] With the substantial improvement of urbanization level, the demand for urban gas as an important energy source has increased significantly. In the heating season, especially in northern regions, due to the drop in temperature, the heating demand of residents and enterprises increases dramatically, leading to a significant increase in urban gas system load. In order to ensure the stable supply of gas in the heating season, it is necessary to accurately analyze the gas system load in order to reasonably allocate resources and avoid supply and demand imbalance.

[0003] The gas consumption in the heating season is influenced by multiple factors. Due to geographical location and climate characteristics, there are significant differences in gas demand among different cities in the autumn and winter seasons, especially when extreme weather such as cold waves occurs, the fluctuation of demand is particularly obvious. Differences in economic development level, population density, and building insulation performance among different cities make it challenging for gas companies to plan procurement and supply. Precise prediction of gas load in the heating season not only helps to ensure the stability of gas supply, but also optimizes resource allocation and reduces operating costs.

[0004] In addition, the usage of gas users is diverse. Household users and commercial users (such as the catering industry) have significant differences in gas usage and usage habits. Household users usually use gas for daily cooking and heating, while commercial users have larger and more volatile usage. The existing management method cannot meet the individual needs of different users, which not only limits the understanding of gas consumption by users, but also affects the ability of gas companies to develop accurate marketing strategies.

[0005] In the prior art, the gas system load is influenced by calendar time, population density, and other factors, making it difficult to predict the load of urban gas in the heating season, which is prone to deviation, and in extreme weather conditions, the prediction result will have greater risk and uncertainty. Therefore, how to improve the accuracy of load prediction of urban gas in the heating season and strengthen risk management and response measures is a problem we need to solve. Therefore, a heating season urban gas system load prediction method and system is proposed. SUMMARY

[0006] The present application aims to provide a heating season urban gas system load prediction method and system to solve the problems raised in the background art.

[0007] To solve the above technical problems, the technical solution adopted by the present application is:

[0008] The first aspect is a heating season urban gas system load prediction method, comprising the following steps:

[0009] Step 1, collecting the relevant raw data of the heating season urban gas system, wherein the raw data includes historical data and real-time data, and preprocessing the collected raw data to obtain a gas load analysis set and a demand variable of gas load analysis;

[0010] Step 2, combining the gas load analysis set and the demand characteristics of gas load analysis, constructing a gas load prediction model, establishing a gas load evaluation index, and performing load prediction;

[0011] Step 3, based on the real-time data of the heating season urban gas system and combined with the regional historical meteorological database, analyzing the risk and influence of historical extreme weather, establishing a risk assessment model, cooperating with the gas load evaluation index, obtaining a risk warning coefficient, quantitatively evaluating the risk, and judging the influence of extreme weather on gas load prediction;

[0012] Step 4, analyzing the risk warning coefficient and the risk quantitative evaluation result, comprehensively predicting the load of the heating season urban gas system, performing early warning and monitoring of the heating season urban gas system, and formulating an emergency plan and countermeasures.

[0013] The further improvement of the technical scheme of the present application is that in step 1, the process of obtaining the gas load analysis set and the demand variable of gas load analysis is:

[0014] Step 101, collecting the relevant raw data of the heating season urban gas system, including gas use data, meteorological data, calendar data, population statistics data and gas price data;

[0015] Step 102, obtaining the historical gas consumption data during the heating season from the database, including weekly and monthly gas consumption data, and obtaining the 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 population statistics data of total population and population density, and collecting historical data and current price of gas price;

[0016] Step 103, performing data cleaning, data conversion and data integration preprocessing operations on the raw data, checking and removing outliers in the data, converting the data into time series format to facilitate analysis of time trends and seasonal patterns, and aligning and integrating the data collected from different sources according to the time stamp to establish a gas load analysis set;

[0017] Step 104, determining the demand variables of the gas load analysis in the gas load analysis set, and classifying and marking the demand variables, including gas use, weather, population and gas price variables.

