A complementary supply method of urban energy based on source, grid, load and storage

Abstract

The present invention discloses a complementary supply method of urban energy based on source, grid, load and storage, which relates to the technical field of power data analysis of heating systems, comprehensively monitors various types of energy in urban energy systems, and collects relevant operating data; analyzes operating data based on machine learning technology, and performs energy demand forecasting and output forecasting of various types of energy; formulates a multi-objective scheduling strategy based on the results of energy demand forecasting and output forecasting analysis, and uses a multi-objective optimization algorithm to find the optimal scheduling scheme; automatically adjusts the operating parameters of each energy system according to the determined optimal scheduling scheme. The present invention improves energy utilization efficiency by matching energy supply and demand, and uses the scheduling of smart grids to adjust the output of generator sets to ensure a high degree of matching between energy supply and load demand. At the same time, it uses renewable energy as a priority power supply source to reduce the consumption of fossil energy and promote the green and low-carbon development of cities.

Description

Technical Field

[0001] The present invention relates to the technical field of power data analysis of heating systems, and in particular to a complementary supply method of urban energy based on source, grid, load and storage. Background Art

[0002] With the acceleration of urbanization and economic development, urban energy demand has shown a growing trend, especially in the field of heating. With the drop in winter temperature and the improvement of residents' living standards, the demand for heating continues to increase, accompanied by energy loss and waste in the related power systems of the heating system. Improving energy utilization efficiency and reducing energy consumption and environmental pollution have become important tasks of urban energy systems. The source-grid-load-storage integrated project can realize the complementary use of multiple energy sources.

[0003] In urban heating systems, when faced with emergencies or load fluctuations, the flexibility and stability of multi-energy systems are poor, making it difficult to coordinate multiple energy sources and balance multiple goals. Therefore, how to adjust the multi-energy system to output more flexible and intelligent heating system grid dispatching measures is the problem we need to solve. To this end, a complementary supply method of urban energy based on source, grid, load and storage is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a complementary supply method of urban energy based on source, grid, load and storage to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A complementary supply method of urban energy based on source, grid, load and storage comprises the following steps: Step 1: Comprehensively monitor all types of energy in the urban energy system and collect relevant operating data, including energy output, load demand, heating system grid status, and energy storage equipment status data; Step 2: Analyze the operation data based on machine learning technology to predict energy demand and output of various energy sources; Step 3: According to the results of energy demand forecast and output forecast analysis, formulate a multi-objective scheduling strategy, and use the multi-objective optimization algorithm to find the optimal scheduling solution; Step 4: Automatically adjust the operating parameters of each energy system according to the determined optimal dispatching plan, and dynamically adjust the load and allocate energy storage resources; Step 5: Evaluate the operation of the energy system and analyze the matching degree of the scheduling strategy.

[0006] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting the operating data includes: The types of energy that need to be monitored in the urban energy system are clarified, including wind power, photovoltaic power and combustion power, and the operating data of each energy type is determined, namely energy output, load demand, heating system grid status and energy storage equipment status. Among them, for the operating data of wind power, the energy output is to monitor the output power, wind speed and wind direction of wind turbines in real time, and the load demand is to analyze the proportion of wind power in the grid and the user's demand for this energy. For the operating data of photovoltaic power, the energy output is to monitor the output power, light intensity and temperature of photovoltaic panels in real time, and the load demand is to analyze the proportion of photovoltaic power in the grid and the user's demand for this energy. For the operating data of combustion power, the energy output is to monitor the output power, fuel consumption rate and emission concentration of the generator set, and the load demand is to analyze the proportion of combustion power in the grid and the user's demand for this energy. For wind power, photovoltaic power and combustion power, the heating system grid status is to monitor the frequency, voltage and current parameters of the grid, as well as the interaction between power and the grid. The energy storage equipment status is to monitor the charge and discharge status, remaining capacity and temperature of the energy storage battery.

[0007] Monitoring equipment is deployed in the urban energy system, and the data collection frequency is configured. The monitoring equipment includes sensors, smart meters and data collectors. The collection frequency of energy output and heating system grid status data is set to once per second to grasp the dynamic changes of energy supply and grid operation in real time. The collection frequency of load demand data is set to once every 15 minutes to analyze the short-term change trend of load. The collection frequency of energy storage equipment status data is set to once every 10 minutes to monitor its long-term operating status.

[0008] Utilize the deployed monitoring equipment to collect operation data from the city energy system in real time according to the set data collection frequency.

[0009] Establish a unified data platform and build a stable and reliable data transmission network to connect various monitoring equipment and data platforms. The data transmission network adopts a combination of wired network (optical fiber, Ethernet) and wireless network (4G / 5G, Wi-Fi) to ensure that data can be transmitted in a timely and accurate manner.

[0010] The monitoring equipment uploads the collected operation data to the data platform through the data transmission network, performs preprocessing operations on the operation data including data cleaning, format conversion and time synchronization to ensure the consistency and comparability of the data, and integrates the operation data to form an operation data sequence.

[0011] A further improvement of the technical solution of the present invention is that in step 2, the process of energy demand forecasting and output forecasting includes: Time series data of wind power, photovoltaic power and combustion power operation data are extracted from the operation data sequence, and feature analysis is performed on the operation data according to the needs of energy demand forecast and output forecast.

