A remote control method for heating systems

Abstract

This invention relates to the field of heating system technology, and more specifically, to a remote control method for a heating system, comprising: taking any area covered by the heating system as the target area, acquiring the outdoor temperature and hot water flow rate of the target area at the current moment in real time; using the Bat Algorithm to obtain all solutions for the hot water flow rate of the target area at the current moment obtained in each iteration, and determining the fitness value of each solution for the hot water flow rate of the target area at the current moment obtained in each iteration; determining the demand degree for the next iteration after the Bat Algorithm has completed a preset number of iterations; determining whether to proceed with the next iteration based on the demand degree, and obtaining the target value of the hot water flow rate at the current moment; and realizing remote control of the heating system. This invention improves the computational efficiency and accuracy of the global optimal solution output by adaptively adjusting the number of iterations of the Bat Algorithm through demand degree calculation.

Description

Technical Field

[0001] This invention relates to the field of heating system technology. More specifically, this invention relates to a remote control method for heating systems. Background Technology

[0002] With the intensification of global climate change and the continuous rise in energy consumption, improving energy efficiency has become a global challenge, especially in the field of intelligent energy management for heating systems. In recent years, the concept of energy conservation and emission reduction has been continuously promoted in urban construction, and improving building energy efficiency has become an industry consensus. Remote control technology for heating systems, through intelligent thermal energy management models, can accurately avoid energy waste, providing key support for environmental protection and sustainable development goals.

[0003] The Bat Algorithm (BA), an emerging heuristic optimization algorithm, is based on the echolocation mechanism of bats. It solves complex optimization problems by simulating biological spatial search behavior. Applying this algorithm to heating systems can optimize energy flow paths by precisely controlling hot water flow parameters, effectively avoiding energy losses caused by overheating, and thus achieving optimal allocation of thermal resources and energy-saving goals.

[0004] However, traditional bat algorithms typically use a fixed threshold for the maximum number of iterations as the output condition for the global optimum during iterative optimization. The setting of the maximum number of iterations directly affects the algorithm's ability to avoid local optima: if the maximum number of iterations is set too small, the bat algorithm may terminate prematurely before fully exploring the solution space, causing the optimization result to stagnate at a local optimum, making it difficult to achieve ideal accuracy; if the maximum number of iterations is set too large, although it can expand the exploration dimension of the solution space and theoretically increase the probability of finding the optimal solution, it will significantly increase computation time and resource consumption, ultimately affecting the accuracy and efficiency of heating system control. Summary of the Invention

[0005] To address the issue that traditional bat algorithm iterations typically use a fixed threshold for the maximum number of iterations as the output condition for the global optimum, the setting of this maximum number of iterations directly affects the algorithm's ability to avoid local optima: if the maximum number of iterations is set too small, the bat algorithm may terminate prematurely before fully exploring the solution space, causing the optimization result to stagnate at a local optimum and making it difficult to achieve ideal accuracy; if the maximum number of iterations is set too large, although it can expand the exploration dimension of the solution space and theoretically increase the probability of finding the optimum, it will significantly increase the computation time and resource consumption, ultimately affecting the accuracy and efficiency of heating system control. Therefore, this invention proposes a remote control method for heating systems, which includes the following steps:

[0006] For any area covered by the heating system, the outdoor temperature and hot water flow rate are acquired in real time. A target value for the hot water flow rate at the current moment is obtained using the Bat Algorithm, which is used for remote control of the heating system. The target value is the optimal solution for the hot water flow rate at the time when the Bat Algorithm iteration terminates. In each iteration of the Bat Algorithm, based on each solution for the hot water flow rate at the current moment obtained in the current iteration, the average of the hot water flow rates at all historical moments with the same outdoor temperature as the current moment, the average of the hot water flow rates at all historical moments with the same time sequence as the current moment, and the hot water flow rate at the current moment obtained in the current iteration... For each solution of the hot water flow value, the corresponding heating cost is determined, and the fitness value of each solution of the hot water flow value at the current moment is determined in the current iteration. In each iteration after the Bat Algorithm has completed the preset number of iterations, the variance of the fitness values ​​of all solutions of the hot water flow value at the current moment obtained in the current iteration, the number of iterations up to the current iteration after the Bat Algorithm has completed the preset number of iterations, and the maximum and minimum values ​​of the fitness values ​​of all solutions of the hot water flow value at the current moment obtained in the current iteration and the previous several iterations are used to determine the demand for the next iteration after the current iteration is completed, and whether to proceed with the next iteration is determined based on the size of the demand.