[0018] Further improvement of the technical scheme of the present application is that, in step 2, the obtaining process of the gas load evaluation index is:

[0019] Step 201, data analysis is performed on the gas load analysis set, features are extracted from the gas use, weather data, population statistics data and gas price data to obtain a feature data set, and the feature data set is divided into a training set and a test set;

[0020] Step 202, selecting a neural network model, using the historical data of the training set to train the model, constructing a gas load prediction model, and using the related data of the test set to test and evaluate the gas load prediction model;

[0021] Step 203, using the trained gas load prediction model to predict the gas load, combining real-time data to analyze the deviation rate, change rate and stability of the gas load, establishing a gas load evaluation index to evaluate the fluctuation of the gas load, and further analyzing the change trend of the gas load.

[0022] Further improvement of the technical scheme of the present application 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] Wherein, GI is the gas load evaluation index, G i is the gas use amount of the i-th day, M i is the weather influence factor, n is the number of days in the evaluation period, T max and T min are the maximum temperature and the minimum temperature in the evaluation period respectively, D p is the population statistics data in the evaluation period, P is the average population threshold of the regional gas use, R is the average gas price in the evaluation period, T i is the average temperature of the i-th day, T base is a preset reference temperature, used to calculate the degree of deviation of the temperature from the reference, H iis the sunshine duration of the i-th day, W i is the wind speed of the i-th day, RH i is the relative humidity of the i-th day, (w1, w2, w3, w4) are weight coefficients of air temperature, sunshine, wind speed and relative humidity respectively, D p，j is the population statistics of the j-th region, U j is the gas usage unit quantity of the j-th region, m is the total number of regions.

[0027] The further improvement of the technical scheme of the present application is that in step 3, the risk warning coefficient acquisition process is:

[0028] Step 301, historical meteorological data is extracted from the regional historical meteorological database, and records of extreme weather time are extracted, including occurrence time, duration, influence range and intensity. Extreme weather refers to adverse weather such as cold wave, snowstorm and gale.

[0029] Step 302, analyze historical heating season gas load data and historical meteorological data, determine the main extreme weather type affecting gas load, identify past extreme weather events and their historical impact on gas load, determine the impact value of extreme weather based on the severity and frequency of extreme weather events, analyze the impact value of all extreme weather conditions, and obtain the extreme weather impact index.

[0030] Step 303, historical meteorological data, gas load data and extreme weather risk assessment index are used as input variables to build a risk assessment model, establish the correlation between extreme weather and gas load, combine the gas load assessment index and the risk assessment model, define the risk warning coefficient, and quantify the risk level.

[0031] Step 304, based on the risk warning coefficient, different load warning levels are divided, including low load warning level, medium load warning level and high load warning level, and corresponding warning thresholds are set 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] The further improvement of the technical scheme of the present application is that the calculation formula of the risk warning coefficient is:

[0034]

[0035] Wherein, 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 state of the current gas load, GI baseGbase is the baseline gas load assessment index, selected as the GI value under normal conditions, E is an extreme weather impact index, measuring the potential impact of extreme weather on gas load, E max Emax is the maximum value of the historical extreme weather impact index, T d T is the degree to which the current temperature deviates from the reference temperature, which is a long-term average, T d，max Tmax is the maximum degree to which the temperature deviates from the reference temperature in history, w j w is the weight of the kth extreme weather event, k is the total number of types of extreme weather events, e j G is the impact value of the jth extreme weather event, G ev G is the actual gas usage during the occurrence of the extreme weather event, G ep G is the expected gas usage without the extreme weather event.

[0036] Further improvement of the technical scheme of the present application is that a plurality of load warning levels correspond to a plurality of warning thresholds, wherein the warning thresholds include upper and lower thresholds;

[0037] The plurality of load warning levels and the plurality of 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, with less risk, and immediate action is not required, but attention should be paid;

[0039] Medium load warning level RAC l ≤ RAC < RAC h ; indicates that the load of the gas system is rising and approaching or exceeding the historical average level, with some risk, which needs to be closely monitored and prepared for measures;

[0040] High load warning level RAC ≥ RAC h ; indicates that the load of the gas system is high, with a very high risk, and immediate action is required to ensure system stability and safety;

[0041] Wherein, 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 is the lower threshold corresponding to the high load warning level and the upper threshold corresponding to the medium load warning level.