[0012] For wind power, wind speed, wind direction and wind power output power are extracted as features. For photovoltaic power, light intensity, temperature and photovoltaic output power are extracted as features. For combustion power, fuel consumption rate, emission concentration and thermal power output power are extracted as features. The feature data set is integrated to obtain the feature data set, and the features are scaled to ensure that different features are comparable in value. The feature data set is then divided into a training set and a test set.

[0013] The supply and demand model is trained using the training set data combined with the linear regression model. During the training process, the model parameters are adjusted to optimize the prediction performance. The cross-validation method is used to evaluate the performance of the model under different parameters to select the best parameters. The trained supply and demand model is evaluated using the test data set, and the prediction error and performance indicators of the supply and demand model are calculated. The model is optimized based on the evaluation results, and the prediction performance of the model is improved through continuous iteration and optimization.

[0014] The supply and demand model is deployed to the actual energy management system to perform energy demand forecasting and energy output forecasting, calculate energy demand and total energy output, and analyze energy demand trends and energy output trends.

[0015] A further improvement of the technical solution of the present invention is that the calculation process of the energy demand is: For each type of energy i, calculate its output ratio at time t.

[0016] Determine the demand elasticity coefficient based on the impact of energy output on demand. Multiply the output ratio of each energy source by the elasticity coefficient. The power of is used to calculate the elastic impact of the output ratio in order to analyze the elastic impact of energy output on demand.

[0017] The elastic effects of all energy sources are summed to obtain the impact of comprehensive energy output on demand.

[0018] Based on the rate of demand decay over time and the rate of energy demand growth over time, the demand decay coefficient and demand growth coefficient are determined, and the time decay factor is calculated according to time t. ,in, is the demand decay coefficient, which indicates the rate at which demand decays over time. The comprehensive energy output impact is multiplied by the time decay factor and then multiplied by the demand growth coefficient , and obtain the demand growth.

[0019] Analyze the demand that would still exist when energy output is zero to determine the base demand, and add the demand growth to the base demand , get the energy demand at time t .

[0020] A further improvement of the technical solution of the present invention is that the calculation process of the total energy output is: The output ratio of each type of energy is calculated, and based on the output power and maximum output power of each type of energy at time t, the output ratio of wind power, photovoltaic power and combustion power at time t is calculated respectively.

[0021] From the calculated output ratios of various types of energy, take the minimum output ratio to clarify the output limit of the weakest link in the energy system.

[0022] Based on the influence of each energy output on the total output, determine the basic output and output elasticity coefficient, and multiply the minimum output ratio by the output elasticity coefficient. to the power of to calculate the elastic effect of each energy output on the total output.

[0023] Analyze the growth rate of energy output over time, determine the output growth coefficient, and calculate the time growth factor based on time t ,in, It is the output growth coefficient, which indicates the growth rate of energy output over time. The output growth is obtained by multiplying the output elasticity effect by the time growth factor.

[0024] Analyze the basic output that still exists when all energy outputs are zero, determine the basic output, and add the output growth to the basic output , get the total energy output at time t .

[0025] A further improvement of the technical solution of the present invention is that in step 3, the process of finding the optimal scheduling solution includes: Clarify the multi-objective optimization goals of power dispatching, including economic goals, environmental protection goals, reliability goals and stability goals.

[0026] Based on the results of energy demand forecast and energy output forecast, the energy demand trend and energy output trend are clarified, and a multi-objective scheduling strategy is formulated, including: adjusting the power generation ratio of traditional energy and new energy, optimizing the operation mode of the heating power system, and combining energy storage technology to smooth power output.

[0027] The operating characteristics and constraints of the heating and power system are analyzed, and a multi-objective optimization algorithm based on the particle swarm optimization algorithm is used to calculate the comprehensive optimization indicators of the optimal scheduling scheme of the heating and power system. A trade-off solution is found between multiple objectives, and the optimal scheduling scheme is solved so that the scheduling scheme reaches the optimal level while meeting all objectives.

[0028] A further improvement of the technical solution of the present invention is that the process of solving the optimal scheduling solution includes: The operating characteristics and constraints of the heating power system are analyzed, including the output characteristics of the generator sets, the transmission characteristics of the power grid and the change characteristics of the load, and the constraints of the heating power system are clarified, including the operating constraints of the generator sets, the stable operation constraints of the power grid and the charging and discharging constraints of the energy storage equipment.

[0029] According to the analysis results, an optimization model with multiple objectives is constructed. The objective functions of the optimization model include economy, environmental protection, reliability and stability, and include constraints of the heating and power system to ensure the feasibility of the optimization solution.

[0030] A multi-objective optimization algorithm based on particle swarm optimization algorithm is selected to initialize the particle swarm. Each particle represents a potential scheduling scheme. Through the iterative process, the speed and position of the particle are updated, that is, the decision variables in the scheduling scheme are adjusted, that is, the output of the generator set and the charging and discharging status of the energy storage device. After each iteration, the fitness of the particle is evaluated, that is, the performance on each objective function, and the external archive is updated according to the Pareto dominance relationship.

[0031] The maximum number of iterations is set as the termination condition. When the termination condition is met, the iteration is stopped and the Pareto optimal solution set, that is, the comprehensive optimization index of the optimal scheduling scheme, is output.

