Optimization Control Method of Ice Thermal Energy Storage Air Conditioning System Based on Dynamic Programming Algorithm

Abstract

The present invention discloses an optimized control method for an ice storage air-conditioning system based on a dynamic programming algorithm, including: collecting the operation data of the ice storage air-conditioning system in real time, constructing a directed graph model, directed graph nodes, and the interconnection weights between the nodes, and converting the charge and discharge operation mode transfer of the ice storage air-conditioning system within a preset optimization time domain into solving the shortest path of the directed graph model; solving the shortest path by using the dynamic programming algorithm based on the directed graph model; generating a control strategy for the ice storage air-conditioning system based on the shortest path and sending it to the system execution layer, and the control strategy includes but is not limited to the switching decision of the charge and discharge operation mode and the start-stop state of the equipment in each time period of the optimization time domain. The present invention controls the charge and discharge operation mode through the dynamic programming method to achieve efficient matching of the ice storage air-conditioning load, so as to improve the system energy efficiency, reduce the operation cost and simplify the operation and maintenance operation.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and specifically, to an optimized control method for an ice storage air-conditioning system based on a dynamic programming algorithm. Background Art

[0002] The ice storage air-conditioning system is an advanced energy utilization technology that stores cooling capacity during low electricity periods and releases it during peak electricity periods, and is widely used in large commercial buildings, industrial facilities, and public places. However, the operation mode of such systems directly affects their energy efficiency and economy.

[0003] Currently, most ice storage air-conditioning systems still rely on empirical settings for operation strategies or adopt fixed charging and discharging modes, and it is difficult to make dynamic adjustments according to real-time electricity price fluctuations, building cooling load changes, and environmental conditions. These inflexible control methods are prone to cause a decline in operation efficiency and cannot fully exert the energy-saving potential of the ice storage system.

[0004] In addition, existing methods often ignore the collaborative optimization problem between ice storage air-conditioning equipment and other subsystems of the air-conditioning system, resulting in the utilization rate of the ice storage device and the overall system performance not reaching the optimal level.

[0005] Therefore, there is an urgent need to develop a new control strategy for ice storage air-conditioning systems. Through precise optimization algorithms, the charging and discharging operation modes of the ice storage system are dynamically adjusted to improve the overall operation efficiency of the system and reduce operating costs. Summary of the Invention

[0006] One of the objectives of the embodiments of the present invention is to provide an optimized method for an ice storage air-conditioning system based on a dynamic programming algorithm, aiming to solve the problems of low energy efficiency of traditional operation strategies, complex manual adjustment, and high system operation and maintenance costs. By controlling the charging and discharging operation modes through the dynamic programming method, efficient matching of ice storage and air-conditioning load is achieved, so as to improve system energy efficiency, reduce operating costs, and simplify operation and maintenance operations, while ensuring a comfortable indoor environment and minimizing energy consumption and electricity costs.

[0007] To solve the above technical problems, in a first aspect, an optimized control method for an ice storage air-conditioning system based on a dynamic programming algorithm provided by an embodiment of the present invention includes:

[0008] Collecting the operation data of the ice storage air-conditioning system in real time, where the operation data includes but is not limited to the current remaining ice volume, outdoor wet bulb temperature, current system load, electricity price curve, and historical operation data;

[0009] Build a directed graph model, which includes directed graph nodes and the interconnection weights between the nodes, and transform the cold storage and release operation mode transfer of the ice storage air-conditioning system within a preset optimization time domain into solving the shortest path of the directed graph model;

[0010] Based on the directed graph model, use the dynamic programming algorithm to solve the shortest path;

[0011] Based on the shortest path, generate a control strategy for the ice storage air-conditioning system and send it to the system execution layer. The control strategy includes, but is not limited to, the switching decision of the cold storage and release operation mode and the start / stop state of the equipment in each time period.

[0012] Further, the method further includes:

[0013] Use the operation data to establish the state space of the ice storage air-conditioning system to feedback the state information of the system. The state information includes, but is not limited to, the current remaining ice volume, the outdoor wet bulb temperature, the current load, the energy consumption feedback value, and the electricity price.