[0042] Further improvement of the technical scheme of the present application is that in step 4, the warning and monitoring process of the urban gas system in the heating season is:

[0043] Step 401, comprehensive analysis of the impact of historical extreme weather events, current weather conditions and gas load changes, prediction of the overall trend of the heating season gas load, judgment of the risk level faced by the current heating season gas system;

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

[0045] Step 403, continuously monitor the deviation of actual gas load and predicted load, monitor the changes of current weather conditions and risk warning coefficient, and according to the warning and monitoring results, formulate corresponding emergency plan and response measures for different load warning risk and load pressure. Low load warning needs to optimize supply chain and resource allocation, high load warning needs to start standby supply, adjust gas production or introduce temporary measures.

[0046] The second aspect is a heating season urban gas system load prediction system for realizing the heating season urban gas system load prediction method, which comprises a gas load supervision center, and the gas load supervision center is connected with a data acquisition and processing module, a prediction model construction module, an extreme weather analysis module, a risk assessment and warning module, an emergency plan response module and a monitoring feedback module. The modules are connected by electrical signals.

[0047] The data acquisition and processing module is used to collect data related to gas system load from multiple data sources, including gas load data, weather data, population statistics data and gas price data, and preprocess the collected data to ensure the accuracy and consistency of the data.

[0048] The prediction model construction module is used to construct a prediction model based on historical data and current situation to predict the urban gas load demand in future heating season, provide a predicted load curve, help plan and adjust gas supply, optimize supply chain management and resource allocation to cope with different load situations.

[0049] The extreme weather analysis module is used to identify extreme weather events from weather data based on pre-set extreme weather definition, record the occurrence time, duration, influence range and intensity information of the extreme weather events, analyze the historical impact of extreme weather events on gas load, determine the main extreme weather types affecting gas load, and calculate the impact value of extreme weather.

[0050] The risk assessment early warning module is configured to combine extreme weather influence and load prediction results, build a risk assessment model, calculate a risk early warning coefficient and quantize a risk assessment result, assess a risk level faced by the gas system in the heating season, provide a risk assessment report and early warning information, support decision makers in formulating emergency plans and coping strategies to cope with possible extreme weather events and load fluctuations.

[0051] The emergency plan response module is configured to formulate corresponding emergency plans for different load warning levels, including emergency response processes, resource allocation schemes, and personnel responsibility divisions, and when a warning signal is triggered, quickly start the emergency plan and execute corresponding countermeasures to ensure stable and safe operation of the gas system.

[0052] The monitoring feedback module is configured to monitor the operating state, load condition and external environmental changes of the gas system in real time to ensure the timeliness and accuracy of the data, and according to the real-time monitoring results and the execution of the emergency plan, to adjust the system, optimize the prediction model, the risk assessment model and the emergency plan, and improve the overall performance and response capability of the system.

[0053] Thanks to the above technical solutions, the present application has the following technical progress compared with the prior art:

[0054] 1. The present application provides a heating season urban gas system load prediction method and system, which significantly improves the accuracy of gas load prediction by comprehensively analyzing gas consumption, meteorological data, population statistics and gas price data, building a gas load prediction model, and calculating an extreme weather influence index by analyzing historical extreme weather events to assess possible risks, and then combining the gas load assessment index and the risk early warning coefficient to quantize the risk level, dynamically adjusting the warning level according to real-time data, and taking preventive measures in time to reduce the impact of extreme weather events on gas supply.