[0032] A further improvement of the technical solution of the present invention is that in step 4, the process of dynamic load adjustment and energy storage resource allocation includes: The decision variables of each energy system are extracted from the optimal scheduling plan, including the output of the generator set, the charging and discharging status of the energy storage equipment, and the load distribution ratio. Based on the value of the decision variables, the specific goals that need to be adjusted for each energy system are clarified, including the need to increase or decrease the output of the generator set, the need to charge or discharge the energy storage equipment, and the need to transfer or adjust the load.

[0033] Analyze and determine the optimal scheduling plan and the values ​​of decision variables, and clarify the target operating parameters of each energy system, including the adjustment of generator sets, energy storage equipment, and transmission and distribution equipment.

[0034] Combined with the target operating parameters of each energy system, dynamic load adjustment is carried out through demand-side response, load shifting and load transfer.

[0035] According to the requirements of the optimal dispatching plan, energy storage and load coordination are carried out by combining the coordination of energy storage equipment, the coordination of energy storage and power generation, and the coordination of energy storage and load.

[0036] A further improvement of the technical solution of the present invention is that in step 5, the process of analyzing the degree of matching of the scheduling strategy includes: Based on the real-time operation data of each energy system, the operation data of each energy system before and after the implementation of the dispatch strategy is extracted, including the output data of the generator set, the charging and discharging data of the energy storage equipment, the load data, and the voltage and frequency data of the power grid.

[0037] The operating data of each energy system is analyzed to determine the indicators for evaluating the dispatching strategy, which are economic indicators and stability indicators. The economic indicators include operating costs and energy utilization efficiency, and the stability indicators include grid voltage and grid frequency. The operating costs include fuel costs, equipment maintenance costs, electricity purchase costs, etc. The dispatching strategy should try to reduce costs to improve the economic benefits of the system. By optimizing the dispatching, the energy utilization efficiency can be improved, and energy waste can be reduced, thereby reducing the unit energy use cost.

[0038] Compare and analyze various indicators before and after the implementation of the dispatch strategy to find out the advantages and disadvantages of the dispatch strategy, and calculate the dispatch matching value to evaluate the degree of match between the dispatch strategy and the actual operation requirements of the energy system.

[0039] The data analysis results and the dispatch strategy matching degree analysis are integrated into an evaluation report, and the evaluation report is fed back to the managers of the energy system.

[0040] A further improvement of the technical solution of the present invention is that the integrated feedback process of the evaluation report includes: Extract various indicator data before and after the implementation of the dispatch strategy from the monitoring system of the energy system, including the output of the generator set, the charging and discharging status of the energy storage equipment, load data, grid voltage and frequency, and integrate and analyze the various indicator data.

[0041] Based on the data analysis results, the advantages of the dispatch strategy in improving efficiency, reducing costs and enhancing reliability are identified, and the shortcomings of the dispatch strategy in actual operation are analyzed. At the same time, the analysis results of the degree of matching between the dispatch strategy and the actual operation requirements of the energy system are obtained.

[0042] Prepare an evaluation report, integrate the analysis results of various indicators in the evaluation report, and based on the analysis results, put forward conclusions and improvement suggestions, including adjusting scheduling parameters and optimizing equipment operation methods.

[0043] Submit the evaluation report to the managers of the energy system and collect their feedback and suggestions to further adjust the scheduling strategy.

[0044] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: 1. The present invention provides a complementary supply method for urban energy based on source, grid, load and storage. By matching energy supply and demand, energy utilization efficiency is improved. By utilizing the dispatch of smart grids, the output of generator sets can be adjusted to ensure a high degree of matching between energy supply and load demand. At the same time, renewable energy is used as a priority power source to reduce the consumption of fossil energy and promote the green and low-carbon development of cities.

[0045] 2. The present invention provides a complementary supply method for urban energy based on source, grid, load and storage. By integrating different forms of energy systems in the region, it realizes the coordinated optimization and efficient complementarity of various forms of energy, enhances the flexibility of the energy system, and through intelligent scheduling and refined management, it realizes effective control of energy costs and meets the intelligent and refined management needs of the energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] Figure 1 The figure is a flow chart of the method of the present invention.

[0048] Figure 2 This is a flow chart of energy demand prediction and output prediction of the present invention.

[0049] Figure 3 This is a flow chart for analyzing the matching degree of scheduling strategies in the present invention. DETAILED DESCRIPTION

