Ground source heat pump optimization method, electronic equipment and program product

Abstract

The invention discloses an optimization method of a ground source heat pump, electronic equipment and a program product, and the method comprises the steps: collecting the operation data and environment data of a ground source heat pump system in real time through an edge computing gateway deployed on site; constructing a multi-objective optimization model of the ground source heat pump system on the cloud server; solving the optimization model by adopting a self-adaptive multi-target genetic algorithm, and outputting a Pareto optimal solution set; selecting a final execution scheme from the Pareto optimal solution set according to a preset decision preference weight, generating a control instruction, and issuing the control instruction to the field executor through the edge computing gateway; the soil temperature field evolution is predicted through the buried pipe heat transfer model, and a prediction result is fed back to the optimization model and used for correcting the soil heat balance objective function, and long-term dynamic optimization is achieved. According to the method, collaborative optimization of economy, environmental protection and sustainability can be realized by constructing the multi-objective optimization model fusing the operation cost, the soil heat balance and the carbon emission.

Description

Technical Field

[0001] This invention relates to the field of ground source heat pump control methods, and in particular to an optimization method, electronic equipment, and program product for a ground source heat pump. Background Technology

[0002] Ground source heat pump systems are a renewable energy technology that efficiently utilizes shallow geothermal energy. They leverage the relatively constant temperature of the underground soil to provide heating and cooling for buildings. For large building complexes, a group control system with multiple heat pump units operating in parallel is often used to meet high load demands.

[0003] Existing group control strategies for ground source heat pump systems are mostly based on simple rules, such as time-sequence rotation control and temperature difference control. While these strategies are simple and reliable, they still suffer from drawbacks such as low intelligence, lag in dynamic load response, conflicting objectives, geothermal incompatibility, and insufficient optimization. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies, such as low level of intelligence, lag in dynamic load response, conflict of multiple objectives, geothermal incompatibility, and insufficient optimization, and to provide an optimization method, electronic equipment, and program product for ground source heat pumps.

[0005] The present invention provides an optimization method for a ground source heat pump, comprising: By deploying edge computing gateways on-site, real-time operational and environmental data of the ground source heat pump system are collected. A multi-objective optimization model for a ground source heat pump system is built on a cloud server. An adaptive multi-objective genetic algorithm is used to solve the optimization model, and the Pareto optimal solution set is output. The final execution plan is selected from the Pareto optimal solution set according to the preset decision preference weights, control commands are generated and sent to the field actuators via the edge computing gateway; The evolution of the soil temperature field is predicted by a buried pipe heat transfer model, and the prediction results are fed back to the optimization model to correct the soil heat balance objective function and achieve long-term dynamic optimization.

[0006] In one of the optional technical solutions: The objective function of the multi-objective optimization model includes at least minimizing the total operating cost of the system, minimizing the annual thermal imbalance of the soil, and minimizing the carbon emissions of the system. The constraints of the multi-objective optimization model include the equipment operating boundary and the lifetime constraint based on the equipment performance degradation model.

[0007] In one of the optional technical solutions: The life constraint of the equipment performance degradation model is determined by introducing the equipment performance degradation coefficient, which is related to the cumulative running time and number of start-ups and shutdowns of the unit. The performance degradation coefficient is obtained by dividing the actual operating time by the factory rated time.

[0008] In one of the optional technical solutions: The performance degradation coefficient can also be obtained in real time through a data-driven performance model, as follows: Continuously monitor and record the operating data of each heat pump unit; The initial performance degradation model was trained using historical running datasets from similar devices. The performance degradation coefficient is obtained by calculating the actual sample points of performance degradation using historical operating data.

[0009] In one of the optional technical solutions: The adaptive multi-objective genetic algorithm includes using a hybrid binary and real number encoding method to represent the start-up and shutdown status and load rate of the unit, and adaptively adjusting the crossover probability and mutation probability based on the degree of stagnation in population evolution.