[0055] 2. The present application provides a heating season urban gas system load prediction method and system, which establishes a dynamic risk early warning and grading response mechanism, automatically divides the load warning level according to the risk early warning coefficient, and triggers the corresponding warning signal and emergency plan, realizes the precise grading and differentiated response of risks by setting three warning levels and corresponding thresholds, and can discover potential risks in advance to gain time for emergency response. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0057] Figure 1 Flow chart of the method of the present application;

[0058] Figure 2 Flow chart of the acquisition of the gas load evaluation index of the present application;

[0059] Figure 3 Flow chart of the acquisition of the risk early warning coefficient of the present application;

[0060] Figure 4 Block diagram of the present application. DETAILED DESCRIPTION

[0061] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0062] Embodiment 1, as shown in the present application provides a heating season urban gas system load prediction method, comprising the following steps: Figures 1-3

[0063] Step 1, collect the relevant raw data of the heating season urban gas system, wherein the raw data includes historical data and real-time data, and pretreat the collected raw data to obtain a gas load analysis set and demand variables for gas load analysis, collect the relevant raw data of the heating season urban gas system including gas use data, meteorological data, calendar data, population statistics data and gas price data, obtain the historical gas use data during the 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 including temperature, humidity, wind speed, rainfall, sunshine duration from the regional historical meteorological database, and collect the current meteorological data, collect the population statistics data of the total population and population density in the region, collect the historical data and current price of the gas price, perform data cleaning, data conversion and data integration preprocessing operations on the raw data, check and remove outliers in the data, convert the data into time series format for easy analysis of time trends and seasonal patterns, and align and integrate the data collected from different sources according to the time stamp, 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, including gas use, meteorology, population and gas price variables;

[0064] ​Step 2, combined with the gas load analysis set and the demand characteristics of the gas load analysis, a gas load prediction model is constructed, a gas load evaluation index is established, the load is predicted, the data of the gas load analysis set is analyzed, the characteristics are extracted from the gas consumption, meteorological data, population statistics data and gas price data to obtain a feature data set, the feature data set is divided into a training set and a test set, a neural network model is selected, and the historical data of the training set is used for model training to construct a gas load prediction model, the related data of the test set is used to test and evaluate the gas load prediction model, the trained gas load prediction model is used to predict the gas load, and combined with real-time data, the deviation rate, change rate and stability of the gas load are analyzed, a gas load evaluation index is established to evaluate the fluctuation of the gas load, and then the change trend of the gas load is analyzed;

[0065] Further, the calculation formula of the gas load evaluation index is:

[0066]

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

[0068]

[0069] Wherein, GI is the gas load evaluation index, G i is the gas consumption of the i-th day, M i is the meteorological influence factor, n is the number of days in the evaluation period, T max and T min are the maximum and minimum temperatures in the evaluation period respectively, D p is the population statistics data in the evaluation period, P is the average population threshold of the regional gas use, R is the average gas price in the evaluation period, 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 deviation of the temperature from the reference, H i is the sunshine duration of the i-th day, W i is the wind speed of 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 population statistics data of the j-th region, U jP is the average gas consumption per capita in the region, and m is the total number of regions. It should be noted that the value of P reflects the average gas consumption per capita after considering the gas consumption in different regions. M i The value of M changes according to changes in weather conditions. Different combinations of temperature, sunshine, wind speed, and relative humidity will have different effects on gas consumption. The greater the deviation of temperature from the baseline temperature, the greater the impact factor M i The greater the impact of weather conditions on gas demand. When gas consumption increases, GI rises. Extreme changes in temperature can cause changes in GI. Population growth or density increases will cause GI to rise without a corresponding decrease in gas consumption. A decrease in gas prices will increase GI. Lower prices will increase gas consumption.

[0070] Step 3: Based on real-time data of the city's gas system during the heating season and combined with the regional historical meteorological database, analyze the risk and impact of historical extreme weather, establish a risk assessment model, and obtain a risk warning coefficient by combining the gas load assessment index to quantitatively assess the risk and determine the impact of extreme weather on gas load prediction. Extract historical meteorological data from the regional historical meteorological database, including the time of occurrence, duration, impact range, and intensity. Extreme weather refers to severe weather such as cold waves, snowstorms, and strong winds. Analyze historical heating season gas load data and historical meteorological data to determine the main types of extreme weather that affect gas load. Identify past extreme weather events and their historical impact on gas load. Based on the severity and frequency of extreme weather events, determine the impact value of extreme weather. Analyze the impact values of all extreme weather conditions to obtain an extreme weather impact index. Use historical meteorological data, gas load data, and extreme weather risk assessment index as input variables to build a risk assessment model and establish the correlation between extreme weather and gas load. Combine the gas load assessment index and risk assessment model to define the risk warning coefficient and quantify the risk level. Based on the risk warning coefficient, divide the load warning levels into low, medium, and high, and set corresponding warning thresholds for each level. When the risk warning coefficient exceeds the preset warning threshold, output the corresponding load warning level and trigger the corresponding risk warning mechanism.

