Flexible heat supply network heat supply method and system considering regional load balance

Abstract

The invention discloses a flexible heat supply network heat supply method and system considering regional load balance, and relates to the field of energy system optimization scheduling, and the method comprises the steps: uniformly deploying flow sensors in a heat supply network, installing an intelligent heat meter on a heat supply pipeline of each user, and directly measuring the heat actually used by the user; collecting heat consumption demand data of each user in real time; historical load data and data collected in real time are utilized, weather forecast and a time period are combined, the load capacity of each area is calculated by setting an area load fluctuation trend algorithm, and the heat demand of each area user is predicted; and a heat supply pipe network regulation and control algorithm is set based on the heat requirements of the users in all the areas and the load capacity of the load data, and heat supply balance between the different areas is adjusted. The problem of excessive or insufficient heat supply of some areas is avoided, reasonable distribution of heat supply requirements of all the areas is ensured, and the stability and reliability of overall heat supply are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy system optimization and scheduling, and in particular to a flexible heating network heating method and system taking regional load balancing into consideration. Background Art

[0002] With the acceleration of urbanization, centralized heating has become an important part of urban infrastructure. However, traditional centralized heating systems often use a unified standard for heat supply, ignoring the diverse needs of users in different regions. This one-size-fits-all approach not only leads to energy waste, but also fails to meet the growing personalized comfort needs of users, reduces user experience, and usually adopts a separate control method for heating control. However, this method often leads to uneven heating due to the coupling characteristics of the heating system, which in turn causes resource waste and inefficiency. In addition, with the acceleration of urbanization and the continuous growth of regional heating demand, traditional heating methods have gradually exposed various limitations, such as low economic efficiency, large initial investment, and high operating costs. Therefore, in order to improve the efficiency and economy of the heating system, ensure balanced heating and efficient and energy-saving operation, it is particularly important to study and implement a set of flexible heating network heating methods and systems that consider regional load balancing.

[0003] In addition, with the increasing application of renewable energy, how to effectively integrate these unstable energy sources has become a new challenge facing the heating system. The existing heating system lacks sufficient flexibility and is difficult to quickly respond to changes in the supply of renewable energy, resulting in low utilization of this part of clean energy. Developing a flexible heating network system that can dynamically adjust the heating strategy according to the heating needs of users in different regions has important theoretical value and application prospects for improving the current urban heating situation and promoting energy conservation and environmental protection.

[0004] For example, the existing Chinese patent with publication number CN108258679A discloses an optimization scheduling method for an electric-thermal integrated energy system taking into account the heat storage characteristics of the heating network, and utilizes the synergy of the source, network, and load to improve the level of renewable energy consumption. On the source side, decoupling is performed through electric heating equipment to determine electricity by heat; on the load side, the flexibility of thermal load is utilized to enhance the demand-side response capability; on the network side, the power grid has the characteristics of easy transmission and difficult storage, and the thermal network has the characteristics of easy storage and difficult transmission. The time delay from the heat source to the user's heating makes the heating network have natural heat storage characteristics. According to the physical structure of the thermal system, a refined thermal network model is established that takes into account the thermal dynamic characteristics of the thermal network such as heating delay and heating loss, and the complementary characteristics of the power system and the thermal system are utilized to improve the level of renewable energy consumption and enhance the flexibility of system regulation.

[0005] However, this design may increase the coupling degree of the system through the coordinated optimization of the source, network and load. Once a problem occurs in a certain link, it may affect the stability of the entire system. Although the heat storage characteristics of the thermal network are conducive to the absorption of renewable energy, it may also lead to certain extreme situations, such as a sudden increase in heating demand or insufficient heat supply, and the system is difficult to meet the heating needs of users. The establishment of a refined thermal network model needs to consider various thermal dynamic characteristics such as heating delay and heating loss, which increases the difficulty of model establishment and solution. To this end, the present invention provides a flexible thermal network heating method and system that takes into account regional load balancing. Summary of the invention

[0006] The object of the present invention is to provide a flexible heating network heating method and system taking into account regional load balancing, so as to solve the existing problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a flexible heating network heating method considering regional load balancing, comprising the following steps:

[0008] S1. Flow sensors are evenly deployed in the heating network, and smart heat meters are installed on each user's heating pipe to directly measure the actual heat used by the user;

[0009] S2, collect the heat demand data of each user in real time through sensors deployed at the user end of each area;

[0010] S3, using historical load data and real-time collected data, combined with weather forecasts and time periods, by setting a regional load fluctuation trend algorithm, calculate the load of each region and predict the heat demand of users in each region;

[0011] S4. Based on the heat demand of users in each area and the load amount of the load data, a heat supply network control algorithm is set to adjust the heat supply balance between different areas.