[0010] In one of the optional technical solutions, the adaptive adjustment of crossover and mutation probabilities based on the degree of population evolution stagnation includes: Calculate the average improvement rate of the elite solution set in consecutive generations of Pareto fronts; If the average improvement rate is less than the first threshold, the crossover probability and mutation probability are increased proportionally. If the average improvement rate is greater than or equal to the second threshold, the crossover probability and mutation probability are reduced proportionally.

[0011] In one of the optional technical solutions: The adaptive multi-objective genetic algorithm is used to solve the optimization model, and the process is executed in the first cycle. The soil temperature field evolution is predicted using a buried pipe heat transfer model, and the prediction results are fed back to the optimization model for execution in the second cycle. The first cycle is shorter than the second cycle.

[0012] The present invention provides an electronic device, including a memory, a processor, and an electronic device program on the memory, wherein the processor executes the electronic device program to implement the steps of any of the aforementioned optimization methods for ground source heat pumps.

[0013] The present invention provides an electronic device readable storage medium storing an electronic device program / instruction thereon, which, when executed by a processor, implements the steps of any of the aforementioned ground source heat pump optimization methods.

[0014] The present invention provides an electronic device program product, including an electronic device program / instruction, which, when executed by a processor, implements the steps of any of the aforementioned ground source heat pump optimization methods.

[0015] The above technical solution has the following beneficial effects: The optimization method for ground source heat pumps provided by this invention achieves synergistic optimization of economy, environmental protection and sustainability by constructing a multi-objective optimization model that integrates operating cost, soil thermal balance and carbon emissions; it achieves efficient global search of complex solution space and effective avoidance of premature convergence by adopting an adaptive hybrid coding genetic algorithm; and it achieves long-term dynamic correction and forward-looking regulation of soil thermal balance by introducing a geothermal feedback mechanism based on digital twin technology. Attached Figure Description

[0016] The disclosure of this invention will become more readily understood by referring to the accompanying drawings. It should be understood that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings: Figure 1 A flowchart illustrating an optimization method for a ground source heat pump according to an embodiment of the present invention; Figure 2 A flowchart illustrating the operation of an optimized ground source heat pump system according to an embodiment of the present invention; Figure 3 A flowchart illustrating an optimization method for a ground source heat pump according to an embodiment of the present invention; Figure 4 A schematic diagram of the chromosome for an optimized method of a ground source heat pump provided in an embodiment of the present invention; Figure 5 A partial flowchart of an optimization method for a ground source heat pump provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0018] like Figure 1 The figure shown illustrates an optimization method for a ground source heat pump according to an embodiment of the present invention, comprising the following steps: Step S101: Collect real-time operating data and environmental data of the ground source heat pump system through the edge computing gateway deployed on site; Step S102: Construct a multi-objective optimization model of the ground source heat pump system on a cloud server; Step S103: Use an adaptive multi-objective genetic algorithm to solve the optimization model and output the Pareto optimal solution set; Step S104: Select the final execution scheme from the Pareto optimal solution set according to the preset decision preference weights, generate control commands and send them to the field actuators via the edge computing gateway; Step S105: Predict the evolution of the soil temperature field using the buried pipe heat transfer model, and feed the prediction results back to the optimization model to correct the soil heat balance objective function and achieve long-term dynamic optimization.

[0019] Among them, such as Figure 2 As shown, this invention is applied to an optimization system for ground source heat pumps, used for intelligent optimization control of the ground source heat pump. The system includes various sensors, actuators, and an edge computing gateway to achieve data acquisition, command issuance, and local security redundancy control. The system's cloud optimization and decision-making layer includes a cloud server, algorithm engine, digital twin model library, and database to run optimization algorithms, store historical data, and provide interactive interfaces. The edge layer and cloud layer interact with each other through an encrypted communication protocol, forming a cloud-edge collaborative architecture.

[0020] like Figure 3 As shown, step S101 is achieved through data acquisition and processing via an edge computing gateway deployed on-site.

[0021] The system monitors and acquires in real time the building's heating and cooling load demand, the inlet and outlet water temperatures of buried pipe loops in various locations, outdoor temperature and humidity, the status and power consumption of each heat pump unit in the system, and the time-of-use electricity price signal from the power grid.