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

[0072]

[0073] where RAC is the risk warning coefficient, which quantifies the risk level of gas load. GI is the current gas load assessment index, reflecting the comprehensive state of the current gas load. GI baseThe index for the baseline gas load is selected as the GI value under normal conditions, E is the extreme weather impact index, which measures the potential impact of extreme weather on gas load, 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 reference temperature, which is a long-term average, T d，max is the maximum degree to which the temperature deviates from the reference temperature in history, w j is the weight of the k-th extreme weather event, k is the total number of types of extreme weather events, e j is the impact value of the j-th extreme weather event, G ev is the actual gas usage during the occurrence of the extreme weather event, G ep is the expected gas usage without the extreme weather event, it is noted that the greater the value of E indicates the more severe the impact of extreme weather, the value of E is positively proportional to the severity and frequency of extreme weather events, and the greater the value of E indicates the greater the potential impact of extreme weather events on gas load, E presents an upward trend with the increase of climate change and extreme weather events, when GI increases or E increases, RAC increases, indicating that the risk level rises;

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

[0075] The plurality of load warning levels and the plurality of warning thresholds satisfy the following relationship:

[0076] Low load warning level RAC < RAC l , indicating that the load of the current gas system is at a normal or low level, with a small risk, and immediate action is not required, but attention should be paid;

[0077] Medium load warning level RAC l ≤ RAC < RAC h , indicating that the load of the gas system is starting to rise, approaching or exceeding the historical average level, with a certain risk, which needs to be closely monitored and prepared for measures;

[0078] High load warning level RAC ≥ RAC h , indicating that the load of the gas system is high, with a very high risk, and immediate action is required to ensure system stability and safety;

[0079] wherein RAC is a 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 is 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 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. This involves comprehensively analyzing the impact of historical extreme weather events, current meteorological conditions, and gas load changes to predict the overall trend of gas load during the heating season, assessing the current risk level faced by the gas system, and predicting the future load demand of the urban gas system based on historical data and current weather forecasts. The prediction results are analyzed to identify peak periods, trough periods, and potential fluctuation ranges of the gas load during the heating season, and a predicted gas load demand curve is plotted. The deviation between the actual gas load and the predicted load is continuously monitored, along with changes in current meteorological conditions and risk warning coefficients. Based on the early warning and monitoring results, corresponding emergency plans and response measures are formulated for different load warning levels, considering the risk and load pressure. Low load warnings require supply chain optimization and resource allocation, while high load warnings require activating backup supply, adjusting gas production, or introducing temporary measures.

[0081] Example 2, as Figure 4 As shown, based on Embodiment 1, the present invention also provides a heating season urban gas system load forecasting system for realizing a heating season urban gas system load forecasting method, including a gas load monitoring center, which is communicatively connected to a data acquisition and processing module, a forecasting model construction module, an extreme weather analysis module, a risk assessment and early warning module, an emergency response plan module, and a monitoring feedback module, wherein the modules are electrically connected.

[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 to preprocess the collected data to ensure the accuracy and consistency of the data.

[0083] The prediction model building module, based on historical data and current conditions, constructs a prediction model to predict the city's gas load demand in the future heating season, provides a predicted load curve, helps plan and adjust gas supply, optimize supply chain management and resource allocation, and cope with different load conditions.