[0014] Preferably, the step of using the dynamic programming algorithm to solve the shortest path based on the directed graph model specifically includes:

[0015] Take the current state information of the system as the initial node;

[0016] Divide the preset optimization time domain into several time periods. Each time period is used as a stage in the dynamic programming algorithm calculation, and all possible system states within each time period are used as the nodes in the path;

[0017] Use the dynamic programming algorithm to calculate the cumulative cost of each upcoming path hour by hour;

[0018] Starting from the terminal state, perform backward recursive calculation through the dynamic programming algorithm, select the path with the smallest cost from multiple upcoming paths, and finally output the hourly optimal operation mode within the preset optimization time domain.

[0019] Preferably, the step of using the dynamic programming algorithm to calculate the cumulative cost of each upcoming path hour by hour specifically includes:

[0020] Use the dynamic programming algorithm to calculate the multi-step cumulative cost J of each upcoming path. The multi-step cumulative cost J is obtained by accumulating the single-step cost g of each stage. The specific calculation formula is as follows:

[0021] ;

[0022] where k is the stage index, x k represents the system state, u k represents the decision variable, u k from stage k for a given dependence on xk is selected from the decision set U k ; N represents the total number of stages and is equal to the total number of optimization times;

[0023] The single-step cost g is calculated by the following formula:

[0024] ;

[0025] where g k,p represents the electricity price cost, which is obtained by multiplying the electricity price at stage k by the system energy consumption, and g k,com represents the comfort cost, which is determined by the chilled water outlet temperature of the chiller or the building terminal temperature.

[0026] Furthermore, the method further includes:

[0027] Real-time monitor the operating state of the system, dynamically update the state space, and recalculate the operating cost of the system. If the operating cost is higher than the preset cost threshold, immediately re-trigger the dynamic programming algorithm to generate a new optimal operating mode.

[0028] Furthermore, the method further includes:

[0029] Set the hyperparameters of the dynamic programming algorithm, specifically including:

[0030] Use the current remaining ice amount, outdoor wet-bulb temperature, and system load in the state space as the main state variables;

[0031] Adjust the weight parameter of the cost function according to the actual electricity price fluctuation curve;

[0032] Set the constraint conditions of the control strategy, and the constraint conditions of the control strategy include: the system control time interval shall not be less than 60 minutes / time, and the threshold of the remaining ice amount is set according to the total chilled water storage capacity and demand of the system.

[0033] Preferably, the mathematical description of the dynamic programming algorithm is as follows:

[0034] ;

[0035] where k is the time period index, x k represents the system state, u k represents the decision variable, and u k is selected from the decision set U k given at stage k that depends on x k ; f k represents the function of (x k , u k ) that describes the mechanism of updating the state from stage k to stage k + 1; N represents the total number of time periods, and the total number of time periods is equal to the total number of optimization times;

[0036] The cost function accumulated with the stages is denoted as g k (x k , u k ). Here, g is the single-step cost and J is the multi-step cumulative cost:

[0037] ;

[0038] By using the dynamic programming algorithm, the optimal value is obtained by minimizing the cost function of all sequences {u0, …, u N-1} that satisfy the control constraint conditions:

[0039] ;

[0040] Among them, " " represents the optimal solution of all states and decisions in the k-th stage; g k represents the single-step cost when the state is x k and the strategy u k is adopted; represents the multi-step cumulative minimum cost from stage k to stage m. Before entering the next stage from stage k, the multi-step cumulative minimum cost of all states x k,i in stage k is calculated;

[0041] The function is obtained, and the optimal control sequence starting from the initial state x0 and the corresponding state trajectory are constructed through the following formula:

[0042] ;

[0043] Among them, represents the optimal control variable in the i-th stage, arg min means finding the control strategy u i value that minimizes the subsequent expression; represents the cost from the current stage i to the next stage i + 1, which is related to the current control strategy u i value and the system state x i ; is the optimal cost function starting from stage i + 1 and based on the state x i+1 to the subsequent final stage.