[0012] A further improvement of the present invention is that the historical load data is obtained by extracting the historical load data of each area within a set period of time in the past from the system database, including the hot water flow, inlet and outlet water temperatures and heating time of each user; through an integrated meteorological data interface, future weather forecast information of each area is obtained, including temperature, wind speed and humidity, and the daily temperature, wind speed and humidity are standardized and weightedly summed to obtain the daily weather impact value.

[0013] A further improvement of the present invention is that the regional load fluctuation trend algorithm takes Monday to Sunday of each week as a recording cycle, calculates the sum of the actual heat consumption demands of users in the region of each node in each recording cycle, obtains the value of the sum and the proportion of all data in the regional recording cycle, and adds one to obtain the time period adjustment factor of each node in each recording cycle, extracts the time period adjustment factor of each time node and multiplies it by the weather impact value of the corresponding date to obtain the weather impact heat regulation value of the recording cycle; takes the weighted sum of historical temperature data, the historical average heat demand of the time node in the recording cycle, and the weather impact heat regulation value of the corresponding date of the recording cycle as training data, and establishes a temperature-user demand relationship model through the SVM model, and obtains the user heat demand of each region at the future timestamp T through the temperature-user demand relationship model.

[0014] A further improvement of the present invention is that the heat supply network control algorithm is collaboratively constructed based on a particle swarm and an annealing algorithm, and the specific steps include:

[0015] S41, determining the decision variables as heating parameters, including the temperature set point, valve opening and water flow of each zone;

[0016] S42, initializing the particle swarm and randomly generating an initial set of heating parameters for each particle;

[0017] S43, setting fitness function Fd;

[0018] S44, setting a fitness threshold, selecting particles with a fitness greater than the fitness threshold, and generating a random new position for each selected particle; returning the heat consumption corresponding to the particles with a fitness less than or equal to the fitness threshold to the temperature-user demand relationship model, re-predicting the user heat demand in each area, and sending it to step S43;

[0019] S45, calculating the fitness of the new position, and calculating the absolute value of the difference between the fitness of the new position and the fitness of the old position to obtain a fitness difference value;

[0020] S46, setting a maximum fitness difference value, when the fitness difference value is less than or equal to the maximum fitness difference value, updating the position of the particle again according to the heating update probability; when the fitness difference value is greater than the maximum fitness difference value, replacing the old particle position with the new particle position;

[0021] S47. After each iteration, calculate and compare the load difference value between the actual heat consumption value of each area and the average heat consumption value. If the load difference value is greater than the set load difference index, return to step S44. If the load difference value is less than or equal to the set load difference index, terminate the iteration and output the heating parameters at this time.

[0022] A further improvement of the present invention is that the fitness function is based on a differential algorithm, combined with the output result of the regional load fluctuation trend algorithm to obtain prediction accuracy fitness and load balancing fitness, and the fitness function is obtained by weighted summation of the prediction accuracy fitness and load balancing fitness.

[0023] The present invention is further improved in that the prediction accuracy fitness is obtained by calculating the average value of the ratio of the absolute value of the difference between the predicted heat demand and the actual heat demand of each region each time and the actual heat demand, and calculating the difference between the reference value 1 and the average value of the ratio;

[0024] Assuming that the current day is the dth day in the recording cycle, the load balancing fitness is obtained by calculating the absolute value of the difference between the standard deviation of the mean of the actual total heat demand on the dth day in the historical M recording cycles in all regions and the standard deviation of the heat demand of each region currently predicted.

[0025] A further improvement of the present invention is that the heating update probability is first obtained by calculating the ratio of the fitness difference value to k×TD, and then calculating the exponential function of the ratio with e as the base, k represents the Boltzmann constant, and TD represents a gradually decreasing temperature.

[0026] A further improvement of the present invention is that the intelligent heat meter collects the user's current hot water flow and inlet and outlet water temperature difference at fixed time intervals to obtain the user's actual heat consumption; the collected data is transmitted to the central control system via a wireless network, and the system sends the collected real-time data to S3.