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

[0085] The risk assessment early warning module is configured to combine extreme weather influence and load prediction results, build a risk assessment model, calculate a risk early warning coefficient and quantize risk assessment results, assess the risk level faced by the gas system in the heating season, provide a risk assessment report and early warning information, support decision makers in formulating emergency plans and coping strategies to cope with possible extreme weather events and load fluctuations;

[0086] The emergency plan response module is configured to formulate corresponding emergency plans for different load warning levels, including emergency response processes, resource allocation schemes, and personnel responsibility division, and when a warning signal is triggered, quickly start the emergency plan and execute corresponding countermeasures to ensure stable and safe operation of the gas system.

[0087] The monitoring feedback module is configured to monitor the operating state, load condition, and external environmental changes of the gas system in real time to ensure the timeliness and accuracy of the data, and according to the real-time monitoring results and the execution of the emergency plan, to adjust and optimize the prediction model, the risk assessment model, and the emergency plan, and to improve the overall performance and response capability of the system.

[0088] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting the load of an urban gas system during the heating season, characterized in that, Includes the following steps: Step 1: Collect relevant raw data of the urban gas system during the heating season. The raw data includes historical data and real-time data. The collected raw data is preprocessed to obtain the gas load analysis set and the demand variables for gas load analysis. Step 2: Combining the gas load analysis set and the demand characteristics of the gas load analysis, construct a gas load forecasting model, establish a gas load assessment index, and perform load forecasting. The process of obtaining the gas load assessment index is as follows: Step 201: 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 dataset, and divide the feature dataset into a training set and a test set. Step 202: Select a neural network model and train the model using historical data from the training set to build a gas load prediction model. Use relevant data from 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 it with real-time data to analyze the deviation rate, change rate and stability of the gas load, establish a gas load assessment index, assess the fluctuation of the gas load, and then analyze the trend of gas load change. The formula for calculating the gas load assessment index is as follows: ； ； ； in, This is a gas load assessment index. For the first Daily gas consumption Meteorological influencing factors, To assess the number of days within the period, and These are the highest and lowest temperatures during the evaluation period, respectively. To assess demographic data within the assessment period, The average population threshold for regional gas use. To assess the average gas price over the evaluation period, For the first The average temperature of the day This is a preset reference temperature used to calculate the degree to which the air temperature deviates from the reference. For the first Daylight hours For the first The wind speed of the day, For the first The relative humidity of the day These are the weighting coefficients for air temperature, sunshine duration, wind speed, and relative humidity, respectively. For the first Population statistics for each region For the first Gas usage per unit area Total number of regions; Step 3: Based on real-time data of the urban gas system during the heating season and combined with the regional historical meteorological database, analyze the risks and impacts of historical extreme weather, establish a risk assessment model, and in conjunction with the gas load assessment index, obtain a risk warning coefficient, quantify the risk, and determine the impact of extreme weather on gas load forecasting. 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. The method for predicting the load of an urban gas system during the 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 for gas load analysis is as follows: Step 101: Collect historical and real-time raw data related to the urban gas system during the heating season, including gas usage data, meteorological data, calendar data, demographic data, and gas price data. Step 102: Obtain historical gas consumption data during the heating season from the database, including weekly and monthly gas consumption data, and obtain current gas consumption data. Extract historical meteorological data from the regional historical meteorological database, including temperature, humidity, wind speed, rainfall, and sunshine duration, and collect current meteorological data. Collect demographic data on the total population and population density of the region, and collect historical and current gas price data. Step 103 involves preprocessing the raw data by cleaning, transforming, and integrating the data, and aligning and integrating the data collected from different sources according to timestamps to establish a gas load analysis set. Step 104: Determine the demand variables for gas load analysis in the gas load analysis set, and classify and label the demand variables. The demand variables include multiple variables such as gas usage, weather, population and gas price.