[0022] Data is collected by the field PLC via the Modbus TCP protocol and uploaded to the cloud platform via the edge computing gateway using the MQTT protocol, with the collection frequency set to once every 5 minutes.

[0023] It is necessary to collect the start-up and shutdown status, power (kW), current (A), supply and return water temperature (°C), and flow rate (m³ / h) of each unit, collect the total supply and return water temperature of the underground pipe manifold, and read the total cooling / heating load of the building through the energy meter, and then connect to the network to obtain the real-time electricity price.

[0024] Distributed data acquisition at the edge layer ensures the real-time performance and integrity of system data, providing a reliable data foundation for subsequent optimization.

[0025] The multi-objective optimization model in step S102 is constructed on a cloud server.

[0026] The optimization model contains three core objective functions: Minimizing the total system operating cost is achieved by calculating the sum of the products of the total system power and the time-of-use electricity price for each time period; Minimizing the annual soil thermal imbalance is determined by calculating the ratio of the difference in heat absorption between winter and summer to the total annual heat exchange. Minimizing the carbon emissions from system operation is calculated by multiplying the total electrical power of the system by the carbon emission factor.

[0027] like Figure 4 As shown, the optimization model solution in step S103 uses an improved adaptive multi-objective genetic algorithm. This algorithm employs a hybrid binary and real-number encoding strategy, where the first part of the chromosome uses binary gene bits to represent the start-up and shutdown status of the unit, and the second part uses real-number gene bits to represent the load percentage of the started unit.

[0028] The algorithm parameters were set as follows: population size 80, maximum number of generations MaxGen = 150, initial crossover probability Pc = 0.85, and baseline mutation probability Pm_base = 0.1. The crossover and mutation probabilities were dynamically adjusted by calculating the average improvement rate Δf of the elite solution set in the Pareto front over several consecutive generations.

[0029] When Δf is less than the threshold of 0.001, the mutation probability is increased to enhance the global exploration capability; When Δf is greater than or equal to the threshold of 0.03, the mutation probability is reduced to promote local fine search.

[0030] Preferably, the chromosome length is 4+3=7. The first 4 binary genes (e.g., [1,1,0,1] represent the startup of units 1, 2, and 4). The last 3 real numbers (e.g., [0.8, 0.9, 0.6]) represent the load rates of these 3 units respectively.

[0031] The average improvement rate Δf of adaptive mutation is calculated as follows: .

[0032] in, The average improvement rate, The average fitness value of all individuals in the gen generation population (which can be the average crowding of the Pareto solution set or a weighted calculation based on ranking). The smaller the value, the slower the population improvement and the more likely it is to stagnate.

[0033] After each generation of evolution is completed, the population is calculated. Then Compare with preset thresholds α and β: like If α < α, then adjust the mutation probability: Pm = min(Pm_base *2,Pm_max) to enhance global exploration capabilities and escape local optima; like If the value is greater than or equal to β, then adjust the mutation probability: Pm = max(Pm_base / 2, Pm_min) to protect superior individuals and promote fine-grained local search. If α≤ If <β, then keep Pm=Pm_base.

[0034] Next, based on the new mutation probabilities, mutation operations are performed on the offspring population. Specifically, bit-flip mutation is used for binary coding segments in chromosomes, and real-value mutation based on Gaussian perturbation is used for real-value coding segments.

[0035] Finally, we obtain a set of Pareto optimal solutions, for example: [Solution A: Cost 300 yuan, imbalance degree 0.04, carbon emissions 500 kg].

[0036] [Solution B: Cost 280 yuan, imbalance degree 0.08, carbon emissions 450 kg].

[0037] This invention significantly improves the convergence speed and solution quality of the algorithm through an adaptive parameter adjustment mechanism, effectively avoiding premature convergence problems.

[0038] In step S104, the control decision and instruction issuance are executed based on preset decision preference weights.

[0039] System administrators can dynamically set the weights of each objective according to actual needs, such as 50% for economy, 30% for environmental protection, and 20% for sustainability.

[0040] The algorithm automatically selects the best compromise from the Pareto optimal solution set based on the weights, and generates control commands that include the specific unit start-up and shutdown status and load rate.