[0007] The beneficial effects are as follows: By comprehensively considering the fitness of the current solution, the average hot water flow rate of the same outdoor temperature and time series in each iteration, as well as the heating cost, the fitness function becomes more comprehensive and accurate, enhancing the algorithm's ability to distinguish the solution space and effectively reducing the risk of getting trapped in local optima; the introduction of dynamic monitoring of fitness variance, iteration count, and historical maximum and minimum fitness values ​​allows for intelligent judgment of the necessity of the next iteration based on the algorithm's convergence state, rather than simply relying on a fixed maximum number of iterations, effectively balancing the conservation of computational resources with the improvement of optimization results; while ensuring optimization accuracy, unnecessary redundant iterations are effectively avoided, reducing computation time and resource consumption, improving the system's real-time control capabilities, and making the heating system operate more efficiently; through the improved Bat Algorithm optimization process, the heating system can autonomously adjust its optimization strategy, respond quickly to environmental changes, achieve intelligent remote management, and promote the development of energy conservation, emission reduction, and green heating.

[0008] Furthermore, the outdoor temperature and hot water flow rate values ​​are filtered and noise-reduced outdoor temperature and hot water flow rate values.

[0009] Furthermore, the filtering and denoising employs a median filtering algorithm.

[0010] Furthermore, the fitness value satisfies:

[0011] In the formula, For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. The fitness value of each solution. For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. One solution. This is the average of hot water flow rates at all historical times with the same outdoor temperature as the current time. This is the average of the hot water flow rates at all historical moments with the same time series as the current moment. For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. The corresponding heating cost for each solution. This is the standard normalization function.

[0012] The beneficial effects are as follows: The fitness function simultaneously considers the deviation between the hot water flow solution and the historical average and time series average outdoor temperatures. After standard normalization and multiplication by the fitness function, it can comprehensively reflect the rationality and economy of the solution, thus making the optimization process more targeted and practical. The fitness function directly incorporates heating costs, prompting the optimization results to not only pursue a reasonable matching of hot water flow but also take into account economic benefits. This is conducive to achieving low-energy operation of the heating system, reducing energy waste, and contributing to the achievement of green and environmental protection goals. By processing each parameter through the standard normalization function, the influence of different dimensions and numerical scales is eliminated, making the contribution of each factor balanced and fair, avoiding a single indicator dominating the optimization results, and helping to improve the convergence speed and global search capability of the algorithm.

[0013] Furthermore, the mean of the hot water flow rate values ​​at all historical moments with the same outdoor temperature as the current moment is: the mean of the hot water flow rate values ​​at all historical moments with the same outdoor temperature as the current moment and the same water temperature as the current moment's water heat flow rate value.

[0014] Furthermore, the average of the hot water flow rate values ​​of all historical moments with the same time sequence as the current moment is: the average of the hot water flow rate values ​​of all historical moments with the same time sequence as the current moment and the same water temperature as the current moment's water heat flow rate value.

[0015] Furthermore, the heating cost is the total cost of heating each solution of the current hot water flow rate value within a preset time period.

[0016] Furthermore, the required degree satisfies:

[0017] In the formula, To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The degree of need for the next iteration after the current iteration is completed. To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The variance of the fitness values ​​of all solutions for the current hot water flow rate obtained in the next iteration. To complete the preset number of iterations of the bat algorithm up to the [number]th iteration... The number of iterations in the current iteration. and These are the first iterations after the Bat Algorithm has completed the preset number of iterations. The maximum and minimum fitness values ​​among all solutions for the current hot water flow rate obtained in the current iteration and in the previous several iterations. It is a natural exponential function. This is the standard normalization function.