[0027] On the other hand, the present invention provides a flexible heating network heating system considering regional load balancing, comprising:

[0028] Equipment installation module, evenly deploy flow sensors in the heating network, and install smart heat meters on each user's heating pipe to directly measure the actual heat used by the user;

[0029] The heat demand collection module collects the heat demand data of each user in real time through sensors deployed at the user end of each area;

[0030] The heat demand forecasting module uses historical load data and real-time collected data, combined with weather forecasts and time periods, to set regional load fluctuation trend algorithms to calculate the load of each region and predict the heat demand of users in each region;

[0031] The heat supply balancing module sets a heat supply network control algorithm based on the heat demand of users in each area and the load amount of the load data to adjust the heat supply balance between different areas.

[0032] A further improvement of the present invention is that the heat demand prediction module includes a weather impact heat regulation value calculation unit and a regional load fluctuation trend algorithm unit; the weather impact heat regulation value calculation unit is used to obtain the time period adjustment factor of each node in each recording cycle through a recording cycle and then obtain the weather impact heat regulation value; the regional load fluctuation trend algorithm unit is used to establish a temperature-user demand relationship model, and obtain the user heat demand of each area at a future timestamp T through the temperature-user demand relationship model.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention firstly sets a regional load fluctuation trend algorithm and a heating network control algorithm, which can adjust the heating balance between different regions according to the heat demand and load data of different regions, effectively avoiding the problem of excess or insufficient heating in some regions; by optimizing the heating parameters, it can ensure the reasonable distribution of heating demand in each region, and improve the stability and reliability of the overall heating.

[0035] 2. By collecting user heat demand data in real time and making accurate predictions, it can ensure that users' heating needs are met at different times and under different weather conditions, thereby improving users' comfort and satisfaction. At the same time, by optimizing heating parameters and adjusting heating balance, it can reduce user complaints and dissatisfaction caused by insufficient or excessive heating.

[0036] 3. By combining particle swarm and annealing algorithm in the heating network control algorithm, the optimal solution can be effectively found in the particle swarm. At the same time, the simulated annealing algorithm is used to jump out of the local optimum and improve the global search capability, thereby realizing the precise control of regional heating demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flow chart of a flexible heating network heating method considering regional load balancing according to the present invention;

[0038] Figure 2 A flow chart of an algorithm for regional load fluctuation trend of a flexible heating network heating method considering regional load balancing according to the present invention;

[0039] Figure 3 A flow chart of a heating network control algorithm using a regional load fluctuation trend algorithm in a flexible heating network heating method taking regional load balancing into consideration in the present invention;

[0040] Figure 4 This is a framework diagram of a flexible heating network heating system that takes regional load balancing into consideration according to the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0042] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0043] Example 1

[0044] Figure 1 The flowchart of the flexible heating network heating method considering regional load balancing disclosed in this embodiment is shown, and the steps are as follows:

[0045] S1. Flow sensors are evenly deployed in the heating network, and smart heat meters are installed on each user's heating pipe to directly measure the actual amount of heat used by the user. The smart heat meter records the flow and temperature difference of hot water flowing through the user end, calculates the actual amount of heat used, and the data can be transmitted to the central control system via the wireless network.

[0046] Each heat meter should have wireless communication capabilities, such as Wi-Fi, Zigbee or LoRa, to ensure a stable data transmission connection with the central control system. The installation of smart heat meters does not require entering the user's home, avoiding privacy issues.

[0047] By directly measuring the hot water flow and temperature difference of the heating pipe, it can accurately reflect the actual heating situation of the user and ensure the high accuracy of the data. The heat meter can infer the user's heating habits by monitoring the flow and temperature difference, and the system can further optimize the heating control strategy.

[0048] S2. Through sensors deployed at the user end of each area, the heat demand data of each user is collected in real time; the smart heat meter collects the user's current hot water flow and inlet and outlet water temperature difference at fixed time intervals, such as every 5 minutes, to obtain the user's actual heat consumption; the collected data is transmitted to the central control system via a wireless network, and the system sends the collected real-time data to S3.

[0049] S3, using historical load data and real-time collected data, combined with weather forecasts and time periods, by setting a regional load fluctuation trend algorithm, calculate the load of each region and predict the heat demand of users in each region;

[0050] S4. Based on the heat demand of users in each area and the load amount of the load data, a heat supply network control algorithm is set to adjust the heat supply balance between different areas.