3. The method for predicting the load of an urban gas system during the heating season according to claim 1, characterized in that: In step 3, the process of obtaining the risk warning coefficient is as follows: Step 301: Extract historical meteorological data from the regional historical meteorological database, and extract records of extreme weather events, including the time of occurrence, duration, scope of impact, and intensity. Step 302: Analyze historical heating season gas load data and historical meteorological data to determine the main extreme weather types affecting gas load, identify past extreme weather events and their historical impact on gas load, determine the impact value of extreme weather based on the severity and frequency of extreme weather events, analyze the impact value of all extreme weather conditions, and obtain the extreme weather impact index. Step 303: Using historical meteorological data, gas load data, and extreme weather risk assessment index as input variables, establish the correlation between extreme weather and gas load by constructing a risk assessment model, and define the risk warning coefficient by combining the gas load assessment index and the risk assessment model to quantify the risk level. Step 304: Based on the risk warning coefficient, different load warning levels are divided into low load warning level, medium load warning level and high load warning level, and corresponding warning thresholds are set for the load warning level; Step 305: When the risk warning coefficient exceeds the preset warning threshold, output the corresponding load warning level and trigger the corresponding risk warning mechanism.

4. The method for predicting the load of an urban gas system during the heating season according to claim 3, characterized in that: The formula for calculating the risk warning coefficient is as follows: ； ； ； in, This is the risk warning coefficient. This is the current gas load assessment index. The baseline gas load assessment index, The extreme weather impact index This represents the highest historical extreme weather impact index. This represents the degree to which the current temperature deviates from the baseline temperature. This represents the largest deviation of temperature from the baseline in history. The weight of the first type of extreme weather event, The total number of types of extreme weather events. For the first The impact value of an extreme weather event This represents the actual gas consumption during extreme weather events. This represents the expected gas consumption under conditions of no extreme weather events.

5. The method for predicting the load of an urban gas system during the heating season according to claim 4, characterized in that: The multiple load warning levels correspond to multiple warning thresholds, wherein the warning thresholds include an upper limit threshold and a lower limit threshold; The multiple load warning levels and the multiple warning thresholds satisfy the following relationship: Low load warning level ; Medium load warning level ; High load warning level ; in, This is the risk warning coefficient. These are the lower threshold corresponding to the medium load warning level and the upper threshold corresponding to the low load warning level. These are the lower threshold corresponding to the high load warning level and the upper threshold corresponding to the medium load warning level.

6. The method for predicting the load of an urban gas system during the heating season according to claim 5, characterized in that: In step 4, the early warning and monitoring process for the urban gas system during the heating season is as follows: Step 401: Comprehensively analyze the impact of historical extreme weather events, current meteorological conditions and changes in gas load, predict the overall trend of gas load during the heating season, and determine the risk level faced by the gas system during the current heating season; Step 402: Based on historical data and current weather forecasts, predict the load demand of the urban gas system for the future heating season, analyze the forecast results, identify the peak periods, trough periods and potential fluctuation ranges of the gas load during the heating season, and plot the predicted gas load demand curve. Step 403: Continuously monitor the deviation between the actual gas load and the predicted load, while also monitoring changes in current meteorological conditions and risk warning coefficients. Based on the warning and monitoring results, formulate corresponding emergency plans and response measures for different load warning levels and load pressures.

7. A heating season urban gas system load forecasting system, used to implement the heating season urban gas system load forecasting method according to any one of claims 1-6, 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 construction module, an extreme weather analysis module, a risk assessment and early warning module, an emergency response module, and a monitoring feedback module. The modules are connected by electrical signals. 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, population statistics and gas price data, and to preprocess the collected data. The prediction model building module constructs a prediction model based on historical data and current conditions to predict the urban gas load demand in the future heating season and provides a predicted load curve. The extreme weather analysis module, based on a preset definition of extreme weather, identifies extreme weather events from meteorological data and records their occurrence time, duration, impact range, and intensity information. It analyzes the historical impact of extreme weather events on gas load, determines the main types of extreme weather affecting gas load, and calculates the impact value of extreme weather. The risk assessment and early warning module is used to combine the impact of extreme weather and load forecast results to construct a risk assessment model, calculate the risk warning coefficient and quantify the risk assessment results, and assess the risk level faced by the gas system during the heating season. The emergency response module is used to formulate corresponding emergency plans for different load warning levels. The monitoring and feedback module is used to monitor the operating status, load conditions, and changes in the external environment of the gas system in real time.

Images