[0044] In a second aspect, an embodiment of the present invention provides an optimized control system for an ice storage air-conditioning system based on a dynamic programming algorithm. The system includes:

[0045] A data acquisition module for real-time acquisition of the operation data of an ice storage air-conditioning system, where the operation data includes but is not limited to the current remaining ice volume, outdoor wet-bulb temperature, current system load, electricity price curve, and historical operation data;

[0046] A model construction module for constructing a directed graph model, where the directed graph model includes directed graph nodes and the interconnection weights between the nodes, and converting the cold storage and release operation mode transfer of the ice storage air-conditioning system within a preset optimization time domain into solving the shortest path of the directed graph model;

[0047] A calculation module for solving the shortest path based on the directed graph model using a dynamic programming algorithm;

[0048] A control module for generating a control strategy for the ice storage air-conditioning system based on the shortest path and sending it to the system execution layer, where the control strategy includes but is not limited to the switching decision of the cold storage and release operation mode and the start / stop state of the equipment in each time period.

[0049] In a third aspect, an embodiment of the present invention further provides a computing device, including a processor or calculator and a memory, where the memory is used to store a computer program, the computer program includes program instructions, and the processor or calculator is configured to call the program instructions to execute the method as described above.

[0050] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor or calculator, the processor or calculator is caused to execute the method as described above.

[0051] Compared with the prior art, an optimization control method for an ice storage air-conditioning system based on a dynamic programming algorithm provided by an embodiment of the present invention has at least the following beneficial effects:

[0052] An optimization method for an ice storage air-conditioning system based on a dynamic programming algorithm in an embodiment of the present invention optimizes the cold storage and release modes of the ice storage system through a dynamic programming algorithm, constructs a state transition model, comprehensively considers factors such as electricity price fluctuations, building cooling load requirements, and equipment operation limitations, realizes the global optimization of the system, thereby improving system energy efficiency, reducing operation costs, and simplifying operation and maintenance operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above characteristics, technical features, advantages and their implementation manners of the present invention will be further described below in a clear and understandable manner in combination with the drawings in the preferred embodiments.

[0054] Figure 1Flowchart of the optimal control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to an embodiment of the present invention;

[0055] Figure 2 Schematic diagram of the directed graph model according to an embodiment of the present invention;

[0056] Figure 3 Schematic diagram of the computing device structure of the optimal control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to an embodiment of the present invention. Detailed implementation manners

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the specific implementation manners of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts, and other implementation manners can also be obtained.

[0058] For the sake of simplicity of the drawings, only the parts related to the invention are schematically shown in each drawing, and they do not represent the actual structure of the product. In addition, for the sake of simplicity and easy understanding of the drawings, in some drawings, only one of the components with the same structure or function is schematically shown, or only one of them is marked. In this article, "one" not only means "only this one", but also means "more than one" situation.

[0059] The following mainly takes some specific embodiments as examples to detail the implementation manners of the technical solutions of the present invention.

[0060] As Figure 1 shown, in order to achieve the invention purpose of the present invention, an optimal control method for an ice storage air-conditioning system based on the dynamic programming algorithm provided by an embodiment of the present invention includes:

[0061] S1. Real-time collect the operation data of the ice storage air-conditioning system, where the operation data includes but is not limited to the current remaining ice volume, outdoor wet bulb temperature, current system load, electricity price curve, and historical operation data;

[0062] S2. Construct a directed graph model, where the directed graph model includes directed graph nodes and the interconnection weights between the nodes, and convert the cold storage and release operation mode transfer of the ice storage air-conditioning system within a preset optimization time domain into solving the shortest path of the directed graph model;

[0063] S3. Based on the directed graph model, use the dynamic programming algorithm to solve the shortest path;

[0064] S4. Generate a control strategy for the ice storage air conditioning system based on the shortest path and send it to the system execution layer. The control strategy includes, but is not limited to, the switching decision of the charging and discharging operation modes in each time period and the start-stop states of the devices.