[0051] Example 2

[0052] Figure 2 The flowchart of the algorithm for regional load fluctuation trend of the flexible heating network heating method considering regional load balancing disclosed in this embodiment is shown, including:

[0053] The historical load data is obtained by extracting the historical load data of each region within a set time in the past (such as a heating season) from the system database. The heat load of heat users changes with conditions such as outdoor temperature, solar radiation and wind speed, and heat usage rules. The purpose of heating regulation is to make the heat generated by the heating system meet the heat needs of heat users and prevent unnecessary waste of resources. Therefore, it includes the hot water flow, inlet and outlet water temperatures and heating time of each user; through the integrated meteorological data interface, the future weather forecast information of each region is obtained, including temperature, wind speed and humidity. The daily temperature, wind speed and humidity are standardized and weighted and summed to obtain the daily weather impact value. Historical data can help the system identify load peaks in different time periods and provide a basis for more accurate load prediction and regulation.

[0054] The regional load fluctuation trend algorithm uses Monday to Sunday of each week as a recording cycle, calculates the sum of the actual heat consumption demands of users in the region at each node in each recording cycle (for example, 150kW on Monday and 130kW on Tuesday), obtains the value of the sum and the proportion of all data in the regional recording cycle (that is, the user demand from historical Monday to Sunday), and adds one to obtain the time period adjustment factor of each node in each recording cycle, extracts the time period adjustment factor of each time node and multiplies it by the weather impact value of the corresponding date to obtain the weather impact heat regulation value of the recording cycle; takes the weighted sum of historical temperature data, the average heat demand of the historical time node (that is, the day of the week) in the recording cycle, and the weather impact heat regulation value of the corresponding date of the recording cycle as training data, and establishes a temperature-user demand relationship model through the SVM model, and obtains the user heat demand of each area at the future timestamp T through the temperature-user demand relationship model.

[0055] Example 3

[0056] Figure 3 The flowchart of the heating network control algorithm using the regional load fluctuation trend algorithm in the flexible heating network heating method considering regional load balancing disclosed in this embodiment is shown. The heating network control algorithm is collaboratively constructed based on the particle swarm and annealing algorithm, and the specific steps include:

[0057] S41, determining the decision variables as heating parameters, including the temperature set point, valve opening and water flow of each zone;

[0058] S42, initializing the particle swarm and randomly generating an initial set of heating parameters for each particle;

[0059] S43, set the fitness function Fd; the fitness function is based on the differential algorithm, through the sim function, combined with the output result of the regional load fluctuation trend algorithm, to obtain the prediction accuracy fitness and the load balancing fitness, and the prediction accuracy fitness and the load balancing fitness are weighted and summed to obtain the fitness function.

[0060] The prediction accuracy fitness is obtained by calculating the average value of the ratio of the absolute value of the difference between the predicted heat demand and the actual heat demand of each region each time and the actual heat demand, and calculating the difference between the reference value 1 and the average value of the ratio. The calculation formula is: ε represents a small positive number to avoid division by zero, and N represents a total of N partitions. represents the predicted user heat demand, y i,d Indicates actual user heat demand;

[0061] Assuming that the current day is the dth day in the recording cycle, the load balancing fitness is obtained by calculating the absolute value of the difference between the standard deviation of the mean of the actual total heat demand on the dth day in the historical M recording cycles in all regions and the standard deviation of the heat demand of each region currently predicted.

[0062] By using machine learning techniques such as the SVM model, the algorithm is able to more accurately predict the user heating demand in each area at the future time stamp T. This helps reduce energy waste or shortages caused by inaccurate predictions and improve energy efficiency.

[0063] The load balancing part of the fitness function aims to optimize the load balancing by evaluating the balance of heat demand in each region. By adjusting the energy allocation strategy, the system can ensure that the demand of all regions is met while minimizing the differences between regions, thereby improving the stability and reliability of the overall system.

[0064] S44. Set the fitness threshold. Since the particle swarm algorithm has its own advantages and disadvantages, the PSO algorithm is based on group search and uses multiple particles in the group to seek the optimal result in the objective function solution space. However, if there are no particles distributed near the optimal solution at the beginning of the particle swarm algorithm or the optimal solution is skipped due to the fast convergence speed, it may fall into the local optimal solution. Therefore, the biggest defect of the PSO algorithm is premature convergence; PSO cannot provide appropriate randomness when exploring the solution space, and because there is no randomness reserved, PSO is difficult to jump out when it falls into the local optimal solution. The SA algorithm uses random search to find the best point; premature convergence occurs because the particle swarm algorithm will quickly gather near the optimal point, and the optimal point may be a local optimum. Therefore, the PSO algorithm can potentially find the global optimum, but it is also possible to fall into a local peak. Since the local optimum is not the global optimum, the particle temperature is high, so the particle can move freely in any direction, so the particles with fitness greater than the fitness threshold are selected, and a random new position is generated for each selected particle based on the SA method; the heat consumption corresponding to the particles with fitness less than or equal to the fitness threshold is returned to the temperature-user demand relationship model, and the user heat demand of each area is re-predicted and sent to step S43;