[0050] 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. Embodiment 1, as Figure 1 As shown, the present invention provides a complementary supply method of urban energy based on source, grid, load and storage, comprising the following steps: Step 1: Comprehensively monitor all types of energy in the urban energy system and collect relevant operating data, where the operating data includes energy output, load demand, heating system grid status, and energy storage device status data. Clarify the types of energy that need to be monitored in the urban energy system, including wind power, photovoltaic power, and combustion power, and determine the operating data of each energy type, namely energy output, load demand, heating system grid status, and energy storage device status. For the operating data of wind power, the energy output is to monitor the output power, wind speed, and wind direction of the wind turbine in real time, and the load demand is to analyze the wind power in the grid. For the operation data of photovoltaic power, the energy output is to monitor the output power, light intensity and temperature of photovoltaic panels in real time, and the load demand is to analyze the proportion of photovoltaic power in the power grid and the user's demand for this energy. For the operation data of combustion power, the energy output is to monitor the output power, fuel consumption rate and emission concentration of the generator set, and the load demand is to analyze the proportion of combustion power in the power grid and the user's demand for this energy. For wind power, photovoltaic power and combustion power, the power grid status of the heating system is to monitor the frequency, voltage and current parameters of the power grid, as well as the interaction between power and the power grid. Energy storage The equipment status is to monitor the charging and discharging status, remaining capacity and temperature of the energy storage battery. Monitoring equipment is deployed in the urban energy system and the data collection frequency is configured. The monitoring equipment includes sensors, smart meters and data collectors. The collection frequency of energy output and heating system grid status data is set to once per second to grasp the dynamic changes of energy supply and grid operation in real time. The collection frequency of load demand data is set to once every 15 minutes to analyze the short-term change trend of load. The collection frequency of energy storage equipment status data is set to once every 10 minutes to monitor its long-term operation status. Using the deployed monitoring equipment, according to The set data collection frequency collects operation data from the urban energy system in real time, establishes a unified data platform, and builds a stable and reliable data transmission network to connect various monitoring devices and data platforms. The data transmission network adopts a combination of wired network (optical fiber, Ethernet) and wireless network (4G / 5G, Wi-Fi) to ensure that the data can be transmitted in a timely and accurate manner. The monitoring equipment uploads the collected operation data to the data platform through the data transmission network, and performs pre-processing operations on the operation data including data cleaning, format conversion and time synchronization to ensure the consistency and comparability of the data, and integrates the operation data to form an operation data sequence.

[0051] Step 2: Analyze the operation data based on machine learning technology to predict energy demand and output of various energy sources. Extract the time series data of wind power, photovoltaic power and combustion power operation data from the operation data sequence, and perform feature analysis on the operation data according to the needs of energy demand forecast and output forecast. For wind power, extract wind speed, wind direction and wind power output power as features. For photovoltaic power, extract light intensity, temperature and photovoltaic output power as features. For combustion power, extract fuel consumption rate, emission concentration and thermal power output power as features. Integrate the feature data set, scale the features to ensure that different features are comparable in value, and combine the features. The data set is divided into a training set and a test set. The supply and demand model is trained using the training set data in combination with a linear regression model. During the training process, the model parameters are adjusted to optimize the prediction performance. The cross-validation method is used to evaluate the performance of the model under different parameters to select the optimal parameters. The trained supply and demand model is evaluated using the test data set, and the prediction error and performance indicators of the supply and demand model are calculated. The model is optimized based on the evaluation results. Through continuous iteration and optimization, the prediction performance of the model is improved. The supply and demand model is deployed in the actual energy management system to perform energy demand forecasting and energy output forecasting, calculate energy demand and total energy output, and analyze energy demand trends and energy output trends.

[0052] Furthermore, the energy demand is calculated as follows: For each type of energy i, calculate its output ratio at time t, that is, ,in, is the output power of the i-th energy source at time t, is its maximum output power.

[0053] According to the impact of energy output on demand, the demand elasticity coefficient is determined, and the output ratio of each energy source is Multiply by the elastic modulus The power of , calculate the elastic impact of output ratio to analyze the elastic impact of energy output on demand.

[0054] The elastic effects of all energy sources are summed up, that is, , and obtain the impact of comprehensive energy output on demand.

[0055] Based on the rate of demand decay over time and the rate of energy demand growth over time, the demand decay coefficient and demand growth coefficient are determined, and the time decay factor is calculated according to time t. ,in, is the demand decay coefficient, which indicates the rate at which demand decays over time. The comprehensive energy output impact is multiplied by the time decay factor and then multiplied by the demand growth coefficient ,Right now , and obtain the demand growth.

[0056] Analyze the demand that would still exist when energy output is zero to determine the base demand, and add the demand growth to the base demand , get the energy demand at time t .

[0057] Among them, the calculation expression of energy demand at time t is:

[0058] In the formula, is the energy demand at time t, is the demand growth coefficient, which indicates the rate at which energy demand increases over time. is the output power of the i-th energy at time t, is the maximum output power of the i-th energy source, is the demand elasticity coefficient, which indicates the impact of energy output on demand. is the demand attenuation coefficient, which indicates the rate at which demand decays over time. is the basic demand, which means the demand that still exists even when the energy output is zero. The value range of is between 0 and 1, indicating that the energy demand is between 0 and 1, 0 means no demand, 1 means the demand reaches the maximum value, as time t increases, gradually decreases, leading to It shows a trend of first increasing and then stabilizing. When increasing, Increase, thereby promoting increase.

[0059] Furthermore, the calculation process of the total energy output is: The output ratio of each type of energy is calculated. Based on the output power and maximum output power of each type of energy at time t, the output ratio of wind power, photovoltaic power and combustion power at time t is calculated respectively, that is, ,in, , , are the output power of these three energy sources at time t, , , are their maximum output powers respectively.

[0060] From the calculated output ratios of various types of energy, take the minimum output ratio to clarify the output limit of the weakest link in the energy system, that is, .

[0061] Based on the influence of each energy output on the total output, determine the basic output and output elasticity coefficient, and multiply the minimum output ratio by the output elasticity coefficient. to the power of to calculate the elastic effect of each energy output on the total output, that is, .

[0062] Analyze the growth rate of energy output over time, determine the output growth coefficient, and calculate the time growth factor based on time t ,in, is the output growth coefficient, which indicates the growth rate of energy output over time. The output elasticity effect is multiplied by the time growth factor to obtain the output growth amount, that is, .

[0063] Analyze the basic output that still exists when all energy outputs are zero, determine the basic output, and add the output growth to the basic output , get the total energy output at time t .