[0041] Preferably, the algorithm automatically selects solution C from the Pareto solution set based on the weight: cost 285 yuan, imbalance degree 0.07, carbon emissions 440 kg as the best compromise. This solution is then decoded into control commands: start units 1, 3 and 4, and set the load rates to 80%, 60% and 70% respectively.

[0042] Commands are sent to the edge gateway via the MQTT protocol, and then the inverters of each heat pump unit are controlled via the Modbus RTU protocol. This embodiment enables the system to adapt to different operational needs and scenario changes through flexible decision preference settings.

[0043] like Figure 5 As shown, the geothermal feedback and long-term correction in step S105 are implemented based on digital twin technology.

[0044] The system establishes a digital twin of the ground source heat pump system and predicts the evolution of the soil temperature field based on the line heat source model.

[0045] The initial soil temperature value is corrected every 24 hours. Based on the total heat absorbed / released by the system in the past 24 hours, the evolution trend of the soil temperature field in the future is predicted.

[0046] The prediction results are fed back to the optimization model to update the baseline value of the thermal balance objective function.

[0047] Correcting the initial soil temperature value every 24 hours effectively avoids error accumulation. Using digital twin technology, based on the total heat absorbed / released by the system over the past 24 hours and an isolinear heat source model based on the buried pipe heat transfer response model, the evolution trend of the soil temperature field over a future period is predicted. This predicted value is then fed back to the optimization model to update the thermal imbalance. This benchmark value makes it more realistic.

[0048] The modified model is as follows:

[0049] or

[0050] in, Let be the soil temperature at time t at a distance r from the center of the pipe. The initial temperature of the soil. For heat, The thermal conductivity of the soil, It is the integral variable.

[0051] The process for calculating the total heat absorbed / released is as follows: 1) Data Acquisition: Retrieve the runtime from the start time of the previous correction cycle to the current time from the system database. .

[0052] and the current average soil temperature monitored through a network of temperature sensors. With initial temperature The difference .

[0053] 2) Heat flux rate calculation: Based on the engineering approximate solution of the line heat source model, the average heat flux rate q (W / m) per unit length of the buried pipe is calculated. The calculation formula is as follows:

[0054] in, λ denoted as α, where α is the soil thermal conductivity, and r is the characteristic radial distance (usually taken as the radius of the buried pipe). γ is Euler's constant.

[0055] 3) Total heat exchange calculation: Calculate the heat flow rate. Multiply by the total length of the buried pipe and running time The total heat exchanged during that time period is obtained. :

[0056] like If >0, it is determined to be the total heat release; if If the value is less than 0, it is determined to be the total heat absorbed. This calculation yields... This will be used as the objective function of soil heat balance. The actual input value.

[0057] This invention effectively solves the problem of soil thermal response lag through a long-term dynamic correction mechanism, ensuring the foresight and accuracy of the optimization strategy.

[0058] In summary, the optimization method for ground source heat pumps provided in this embodiment of the invention achieves synergistic optimization of economy, environmental protection and sustainability by constructing a multi-objective optimization model that integrates operating cost, soil thermal balance and carbon emissions; it achieves efficient global search of complex solution space and effective avoidance of premature convergence by adopting an adaptive hybrid coding genetic algorithm; and it achieves long-term dynamic correction and forward-looking regulation of soil thermal balance by introducing a geothermal feedback mechanism based on digital twin technology.

[0059] In one embodiment: The objective function of the multi-objective optimization model includes at least minimizing the total operating cost of the system, minimizing the annual thermal imbalance of the soil, and minimizing the carbon emissions of the system. The constraints of the multi-objective optimization model include the equipment operating boundary and the lifetime constraint based on the equipment performance degradation model.

[0060] In this embodiment, the method for minimizing the total system operating cost is as follows: .

[0061] in, Let t be the total electrical power of the system during time period t. Let t be the time-of-use electricity price for period t.

[0062] The method for minimizing the annual soil thermal imbalance is as follows: .

[0063] in, To estimate the total heat absorption in winter, The total heat absorption in summer, winter and summer can all be predicted by the model. The buried pipe is regarded as a continuous linear heat source. By changing the soil temperature field, the total heat exchange required to cause this change can be deduced.