[0065] S45, calculating the fitness of the new position, and calculating the absolute value of the difference between the fitness of the new position and the fitness of the old position to obtain a fitness difference value;

[0066] S46. Set the maximum value of the fitness difference. When the fitness difference value is less than or equal to the maximum value of the fitness difference, update the position of the particle again according to the heat supply update probability. When the fitness difference value is greater than the maximum value of the fitness difference, replace the old particle position with the new particle position. The heat supply update probability is first obtained by calculating the ratio of the fitness difference value to k×TD, and then calculating the exponential function of the ratio with e as the base, where k represents the Boltzmann constant, TD represents a gradually decreasing temperature, and the step size of the reduction is set by the staff.

[0067] S47. After each iteration, calculate and compare the load difference value between the actual heat consumption value of each area and the average heat consumption value. If the load difference value is greater than the set load difference index, return to step S44. If the load difference value is less than or equal to the set load difference index, terminate the iteration and output the heating parameters at this time.

[0068] The threshold and weight may be set by default according to the present invention, or may be set by an operator.

[0069] Example 4

[0070] Figure 4The framework diagram of the flexible heating network heating system considering regional load balancing of the present invention is shown. Based on the same inventive concept as that of Embodiments 1 to 3, the present invention provides a flexible heating network heating system considering regional load balancing, including:

[0071] Equipment installation module, evenly deploy flow sensors in the heating network, and install smart heat meters on each user's heating pipe to directly measure the actual heat used by the user;

[0072] The heat demand collection module collects the heat demand data of each user in real time through sensors deployed at the user end of each area;

[0073] The heat demand forecasting module uses historical load data and real-time collected data, combined with weather forecasts and time periods, to set regional load fluctuation trend algorithms to calculate the load of each region and predict the heat demand of users in each region;

[0074] The heat supply balancing module sets a heat supply network control algorithm based on the heat demand of users in each area and the load amount of the load data to adjust the heat supply balance between different areas.

[0075] The heat demand prediction module includes a weather impact heat regulation value calculation unit and a regional load fluctuation trend algorithm unit;

[0076] The weather impact heat regulation value calculation unit is used to obtain the time period adjustment factor of each node in each recording cycle through the recording cycle and then obtain the weather impact heat regulation value;

[0077] The regional load fluctuation trend algorithm unit is used to establish an air temperature-user demand relationship model, and obtain the user heat demand of each area at a future time stamp T through the air temperature-user demand relationship model.

[0078] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A flexible heating network heating method considering regional load balancing, characterized in that: The following steps are involved: S1. Flow sensors are evenly deployed in the heating network, and smart heat meters are installed on each user's heating pipe to directly measure the actual heat used by the user; S2, collect the heat demand data of each user in real time through sensors deployed at the user end of each area; S3, using historical load data and real-time collected data, combined with weather forecasts and time periods, by setting a regional load fluctuation trend algorithm, calculate the load of each region and predict the heat demand of users in each region; S4. Based on the heat demand of users in each area and the load amount of the load data, a heat supply network control algorithm is set to adjust the heat supply balance between different areas.

2. The flexible heating network heating method considering regional load balancing according to claim 1 is characterized in that: The historical load data is obtained by extracting the historical load data of each area within a set period of time in the past from the system database, including the hot water flow, inlet and outlet water temperatures and heating time of each user; through the integrated meteorological data interface, the future weather forecast information of each area is obtained, including temperature, wind speed and humidity, and the daily temperature, wind speed and humidity are standardized and weightedly summed to obtain the daily weather impact value.

3. The flexible heating network heating method considering regional load balancing according to claim 2 is characterized in that: The regional load fluctuation trend algorithm uses Monday to Sunday of each week as a recording cycle, calculates the sum of the actual heat consumption demands of users in the region of each node in each recording cycle, obtains the value of the sum and the proportion of all data in the regional recording cycle, and adds one to obtain the time period adjustment factor of each node in each recording cycle, extracts the time period adjustment factor of each time node and multiplies it by the weather impact value of the corresponding date to obtain the weather impact heat regulation value of the recording cycle; takes the weighted sum of historical temperature data, the historical average heat demand of the time node in the recording cycle, and the weather impact heat regulation value of the corresponding date of the recording cycle as training data, and establishes a temperature-user demand relationship model through the SVM model, and obtains the user heat demand of each region at the future timestamp T through the temperature-user demand relationship model.