[0064] Among them, the calculation expression of total energy output at time t is:

[0065] In the formula, is the total energy output at time t, , , They represent the output power of wind power, photovoltaic power and combustion power at time t, , , Respectively represent the maximum output power of wind power, photovoltaic power and combustion power, is the output elasticity coefficient, which indicates the influence of each energy output on the total output. is the output growth coefficient, which indicates the growth rate of energy output over time. The basic output is the basic output that exists when all energy outputs are zero. The value range of is 0 to 1, indicating that the total energy output is between 0 and 1, 0 means no output, 1 means the output reaches the maximum value, as time t increases, Gradually increasing, leading to It shows a trend of slow growth at first and then accelerated growth. , , When increasing, Increase, thereby promoting increase.

[0066] Step 3: Based on the results of energy demand forecast and output forecast analysis, formulate a multi-objective scheduling strategy, and use a multi-objective optimization algorithm to find the optimal scheduling solution.

[0067] Step 4: Automatically adjust the operating parameters of each energy system according to the determined optimal scheduling plan, and dynamically adjust the load and allocate energy storage resources.

[0068] Step 5: Evaluate the operation of the energy system and analyze the matching degree of the scheduling strategy.

[0069] Embodiment 2, as Figure 2 , Figure 3 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in step 3, the process of searching for the optimal scheduling solution includes: Clarify the multi-objective optimization goals of power dispatching, including economic goals, environmental protection goals, reliability goals and stability goals. Among them, the economic goal is to minimize the operating cost of the energy system, including fuel costs, equipment maintenance costs, electricity purchase costs, etc. The environmental protection goal is to minimize the environmental impact of the energy system, including reducing greenhouse gas emissions and pollutant emissions. The reliability goal is to ensure the reliability of energy supply, meet the energy needs of users, and avoid power outages or insufficient supply. The stability goal is to maintain the stable operation of the power grid and avoid voltage fluctuations, frequency deviations and other problems. Based on the results of energy demand forecasts and energy output forecasts, clarify the energy demand trend and energy output trend. According to the situation, a multi-objective dispatching strategy is formulated, including: adjusting the power generation ratio of traditional energy and new energy, optimizing the operation mode of the heating power system, and combining energy storage technology to smooth the power output. Among them, by reasonably arranging the power generation ratio of traditional energy and new energy to meet energy demand and maintain system stability, by optimizing the operation mode of the heating power system, reasonably arranging the start and stop plan of the unit, reducing operating costs and equipment losses, applying energy storage technology, smoothing power output, and improving power quality, the operating characteristics and constraints of the heating power system are analyzed, and a multi-objective optimization algorithm based on the particle swarm optimization algorithm is used to calculate the comprehensive optimization index of the optimal dispatching scheme of the heating power system. Find a trade-off solution between the two, solve the optimal dispatching plan, so that the dispatching plan is optimal while meeting all the objectives. Analyze the operating characteristics and constraints of the heating power system, including the output characteristics of the generator set, the transmission characteristics of the power grid and the change characteristics of the load, and clarify the constraints of the heating power system, including the operating constraints of the generator set, the stable operation constraints of the power grid and the charging and discharging constraints of the energy storage equipment. According to the analysis results, build an optimization model with multiple objectives. The objective functions of the optimization model include economy (minimizing operating costs), environmental protection (minimizing carbon emissions), reliability (maximizing power supply reliability) and stability (maximizing voltage and frequency stability). The constraints of the heating and power system are included to ensure the feasibility of the optimization solution. A multi-objective optimization algorithm based on the particle swarm optimization algorithm is selected to initialize the particle swarm. Each particle represents a potential scheduling plan. Through the iterative process, the speed and position of the particle are updated, that is, the decision variables in the scheduling plan are adjusted, that is, the output of the generator set and the charging and discharging status of the energy storage device. After each iteration, the fitness of the particle is evaluated, that is, the performance on each objective function, and the external archive is updated according to the Pareto dominance relationship. The maximum number of iterations is set as the termination condition. When the termination condition is met, the iteration is stopped and the Pareto optimal solution set is output, that is, the comprehensive optimization index of the optimal scheduling plan.

[0070] Furthermore, the calculation expression of the comprehensive optimization index of the optimal dispatching scheme of the heating power system is:

[0071] In the formula, It is a comprehensive optimization index for the optimal dispatching scheme of the heating power system. is the kth decision variable, such as the output of the generator set, the charging and discharging status of the energy storage device, etc. is the weight coefficient of the kth decision variable, reflecting its importance in the optimization process, is the attenuation coefficient of the kth decision variable, which is used to adjust the attenuation rate of the exponential function. is the number of decision variables, is the weight coefficient of the jth objective function, such as economic objectives, environmental protection objectives, etc. is the decision variable of the jth objective function, is the exponential coefficient of the jth objective function, which is used to adjust the nonlinearity of the objective function. is the number of objective functions, The value range is 0 to 1, indicating that the comprehensive optimization index of the optimal scheduling scheme is between 0 and 1. The closer the value is to 1, the better the scheduling scheme is. 0 indicates the worst scheme, and 1 indicates the best scheme. The increase of exponential function gradually decreases, resulting in a decrease in the numerator; at the same time, the minimum function According to the decision variables of each objective function changes with the change of, which may increase or decrease, thus affecting the value of the entire formula. The value trend of depends on the comprehensive changes of the numerator and denominator. Through the iterative optimization of the particle swarm optimization algorithm, we find Maximize the optimal scheduling solution.