[0064] The method for minimizing the carbon emissions of system operation is as follows: .

[0065] in, Let t be the total electrical power of the system during time period t. It is a carbon emission factor.

[0066] The constraints include equipment operating boundaries, such as no more than 3 operating units, unit load rate maintained within the range of 30%-100%, underground pipe outlet water temperature greater than or equal to 5℃, start-stop interval of no less than 15 minutes, performance degradation coefficient less than 0.15, and life constraints based on the equipment performance degradation model. This invention effectively solves the problem of balancing economy, environmental protection, and sustainability in traditional control systems by establishing a multi-objective optimization model.

[0067] The system constructs a multi-objective optimization model that comprehensively considers economic efficiency, environmental friendliness, and sustainability. The operating cost objective is calculated by multiplying the real-time electricity price by the total system power to ensure economical operation. The soil thermal imbalance objective is calculated by the ratio of the difference in heat absorption between winter and summer to the total annual heat exchange to maintain soil thermal balance. The carbon emission objective is calculated by multiplying the total system power by the carbon emission factor to reduce environmental impact. Equipment operating boundary constraints include the number of operating units, load rate range, and start-stop intervals to ensure safe equipment operation. Lifespan constraints are based on an equipment performance degradation model to extend equipment lifespan.

[0068] In one embodiment: The life constraint of the equipment performance degradation model is determined by introducing the equipment performance degradation coefficient, which is related to the cumulative running time and number of start-ups and shutdowns of the unit. The performance degradation coefficient is obtained by dividing the actual operating time by the factory rated time.

[0069] In this embodiment, the performance degradation coefficient can be calculated using the formula λ = actual running time / factory rated time. The performance degradation coefficient reflects the degree of wear and tear on the equipment; as running time and the number of start-stop cycles increase, the value of λ gradually decreases. The system sets different operating strategies based on the λ value: when λ > 0.8, the equipment can operate at full load; when 0.6 < λ ≤ 0.8, the maximum load rate is limited to 80%; when λ ≤ 0.6, the equipment is used only as a standby unit. The advantage of this technical solution is that it achieves refined control based on the actual state of the equipment, effectively extending the equipment's service life and reducing maintenance costs.

[0070] In one embodiment: The performance degradation coefficient can also be obtained in real time through a data-driven performance model, as follows: Continuously monitor and record the operating data of each heat pump unit; The initial performance degradation model was trained using historical running datasets from similar devices. The performance degradation coefficient is obtained by calculating the actual sample points of performance degradation using historical operating data.

[0071] In this embodiment, multi-dimensional operational data, including cumulative running time, number of start-stop cycles, average load rate, condensing temperature, and evaporating temperature, are collected. Then, a performance degradation prediction model is trained using a random forest regression algorithm. This model can capture the non-linear relationship between each feature and performance degradation. In practical applications, the system updates the model parameters quarterly, adapting to changing equipment performance trends through incremental learning. The advantage of this technical solution is that it provides more accurate performance evaluation, enabling timely detection of equipment performance anomalies and providing decision support for preventative maintenance.

[0072] In one embodiment: The adaptive multi-objective genetic algorithm includes using a hybrid binary and real number encoding method to represent the start-up and shutdown status and load rate of the unit, and adaptively adjusting the crossover probability and mutation probability based on the degree of stagnation in population evolution.

[0073] In this embodiment, the algorithm employs an innovative hybrid encoding scheme to accurately describe the system state. For a system with n units, the first n bits of the chromosome use binary encoding to represent the start / stop status, and the last n bits use real-number encoding to represent the load rate. During the evolutionary process, the algorithm monitors population diversity indicators and convergence speed in real time, and automatically adjusts genetic parameters when evolutionary stagnation is detected. This significantly improves the algorithm's search efficiency, achieving faster convergence speed and obtaining higher quality solution sets than the standard genetic algorithm in tests.