4. The flexible heating network heating method considering regional load balancing according to claim 3 is characterized in that: The heating network control algorithm is constructed based on the collaborative construction of particle swarm and annealing algorithm, and the specific steps include: S41, determining the decision variables as heating parameters, including the temperature set point, valve opening and water flow of each zone; S42, initializing the particle swarm and randomly generating an initial set of heating parameters for each particle; S43, setting fitness function Fd; S44, setting a fitness threshold, selecting particles with a fitness greater than the fitness threshold, and generating a random new position for each selected particle; returning the heat consumption corresponding to the particles with a fitness less than or equal to the fitness threshold to the temperature-user demand relationship model, re-predicting the user heat demand in each area, and sending it to step S43; S45, calculating the fitness of the new position, and calculating the absolute value of the difference between the fitness of the new position and the fitness of the old position to obtain a fitness difference value; S46, setting a maximum fitness difference value, when the fitness difference value is less than or equal to the maximum fitness difference value, updating the position of the particle again according to the heating update probability; when the fitness difference value is greater than the maximum fitness difference value, replacing the old particle position with the new particle position; S47. After each iteration, calculate and compare the load difference value between the actual heat consumption value of each area and the average heat consumption value. If the load difference value is greater than the set load difference index, return to step S44. If the load difference value is less than or equal to the set load difference index, terminate the iteration and output the heating parameters at this time.

5. The flexible heating network heating method considering regional load balancing according to claim 4 is characterized in that: The fitness function is based on a differential algorithm and is combined with the output result of the regional load fluctuation trend algorithm to obtain prediction accuracy fitness and load balancing fitness, and the fitness function is obtained by weighted summation of the prediction accuracy fitness and load balancing fitness.

6. The flexible heating network heating method considering regional load balancing according to claim 5 is characterized in that: The prediction accuracy fitness is obtained by calculating the average value of the ratio of the absolute value of the difference between the predicted heat demand and the actual heat demand of each region each time and the actual heat demand, and calculating the difference between the reference value 1 and the average value of the ratio; Assuming that the current day is the dth day in the recording cycle, the load balancing fitness is obtained by calculating the absolute value of the difference between the standard deviation of the mean of the actual total heat demand on the dth day in the historical M recording cycles in all regions and the standard deviation of the heat demand of each region currently predicted.

7. The flexible heating network heating method considering regional load balancing according to claim 6 is characterized in that: The heating update probability is first obtained by calculating the ratio of the fitness difference value to k×TD, and then calculating the exponential function of the ratio with e as the base, where k represents the Boltzmann constant and TD represents a gradually decreasing temperature.

8. The flexible heating network heating method considering regional load balancing according to claim 7 is characterized in that: The smart heat meter collects the user's current hot water flow and inlet and outlet water temperature difference at fixed time intervals to obtain the user's actual heat consumption; the collected data is transmitted to the central control system via a wireless network, and the system sends the collected real-time data to S3.

9. A flexible heating network heating system considering regional load balancing, used to execute the flexible heating network heating method considering regional load balancing according to any one of claims 1 to 8, characterized in that: include: Equipment installation module, evenly deploy flow sensors in the heating network, and install smart heat meters on each user's heating pipe to directly measure the actual heat used by the user; The heat demand collection module collects the heat demand data of each user in real time through sensors deployed at the user end of each area; The heat demand forecasting module uses historical load data and real-time collected data, combined with weather forecasts and time periods, to set regional load fluctuation trend algorithms to calculate the load of each region and predict the heat demand of users in each region; The heat supply balancing module sets a heat supply network control algorithm based on the heat demand of users in each area and the load amount of the load data to adjust the heat supply balance between different areas.

10. The flexible heating network heating system considering regional load balancing according to claim 9 is characterized in that: The heat demand prediction module includes a weather impact heat regulation value calculation unit and a regional load fluctuation trend algorithm unit; the weather impact heat regulation value calculation unit is used to obtain the time period adjustment factor of each node in each recording cycle through the recording cycle and then obtain the weather impact heat regulation value; The regional load fluctuation trend algorithm unit is used to establish an air temperature-user demand relationship model, and obtain the user heat demand of each area at a future time stamp T through the air temperature-user demand relationship model.

Images