[0018] The beneficial effects are as follows: The demand function, by combining the variance of the fitness value, the current iteration count, and the difference between the current fitness value and the historical maximum and minimum fitness values, scientifically quantifies the demand for continuing iterations, which helps to dynamically adjust the termination conditions of the algorithm and avoids the drawbacks of the traditional fixed maximum iteration count; By utilizing the decay effect of the exponential function on the fitness variance, combined with the fitness extreme value difference, it can identify the convergence state and diversity of the current solution group, preventing the algorithm from prematurely stopping at local optima or meaningless continuous iterations, and improving the ability to fully explore the solution space; Through the normalized demand metric, the heating system optimization control can intelligently decide whether to proceed to the next iteration, rationally allocate computing resources, reduce unnecessary computing overhead, and ensure system response speed and real-time performance, making it suitable for remote and online control scenarios.

[0019] Furthermore, determining whether to proceed to the next iteration based on the demand level includes: in response to the demand level being greater than a preset iteration threshold, determining that the iteration of the Bat Algorithm is not complete and proceeding to the next iteration; otherwise, the iteration terminates.

[0020] The beneficial effects are: by setting a dynamic threshold based on demand to determine whether the iteration should continue, the inflexibility of the traditional fixed number of iterations is avoided, and the algorithm can intelligently decide when to terminate the iteration based on the actual optimization effect, thereby improving the adaptability and efficiency of the algorithm.

[0021] Furthermore, the method for remotely controlling the heating system includes: adjusting the current hot water flow rate to the target value to complete the remote control method for the heating system.

[0022] The beneficial effects are as follows: by adjusting the hot water flow rate of the target area to the optimal solution calculated by the algorithm, the optimal match between heating parameters and environment and demand is effectively ensured, improving the accuracy and comfort of heating effect; by using the optimal solution obtained by dynamic optimization using the Bat algorithm, remote control can quickly respond to environmental changes and user needs, realize real-time dynamic adjustment, and enhance the flexibility and adaptability of the system; by accurately adjusting the hot water flow rate, overheating or underheating is avoided, energy waste is reduced, heating costs are reduced, and economical and energy-saving operation is achieved, which is in line with the concept of green energy conservation.

[0023] The present invention has the following beneficial effects:

[0024] (1) Abandoning the limitations of the traditional fixed maximum number of iterations, the algorithm dynamically evaluates whether to continue iterating by "demand degree". After the preset number of iterations, it adaptively judges the necessity of iteration by combining factors such as the fitness variance of the solution and historical iteration data. This avoids falling into local optima due to insufficient iterations and prevents excessive iterations from wasting computational resources, thus significantly improving the optimization efficiency and solution accuracy of the algorithm in heating system control.

[0025] (2) The fitness value calculation integrates multiple dimensions of data such as the current solution, historical temperature and time-series corresponding average flow rate and heating cost, making the algorithm more in line with the actual operation scenario of the heating system. For example, considering the average of historical data can reduce random fluctuation interference, and incorporating heating cost directly relates to the energy-saving target, guiding the algorithm to converge toward the economical and efficient hot water flow optimal solution and optimizing the heat energy distribution strategy.

[0026] (3) Real-time acquisition of outdoor temperature and hot water flow data, combined with the dynamically adjusted bat algorithm, can quickly respond to environmental changes and optimize hot water flow in a timely manner; at the same time, through precise iterative control, the algorithm oscillation or premature stagnation is avoided, ensuring that the heating system can operate stably and efficiently under different working conditions, reducing energy waste and helping to achieve energy conservation and emission reduction goals. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating the steps of a remote control method for a heating system according to an embodiment of the present invention. Detailed Implementation

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below. The described embodiments are only a part of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0030] Please see Figure 1The diagram illustrates a flowchart of a remote control method for a heating system according to an embodiment of the present invention, the method comprising the following steps:

[0031] S01: Take any area covered by the heating system as the target area and obtain the outdoor temperature and hot water flow rate of the target area in real time at the current moment.

[0032] The implementers can set the data collection frequency according to the specific implementation situation, for example, 5 minutes / time.

[0033] Specifically, the outdoor temperature (obtained using a temperature sensor) and hot water flow rate (obtained using a flow sensor) are the outdoor temperature and hot water flow rate values ​​after filtering and noise reduction.

[0034] Specifically, the filtering and denoising uses a median filtering algorithm.

[0035] S02: Use the bat algorithm to obtain all solutions for the hot water flow rate of the target area at the current time in each iteration, and determine the fitness value of each solution for the hot water flow rate of the target area at the current time in each iteration.