[0074] In one embodiment, the adaptive adjustment of crossover and mutation probabilities based on the degree of population evolutionary stagnation includes: Calculate the average improvement rate of the elite solution set in consecutive generations of Pareto fronts; If the average improvement rate is less than the first threshold, the crossover probability and mutation probability are increased proportionally. If the average improvement rate is greater than or equal to the second threshold, the crossover probability and mutation probability are reduced proportionally.

[0075] In this embodiment, by comparing the improvement rate with the first threshold and the second threshold respectively, the algorithm can automatically balance between exploration and development, effectively avoiding premature convergence and improving the solution quality.

[0076] In one embodiment: The adaptive multi-objective genetic algorithm is used to solve the optimization model, and the process is executed in the first cycle. The soil temperature field evolution is predicted using a buried pipe heat transfer model, and the prediction results are fed back to the optimization model for execution in the second cycle. The first cycle is shorter than the second cycle.

[0077] In this embodiment, the optimal operating strategy is quickly solved based on the latest system status and load forecasts to ensure real-time system responsiveness. Soil temperature field evolution is predicted based on a buried pipe heat transfer model, and the heat balance objective function is corrected to ensure long-term operational stability. Two levels exchange information via a data bus: short-term optimization provides actual operating data for long-term forecasting, while long-term forecasting provides environmental parameter corrections for short-term optimization. The effectiveness of this technical solution lies in ensuring both real-time system control performance and considering the long-term impact of soil thermal inertia, achieving a balance between short-term benefits and long-term sustainability.

[0078] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0079] like Figure 6 The diagram shows a hardware structure of an electronic device according to the present invention, including a memory 602, a processor 601, and an electronic device program on the memory 602. The processor 601 executes the electronic device program to implement the steps of the optimization method of the ground source heat pump in any of the above embodiments.

[0080] Figure 6 Take the 601 processor as an example.

[0081] The electronic device may also include an input device 603 and a display device 604.

[0082] The processor 601, memory 602, input device 603 and display device 604 can be connected by a bus or other means. The figure shows an example of connection by a bus.

[0083] The memory 602, as a non-volatile electronic device readable storage medium, can be used to store non-volatile software programs, non-volatile electronic device executable programs, and modules, such as the program instructions / modules corresponding to the ground source heat pump optimization method in the embodiments of this application. The processor 601 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 602, thereby implementing the ground source heat pump optimization method in the above embodiments.

[0084] The memory 602 may include a program storage area and a data storage area. The program storage area may store an operating system and an application program required for at least one function. The data storage area may store data created based on the use of the ground source heat pump optimization method, etc. Furthermore, the memory 602 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 602 may optionally include memory remotely located relative to the processor 601, and these remote memories may be connected via a network to the apparatus performing the ground source heat pump optimization method. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0085] The input device 603 can receive user clicks and generate signal inputs related to user settings and function control of the ground source heat pump optimization method. The display device 604 may include a display screen or other display equipment.

[0086] When one or more modules are stored in the memory 602, and are run by one or more processors 601, the optimization method of the ground source heat pump in any of the above method embodiments is executed.

[0087] When the electronic device disclosed in this invention is running, it can execute all the steps of the above-mentioned optimization method for ground source heat pumps. By constructing a multi-objective optimization model that integrates operating costs, soil thermal balance, and carbon emissions, it achieves synergistic optimization of economy, environmental protection, and sustainability. By adopting an adaptive hybrid coding genetic algorithm, it achieves efficient global search of complex solution space and effective avoidance of premature convergence. By introducing a geothermal feedback mechanism based on digital twin technology, it achieves long-term dynamic correction and forward-looking regulation of soil thermal balance.

[0088] An embodiment of the present invention provides an electronic device readable storage medium storing an electronic device program / instructions, which, when executed by a processor 601, implements all the steps of the ground source heat pump optimization method as described above.

[0089] In the context of this disclosure, a storage medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The storage medium can be a machine-readable signal medium or a machine-readable storage medium. Optionally, the storage medium can be a non-transitory electronically readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD ROM), magnetic tape, floppy disk, and optical data storage device.

[0090] One embodiment of the present invention provides an electronic device program product, including an electronic device program / instruction, which, when executed by a processor, implements the steps of the ground source heat pump optimization method as described above.