[0072] In step 4, the process of dynamic load adjustment and energy storage resource allocation includes: Extract the decision variables of each energy system from the optimal scheduling plan, including the output of the generator set, the charging and discharging status of the energy storage equipment, and the load distribution ratio, and clarify the specific goals that need to be adjusted for each energy system based on the value of the decision variables, including the need to increase or decrease the output of the generator set, the need to charge or discharge the energy storage equipment, and the need to transfer or adjust the load. Analyze the determined optimal scheduling plan and the value of the decision variables, and clarify the target operating parameters of each energy system, including the adjustment of the generator set, the adjustment of the energy storage equipment, and the adjustment of the transmission and distribution equipment. Among them, the adjustment of the generator set is to adjust the output and optimize the operation mode. According to the output value of the generator set in the optimal scheduling plan, its operating parameters are automatically adjusted, such as adjusting the fuel supply The optimal operation mode is selected according to the operating characteristics of the generator set, such as operating in a high-efficiency range and avoiding frequent start and stop, so as to improve the power generation efficiency and equipment life; the energy storage device is adjusted to the charging state adjustment and the discharging state adjustment. When the optimal scheduling plan requires the energy storage device to charge, the charging program is automatically started. According to the charging characteristics of the energy storage device, the charging current and voltage are reasonably set to ensure the charging efficiency and safety. When the optimal scheduling plan requires the energy storage device to discharge, the discharging program is automatically started. According to the discharge demand and the discharge characteristics of the energy storage device, the discharge current and voltage are reasonably set to meet the needs of the power grid or Load demand; transmission and distribution equipment adjustment is transmission equipment adjustment and distribution equipment adjustment. According to the power transmission demand, the voltage and current parameters of the transmission line are adjusted to optimize the power transmission efficiency and reduce losses. According to the load distribution situation, the tap position of the distribution transformer and the operating status of the distribution line are adjusted to ensure reasonable power distribution and voltage stability. Combined with the target operating parameters of each energy system, the load is dynamically adjusted through demand-side response, load transfer and load transfer. Among them, the demand-side response system sends load adjustment signals to users to guide users to increase power load when the power supply is sufficient, and reduce power load or transfer load when the power supply is tight. According to the optimal scheduling plan The load distribution ratio in the grid is adjusted to transfer part of the load from one area or time period to another area or time period to balance the supply and demand relationship and improve the operation efficiency of the power grid. For controllable loads, such as industrial loads and some equipment in commercial loads, direct control is performed, such as starting or stopping the operation of certain equipment, adjusting the operating parameters of the equipment, etc., to meet the needs of load adjustment. According to the requirements of the optimal scheduling plan, energy storage and load coordination are carried out in combination with energy storage equipment coordination, energy storage and power generation coordination, and energy storage and load coordination. Among them, when there are multiple energy storage devices, according to the requirements of the optimal scheduling plan, the charging and discharging behaviors of each energy storage device are coordinated to make them work together to achieve the best energy storage effect and grid support capability;The operation of energy storage equipment and generator sets is optimized in coordination. For example, when the generator set output is insufficient, the energy storage equipment is discharged in time to supplement, and when the generator set output is excessive, the energy storage equipment is charged to store excess electric energy to improve energy utilization efficiency; according to the load changes and the requirements of the optimal scheduling plan, the charging and discharging strategy of the energy storage equipment is dynamically adjusted to provide stable and reliable power support for the load, smooth load fluctuations, and improve the stability and reliability of the power grid. ;

[0073] In step 5, the process of analyzing the matching degree of the scheduling strategy includes: Based on the real-time operation data of each energy system, the operation data of each energy system before and after the implementation of the dispatching strategy are extracted, including the output data of the generator set, the charging and discharging data of the energy storage equipment, the load data, the voltage and frequency data of the power grid, and the operation data of each energy system are analyzed to determine the indicators for dispatching strategy evaluation, which are economic indicators and stability indicators. Among them, economic indicators include operating costs and energy utilization efficiency, stability indicators include power grid voltage and power grid frequency, operating costs include fuel costs, equipment maintenance costs, electricity purchase costs, etc. The dispatching strategy should try to reduce costs to improve the economic benefits of the system, and improve energy utilization efficiency and reduce energy waste by optimizing scheduling, thereby reducing the unit energy use cost. The various indicators before and after the implementation of the dispatching strategy are compared and analyzed to find out the advantages and disadvantages of the dispatching strategy, and calculate the dispatching matching value to evaluate the matching degree between the dispatching strategy and the actual operation needs of the energy system. The data analysis results and the dispatch strategy matching degree analysis are integrated into an evaluation report, and the evaluation report is fed back to the manager of the energy system. The various indicator data before and after the implementation of the dispatch strategy are extracted from the monitoring system of the energy system, including the output of the generator set, the charging and discharging status of the energy storage equipment, the load data, the grid voltage and frequency, and the various indicator data are integrated and analyzed. According to the data analysis results, the advantages of the dispatch strategy in improving efficiency, reducing costs and enhancing reliability are identified, and the shortcomings of the dispatch strategy in actual operation are analyzed. At the same time, the analysis results of the matching degree between the dispatch strategy and the actual operation needs of the energy system are obtained, and an evaluation report is compiled. The analysis results of various indicators are integrated in the evaluation report. Based on the analysis results, conclusions and improvement suggestions are put forward, including adjusting the dispatch parameters and optimizing the equipment operation mode. The evaluation report is submitted to the manager of the energy system, and the feedback and suggestions of the manager are collected to further adjust the dispatch strategy.