[0036] Implementers can set various parameters of the bat algorithm according to the specific implementation situation. For example, the number of solutions randomly generated in the solution space in each iteration is preset to an empirical value of 50, and the solution space is preset to an empirical value. The solution space for velocity is preset to empirical values. The search frequency range is preset to The initial loudness is preset to an empirical value of 1, the loudness attenuation coefficient is preset to an empirical value of 0.95, the pulse rate is preset to an empirical value of 0.6, and the pulse enhancement coefficient is preset to an empirical value of 0.08.

[0037] It should be noted that, in order to facilitate the dynamic adaptation of the maximum number of iterations when the Bat Algorithm outputs the global optimal solution at the current moment, this step requires constructing the calculation method for the fitness value of each solution in each iteration of the Bat Algorithm. The logic underlying this construction is as follows: if the cost of the hot water flow rate corresponding to a solution is higher within a certain time period, it indicates a lower degree of optimization for this solution, and a higher corresponding fitness value; if the difference between the hot water flow rate corresponding to a solution and the average hot water flow rate at the same time (24-hour system, for example, if the current time is 12 o'clock, then the same time series are 12 o'clock on each day in the historical heating season) of the target area at the current moment is smaller, it indicates that this solution better meets the heating demand of the target area at the current moment, indicating a higher degree of optimization, and a lower fitness value (analyzed from this perspective). One can consider the characteristic that the hot water flow rate of the heating system changes over time, so that the optimal solution better matches the actual demand at the current moment. If the difference between the hot water flow rate corresponding to a solution and the average hot water flow rate of the target area at the same outdoor temperature at the current moment is smaller, it means that this solution better matches the heating demand of the target area at the current outdoor temperature, indicating that its degree of optimization is greater and its fitness value is smaller. (From this perspective, one can consider the characteristic that the hot water flow rate of the heating system changes with the outdoor temperature, so that the optimal solution better matches the actual demand at the current moment.)

[0038] In each iteration of obtaining the optimal solution using the Bat Algorithm, the fitness value of each solution of the target area at the current time is determined based on each solution of the target area at the current time, the average value of the target area at all historical times with the same outdoor temperature as the current time, the average value of the target area at all historical times with the same time sequence as the current time, and the heating cost corresponding to each solution of the target area at the current time.

[0039] Specifically, the average hot water flow rate of the target area at all historical times with the same outdoor temperature as the current time is:

[0040] The average hot water flow rate of the target area at all historical moments with the same outdoor temperature and water temperature as the current moment.

[0041] Specifically, the average hot water flow rate of the target area at all historical times with the same time sequence as the current time is:

[0042] The target region is the average hot water flow rate of all historical times that have the same time series as the current time and the same water temperature as the current time.

[0043] Specifically, the heating cost is:

[0044] The total cost of heating the target area within a preset time period for each solution of the hot water flow rate value at the current moment.

[0045] The implementers can set the duration of the time period according to the specific implementation situation, for example, 5 minutes.

[0046] Specifically, the fitness value satisfies:

[0047] ;

[0048] In the formula, For the first The target region for the next iteration is the hot water flow rate at the current moment. The fitness value of each solution. For the first The target region for the next iteration is the hot water flow rate at the current moment. One solution. This is the average hot water flow rate of the target area at all historical times when the outdoor temperature is the same as the current time. This is the average hot water flow rate of the target area at all historical times with the same time series as the current time. For the first The target region for the next iteration is the hot water flow rate at the current moment. The corresponding heating cost for each solution. This is the standard normalization function.

[0049] in, The smaller the value, the closer the solution is to the heating demand of the target area at the current outdoor temperature. The greater the degree of optimization, the smaller the fitness value; and vice versa. The smaller the value, the better the solution matches the heating demand of the target area at the current moment, the greater its degree of optimization, and the smaller its fitness value; conversely, the smaller the value, the greater the fitness value. The larger the value, the greater the cost of the solution, the lower its fitness level, and the greater its fitness value; conversely, the smaller the value, the greater the fitness value.

[0050] S03: Determine the degree of need for the next iteration after the current iteration is completed after the Bat Algorithm has completed the preset number of iterations.