[0091] By running the aforementioned electronic equipment program, all steps of the optimization method for ground source heat pumps described above can be executed. By constructing a multi-objective optimization model that integrates operating costs, soil thermal balance, and carbon emissions, synergistic optimization of economy, environmental protection, and sustainability can be achieved. By employing an adaptive hybrid coding genetic algorithm, efficient global search of complex solution spaces and effective avoidance of premature convergence can be achieved. By introducing a geothermal feedback mechanism based on digital twin technology, long-term dynamic correction and forward-looking regulation of soil thermal balance can be achieved.

[0092] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. An optimization method for a ground source heat pump, characterized in that, include: By deploying an edge computing gateway on-site, real-time operational and environmental data of the ground source heat pump system are collected. A multi-objective optimization model for a ground source heat pump system is built on a cloud server. An adaptive multi-objective genetic algorithm is used to solve the optimization model, and the Pareto optimal solution set is output. The final execution plan is selected from the Pareto optimal solution set according to the preset decision preference weights, control commands are generated and sent to the field actuators via the edge computing gateway; The evolution of the soil temperature field is predicted by a buried pipe heat transfer model, and the prediction results are fed back to the optimization model to correct the soil heat balance objective function and achieve long-term dynamic optimization.

2. The optimization method for ground source heat pumps according to claim 1, characterized in that: The objective function of the multi-objective optimization model includes at least minimizing the total operating cost of the system, minimizing the annual thermal imbalance of the soil, and minimizing the carbon emissions of the system. The constraints of the multi-objective optimization model include the equipment operating boundary and the lifetime constraint based on the equipment performance degradation model.

3. The optimization method for ground source heat pumps according to claim 2, characterized in that: The life constraint of the equipment performance degradation model is determined by introducing the equipment performance degradation coefficient, which is related to the cumulative running time and number of start-ups and shutdowns of the unit. The performance degradation coefficient is obtained by dividing the actual operating time by the factory rated time.

4. The optimization method for ground source heat pumps according to claim 3, characterized in that: The performance degradation coefficient can also be obtained in real time through a data-driven performance model, as follows: Continuously monitor and record the operating data of each heat pump unit; The initial performance degradation model was trained using historical running datasets from similar devices. The performance degradation coefficient is obtained by calculating the actual sample points of performance degradation using historical operating data.

5. The optimization method for ground source heat pumps according to claim 1, characterized in that: The adaptive multi-objective genetic algorithm includes using a hybrid binary and real number encoding method to represent the start-up and shutdown status and load rate of the unit, and adaptively adjusting the crossover probability and mutation probability based on the degree of stagnation in population evolution.

6. The optimization method for a ground source heat pump according to claim 5, characterized in that, The adaptive adjustment of crossover and mutation probabilities based on the degree of population evolutionary stagnation includes: Calculate the average improvement rate of the elite solution set in consecutive generations of Pareto fronts; If the average improvement rate is less than the first threshold, the crossover probability and mutation probability are increased proportionally. If the average improvement rate is greater than or equal to the second threshold, the crossover probability and mutation probability are reduced proportionally.

7. The optimization method for a ground source heat pump according to claim 1, characterized in that: The adaptive multi-objective genetic algorithm is used to solve the optimization model, and the process is executed in the first cycle. The soil temperature field evolution is predicted using a buried pipe heat transfer model, and the prediction results are fed back to the optimization model for execution in the second cycle. The first cycle is shorter than the second cycle.

8. An electronic device, comprising a memory, a processor, and an electronic device program on the memory, characterized in that, The processor executes the electronic device program to implement the steps of the optimization method for the ground source heat pump according to any one of claims 1-7.

9. An electronic device readable storage medium having an electronic device program / instructions stored thereon, characterized in that, When the electronic device program / instructions are executed by the processor, they implement the steps of the optimization method for the ground source heat pump as described in any one of claims 1-7.

10. An electronic device program product, comprising an electronic device program / instructions, characterized in that, When the electronic device program / instructions are executed by the processor, they implement the steps of the optimization method for the ground source heat pump as described in any one of claims 1-7.

Images