[0074] Furthermore, the calculation expression of the scheduling matching value is:

[0075] In the formula, is the dispatch matching value, which indicates the matching degree between the dispatch strategy and the actual operation demand of the energy system. For the The weight coefficient of each economic indicator reflects its importance in the matching degree assessment. and Respectively represent The values ​​of the economic indicators before and after the implementation of the scheduling strategy, For the The adjustment coefficient of each economic indicator is used to adjust the impact of indicator changes on the matching degree. and Respectively represent the voltage values ​​before and after the scheduling strategy is implemented, and Respectively represent the frequency values ​​before and after the scheduling strategy is implemented, The value range of is 0 to 1. The closer the value is to 1, the higher the matching degree is. It means that the matching degree between the dispatch strategy and the actual operation demand of the energy system is between 0 and 1. 0 means no matching at all and 1 means perfect matching. With the improvement of the dispatch strategy in terms of economy, environmental protection and stability, the value of the numerator will increase and the value of the denominator will decrease, so that The value of gradually increases and tends to 1, indicating that the matching degree between the scheduling strategy and the actual operation demand of the energy system is continuously improving.

[0076] 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 complementary supply method of urban energy based on source, grid, load and storage, characterized in that: The following steps are involved: Step 1: Comprehensively monitor all types of energy in the urban energy system and collect relevant operating data; Step 2: Analyze the operation data based on machine learning technology to predict energy demand and output of various energy sources; Step 3: According to the results of energy demand forecast and output forecast analysis, formulate a multi-objective scheduling strategy, and use the multi-objective optimization algorithm to find the optimal scheduling solution; Step 4: Automatically adjust the operating parameters of each energy system according to the determined optimal dispatching plan, and dynamically adjust the load and allocate energy storage resources; Step 5: Evaluate the operation of the energy system and analyze the matching degree of the scheduling strategy.

2. The complementary supply method of urban energy based on source, grid, load and storage according to claim 1 is characterized by: In step 1, the process of collecting operation data includes: Identify the types of energy that need to be monitored in the urban energy system, including wind power, photovoltaic power and combustion power, and determine the operating data of each energy type, namely energy output, load demand, heating system grid status and energy storage equipment status; Deploy monitoring equipment in the urban energy system and configure the data collection frequency, where the monitoring equipment includes sensors, smart meters and data collectors; Using the deployed monitoring equipment, real-time operation data is collected from the city energy system according to the set data collection frequency; Establish a unified data platform and build a stable and reliable data transmission network to connect various monitoring equipment and data platforms; The monitoring equipment uploads the collected operation data to the data platform through the data transmission network, performs preprocessing operations on the operation data including data cleaning, format conversion and time synchronization, and integrates the operation data to form an operation data sequence.

3. The complementary supply method of urban energy based on source, grid, load and storage according to claim 2 is characterized by: In step 2, the process of energy demand forecasting and output forecasting includes: Extract the time series data of wind power, photovoltaic power and combustion power operation data from the operation data sequence, and perform feature analysis on the operation data according to the needs of energy demand forecast and output forecast; For wind power, wind speed, wind direction and wind power output are extracted as features; for photovoltaic power, light intensity, temperature and photovoltaic output are extracted as features; for combustion power, fuel consumption rate, emission concentration and thermal power output are extracted as features. The feature data set is integrated and divided into a training set and a test set. Use the training set data combined with the linear regression model to train the supply and demand model. During the training process, adjust the model parameters to optimize the prediction performance. Use the cross-validation method to evaluate the performance of the model under different parameters. Use the test data set to evaluate the trained supply and demand model and optimize the model based on the evaluation results. The supply and demand model is deployed to the actual energy management system to perform energy demand forecasting and energy output forecasting, calculate energy demand and total energy output, and analyze energy demand trends and energy output trends.

4. The complementary supply method of urban energy based on source, grid, load and storage according to claim 3 is characterized by: The calculation process of the energy demand is: For each type of energy i, calculate its output ratio at time t; Determine the demand elasticity coefficient based on the impact of energy output on demand. Multiply the output ratio of each energy source by the elasticity coefficient. The power of is used to calculate the elasticity of the output ratio to analyze the elasticity of energy output on demand. The elasticity effects of all energy sources are summed to obtain the impact of comprehensive energy output on demand; Based on the rate of demand decay over time and the rate of energy demand growth over time, the demand decay coefficient and demand growth coefficient are determined, and the time decay factor is calculated according to time t, and the comprehensive energy output impact is multiplied by the time decay factor and the demand growth coefficient. , and get the demand growth; Analyze the demand that would still exist when energy output is zero to determine the base demand, and add the demand growth to the base demand , get the energy demand at time t .