[0051] It should be noted that, to ensure the algorithm has sufficient iterations to search for the global optimum in the early stages, when the algorithm outputs the global optimum at each time step, it is stipulated that after completing the initial iterations (a preset number of iterations, exemplarily 20), it dynamically determines whether further iterations are needed. Based on this, this step can analyze the diversity of all solutions and the changing characteristics of the optimal solution in each iteration to obtain the algorithm's need for the next iteration after each iteration following the initial iteration. The logic used to calculate the algorithm's need for the next iteration after each iteration following the initial iteration is as follows: if the diversity of fitness values ​​corresponding to all solutions is lower after the iteration following the initial iteration, it means that the algorithm needs to continue iteratively searching and searching in the solution space to prevent the algorithm from getting trapped in local optima, so the need for the next iteration will be greater after this iteration; if the number of iterations completed by the algorithm is lower after the iteration following the initial iteration, it means that the algorithm is more likely to be in the early stages after the current iteration, and in order to output the optimal solution more accurately, the algorithm needs to search more extensively, so the need for the next iteration will also be greater after this iteration. However, it cannot be ruled out that the algorithm might converge to the global optimum with fewer iterations when the current global optimum is output. Therefore, further analysis can be conducted to examine the changes in the fitness value corresponding to the optimal solution across multiple iterations. For example, if after the initial iteration, the fitness value of the solution is higher than that of the previous iterations... If the fitness value of the optimal solution does not show a significant decreasing trend in the next iteration (i.e., the quality of the optimal solution does not improve significantly in multiple iterations), it indicates that the algorithm is more likely to approach saturation. Therefore, iteration can be stopped earlier to avoid wasting computational resources. Thus, the demand for the next iteration will be smaller after this iteration is completed. In this embodiment, the preset number of iterations is used. .

[0052] In each iteration of the Bat Algorithm after completing the preset number of iterations, the fitness value of all solutions for the target region at the current time is determined based on the variance of the fitness values ​​of all solutions for the target region at the current time, the number of iterations up to the current iteration after completing the preset number of iterations, and the maximum and minimum fitness values ​​of all solutions for the target region at the current time in the previous several iterations with the same preset number of iterations.

[0053] Specifically, the required degree satisfies:

[0054] ;

[0055] In the formula, To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The degree of need for the next iteration in the current iteration. To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The variance of the fitness values ​​of all solutions for the target region at the current moment in the next iteration. To complete the preset number of iterations of the bat algorithm up to the [number]th iteration... The number of iterations in the current iteration. and These are the first iterations after the Bat Algorithm has completed the preset number of iterations. In the next iteration, the maximum and minimum fitness values ​​among all solutions for the target region with the same preset iteration number at the current moment, based on the hot water flow rate value. It is a natural exponential function. This is the standard normalization function.

[0056] in, The smaller the value, the better the algorithm performs in the first iteration. The lower the diversity of fitness values ​​corresponding to all solutions after the nth iteration, the more the algorithm needs to continue iterative searching in the solution space to prevent it from getting trapped in local optima. The greater the need for the next iteration after the first iteration is completed. The smaller the value, the fewer iterations the algorithm has completed after the initial iteration. This indicates that in the first iteration... After the first iteration, the greater the likelihood that the algorithm is in the early stages, the more extensive the search needs to be to output the optimal solution more accurately. Therefore, the second iteration... The demand for the next iteration will increase after the previous iteration is completed. The smaller the value, the better the algorithm performs in the first iteration. After the first iteration, if the fitness value corresponding to the optimal solution did not show a significant decreasing trend in the previous iterations (i.e., the quality of the optimal solution did not improve significantly in the multiple iterations), it indicates that the algorithm is more likely to approach saturation. Therefore, the iteration can be stopped early to avoid wasting computational resources. The need for the next iteration decreases after each iteration is completed.

[0057] S04: Determine whether to proceed with the next iteration based on the magnitude of demand, and obtain the target value of the hot water flow rate at the current moment.

[0058] Specifically, the termination of the iteration includes:

[0059] If the demand exceeds a preset iteration threshold, the iteration of the Bat Algorithm is deemed incomplete and proceeds to the next iteration; otherwise, the iteration terminates.

[0060] Implementers can set the iteration threshold according to the specific implementation situation, for example, 0.7.

[0061] S05: Enables remote control of the heating system.