5. The complementary supply method of urban energy based on source, grid, load and storage according to claim 4 is characterized by: The calculation process of the total energy output is: The output ratio of each type of energy is calculated. Based on the output power and maximum output power of each type of energy at time t, the output ratio of wind power, photovoltaic power and combustion power at time t is calculated respectively; From the calculated output ratios of each type of energy, take the minimum output ratio to clarify the output limit of the weakest link in the energy system; Based on the influence of each energy output on the total output, determine the basic output and output elasticity coefficient, and multiply the minimum output ratio by the output elasticity coefficient. to the power of to calculate the elastic effect of each energy output on the total output; Analyze the growth rate of energy output over time, determine the output growth coefficient, and calculate the time growth factor based on time t. Multiply the output elasticity effect by the time growth factor to obtain the output growth amount; Analyze the basic output that still exists when all energy outputs are zero, determine the basic output, and add the output growth to the basic output , get the total energy output at time t .

6. The complementary supply method of urban energy based on source, grid, load and storage according to claim 5 is characterized by: In step 3, the process of finding the optimal scheduling solution includes: Clarify the multi-objective optimization goals of power dispatching, including economic goals, environmental goals, reliability goals and stability goals; Based on the results of energy demand forecast and energy output forecast, clarify the energy demand trend and energy output trend, and formulate a multi-objective dispatch strategy, including: adjusting the power generation ratio of traditional energy and new energy, optimizing the operation mode of the heating and power system, and combining energy storage technology to smooth power output; The operating characteristics and constraints of the heating and power system are analyzed, and a multi-objective optimization algorithm based on the particle swarm optimization algorithm is used to calculate the comprehensive optimization indicators of the optimal scheduling scheme of the heating and power system, find a trade-off solution between multiple objectives, and solve the optimal scheduling scheme.

7. The complementary supply method of urban energy based on source, grid, load and storage according to claim 6 is characterized by: The process of solving the optimal scheduling solution includes: Analyze the operating characteristics and constraints of the heating power system, including the output characteristics of the generator sets, the transmission characteristics of the power grid and the change characteristics of the load, and clarify the constraints of the heating power system, including the operating constraints of the generator sets, the stable operation constraints of the power grid and the charging and discharging constraints of the energy storage equipment; Based on the analysis results, an optimization model with multiple objectives is constructed. The objective functions of the optimization model include economy, environmental protection, reliability and stability, and also include the constraints of the heating and power system. Select a multi-objective optimization algorithm based on the particle swarm optimization algorithm, initialize the particle swarm, update the speed and position of the particles through an iterative process, adjust the decision variables in the scheduling scheme, evaluate the fitness of the particles after each iteration, and update the external archive according to the Pareto dominance relationship; The maximum number of iterations is set as the termination condition. When the termination condition is met, the iteration is stopped and the Pareto optimal solution set, that is, the comprehensive optimization index of the optimal scheduling scheme, is output.

8. The complementary supply method of urban energy based on source, grid, load and storage according to claim 7 is characterized by: In step 4, the process of dynamic load adjustment and energy storage resource allocation includes: Extract the decision variables of each energy system from the optimal dispatching plan, including the output of the generator set, the charging and discharging status of the energy storage equipment, and the load distribution ratio, and clarify the specific goals that need to be adjusted for each energy system based on the values ​​of the decision variables; Analyze the determined optimal dispatching scheme and the values ​​of decision variables, and clarify the target operating parameters of each energy system, including the adjustment of generator sets, energy storage equipment, and transmission and distribution equipment; Combined with the target operating parameters of each energy system, dynamic load adjustment is carried out through demand-side response, load shifting and load transfer; According to the requirements of the optimal dispatching plan, energy storage and load coordination are carried out by combining the coordination of energy storage equipment, the coordination of energy storage and power generation, and the coordination of energy storage and load.

9. The complementary supply method of urban energy based on source, grid, load and storage according to claim 8 is characterized by: In step 5, the process of analyzing the degree of matching of the scheduling strategy includes: Based on the real-time operation data of each energy system, extract the operation data of each energy system before and after the implementation of the dispatch strategy, including the output data of the generator set, the charging and discharging data of the energy storage equipment, the load data, and the voltage and frequency data of the power grid; Analyze the operating data of each energy system and determine the indicators for dispatch strategy evaluation, which are economic indicators and stability indicators. The economic indicators include operating costs and energy efficiency, and the stability indicators include grid voltage and grid frequency. Compare and analyze various indicators before and after the implementation of the dispatch strategy, find out the advantages and disadvantages of the dispatch strategy, and calculate the dispatch matching value to evaluate the matching degree between the dispatch strategy and the actual operation requirements of the energy system; The data analysis results and the dispatch strategy matching degree analysis are integrated into an evaluation report, and the evaluation report is fed back to the managers of the energy system.

10. The complementary supply method of urban energy based on source, grid, load and storage according to claim 9, characterized in that: The integrated feedback process of the evaluation report includes: Extract various indicator data before and after the implementation of the dispatch strategy from the monitoring system of the energy system, including the output of the generator set, the charging and discharging status of the energy storage equipment, the load data, the voltage and frequency of the power grid, and integrate and analyze the various indicator data; Based on the data analysis results, identify the advantages of the dispatch strategy in improving efficiency, reducing costs and enhancing reliability, analyze the shortcomings of the dispatch strategy in actual operation, and obtain the analysis results of the degree of matching between the dispatch strategy and the actual operation requirements of the energy system; Prepare an evaluation report, integrate the analysis results of various indicators in the evaluation report, and put forward conclusions and improvement suggestions based on the analysis results, including adjusting scheduling parameters and optimizing equipment operation mode; Submit the evaluation report to the managers of the energy system and collect their feedback and suggestions to further adjust the scheduling strategy.

Images