[0062] The target value of the hot water flow rate at the current moment is obtained using the bat algorithm, which is then used for remote control of the heating system.

[0063] Specifically, the method for enabling remote control of the heating system includes:

[0064] The hot water flow rate of the target area at the current moment is adjusted to the hot water flow rate corresponding to the optimal solution, thus completing the remote control method for the heating system.

[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A remote control method for a heating system, characterized in that, include: For any area covered by the heating system, the outdoor temperature and hot water flow rate are obtained in real time. The target value of the hot water flow rate at the current moment is obtained using the Bat Algorithm, which is used to remotely control the heating system. The target value is the optimal solution of the hot water flow rate at the current moment when the Bat Algorithm iteration terminates. In each iteration of the Bat Algorithm, the fitness value of each solution of the hot water flow value at the current moment is determined based on each solution of the hot water flow value at the current moment obtained in the current iteration, the mean of the hot water flow values ​​at all historical moments with the same outdoor temperature at the current moment, the mean of the hot water flow values ​​at all historical moments with the same time sequence as the current moment, and the heating cost corresponding to each solution of the hot water flow value at the current moment obtained in the current iteration. In each iteration of the Bat Algorithm after completing a preset number of iterations, the fitness value of all solutions for the hot water flow rate at the current moment obtained in the current iteration is determined based on the variance of the fitness values ​​of all solutions for the hot water flow rate at the current moment obtained in the current iteration, the number of iterations up to the current iteration after the Bat Algorithm has completed a preset number of iterations, and the maximum and minimum fitness values ​​of all solutions for the hot water flow rate at the current moment obtained in the current iteration and the previous several iterations. The demand for the next iteration is then determined based on the size of the demand.

2. The remote control method for a heating system according to claim 1, characterized in that, The outdoor temperature and hot water flow rate values ​​mentioned are the filtered and noise-reduced outdoor temperature and hot water flow rate values.

3. The remote control method for a heating system according to claim 2, characterized in that, The filtering and denoising uses a median filtering algorithm.

4. The remote control method for a heating system according to claim 1, characterized in that, The fitness value satisfies: ； In the formula, For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. The fitness value of each solution. For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. One solution. This is the average of hot water flow rates at all historical times with the same outdoor temperature as the current time. This is the average of the hot water flow rates at all historical moments with the same time series as the current moment. For the first The hot water flow rate value obtained in the current moment is obtained in the iteration. The corresponding heating cost for each solution. This is the standard normalization function.

5. A remote control method for a heating system according to claim 1 or 4, characterized in that, The mean of hot water flow rates for all historical times with the same outdoor temperature as the current time is: The average of all historical hot water flow rates that have the same outdoor temperature and water temperature as the current time.

6. A remote control method for a heating system according to claim 1 or 4, characterized in that, The average of the hot water flow rates for all historical times with the same time sequence as the current time is: The average of the hot water flow rates of all historical times that have the same time sequence as the current time and the same water temperature as the current time's water heat flow rate.

7. A remote control method for a heating system according to claim 1 or 4, characterized in that, The heating cost is: The total cost of providing heating for each solution of the current hot water flow rate over a preset time period.

8. A remote control method for a heating system according to claim 1, characterized in that, The required degree is satisfied as follows: ； In the formula, To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The degree of need for the next iteration after the current iteration is completed. To determine the number of iterations after the Bat Algorithm completes the preset number of iterations. The variance of the fitness values ​​of all solutions for the current hot water flow rate obtained in the next iteration. To complete the preset number of iterations of the bat algorithm up to the [number]th iteration... The number of iterations in the current iteration. and These are the first iterations after the Bat Algorithm has completed the preset number of iterations. The maximum and minimum fitness values ​​among all solutions for the current hot water flow rate obtained in the current iteration and in the previous several iterations. It is a natural exponential function. This is the standard normalization function.

9. A remote control method for a heating system according to claim 1, characterized in that, The process of determining whether to proceed with the next iteration based on the magnitude of demand includes: If the demand exceeds a preset iteration threshold, the iteration of the Bat Algorithm is deemed incomplete and proceeds to the next iteration; otherwise, the iteration terminates.

10. A remote control method for a heating system according to claim 1, characterized in that, The heating system for remote control includes: Adjust the current hot water flow rate to the target value to complete the remote control method for the heating system.

Images