[0065] Among them, in step S1, the operation data of the ice storage air conditioning system is collected in real time. The operation data includes the operation parameters and environmental parameters of the system, and this operation data is used as the input of the dynamic programming model.

[0066] That is, by installing data acquisition modules such as sensors, the operation parameters of the air conditioning system are collected in real time, including the cold storage capacity and cold discharge capacity of the ice storage device, as well as environmental parameters such as building cooling load, electricity price fluctuation curve, environmental temperature and humidity.

[0067] These data are cleaned and preprocessed by edge computing devices to provide accurate input for the dynamic programming model.

[0068] In step S2, the state space and directed graph model of the charging and discharging operation of the ice storage air conditioning system are established as follows:

[0069] Use the operation data to establish the state space of the ice storage air conditioning system to feedback the state information of the system. The state information includes, but is not limited to, the current remaining ice amount, outdoor wet bulb temperature, current load, energy consumption feedback value and electricity price. That is, according to the operation characteristics of the ice storage air conditioning system, a state space is established, including parameters such as the cold storage state, cooling load demand, and electricity price interval in different time periods.

[0070] A network modeling tool (such as the NetworkX library in Python) can be used to construct the operation optimization problem as a directed graph model, such as Figure 2 In, the circles represent the nodes of the directed graph, and the connection lines between different circles represent the interconnection weights between the nodes. By this method, the optimization problem of the charging and discharging operation mode of the ice storage air conditioning system within the next 12 hours is transformed into a shortest path problem.

[0071] The construction of the directed graph model specifically includes the following steps:

[0072] 1) Define state variables and establish directed graph nodes: Each node in the directed graph represents a state of the dynamic programming algorithm. The state consists of three parts:

[0073] Current remaining ice amount: Reflects the current cold storage capacity level of the system;

[0074] Outdoor wet bulb temperature: A key environmental variable that affects air conditioning load and energy consumption;

[0075] Current system load: That is, the cooling capacity demand during the current time period.

[0076] The directed edges between nodes represent the process of the system transitioning from one state to another.

[0077] 2) Define the interconnection weights between nodes: Define weights for each directed edge. The weight is the operating cost (COST) corresponding to the state transition, and its calculation method is the product of the system energy consumption and the electricity price at the current moment. The cost weight calculated by this method can reflect the comprehensive impact of energy consumption and electricity price on the operation mode.

[0078] 3) Add constraint conditions: Ensure that the remaining ice amount of the ice storage cooling system at the end of operation (the end of the optimization period) is less than the preset threshold to ensure the practical feasibility of the optimization scheme;

[0079] Ensure that the cooling storage and release capabilities of the system in each time period meet the current load demand, while following the physical limitations of the system (such as the ice amount cannot be negative).

[0080] Finally, through the above process, a directed graph model containing multiple layers of nodes is constructed, where each layer of nodes corresponds to a time period within the next 12 hours. Each path represents a possible operation mode from the initial state to the terminal state, including:

[0081] The action set, that is, the power range and duration of cooling storage or release.

[0082] Construct the objective function, with the minimization of electricity cost as the optimization goal, while constraining the system operation conditions, such as the maximum cooling storage capacity, the upper limit of equipment load, etc.

[0083] According to the building cooling load prediction, electricity price curve and system operation constraints, design the optimal cooling storage and release strategy:

[0084] That is, by modeling parameters such as load changes, cooling storage status, and electricity price fluctuations during the system operation period, dynamically generate the globally optimal decision path to guide the system to adjust the cooling storage and release mode in real time.

[0085] Preferably, based on the directed graph model, using the dynamic programming algorithm to solve the shortest path specifically includes:

[0086] Take the current state information of the system as the initial node;

[0087] Divide the preset optimization time domain into several time periods. Each time period is used as a stage in the dynamic programming algorithm calculation, and all possible system states within each time period are used as nodes in the path;

[0088] Use the dynamic programming algorithm to calculate the cumulative cost of each path that will occur hour by hour;

[0089] Starting from the terminal state, through reverse recursive calculation using the dynamic programming algorithm, select the path with the minimum cost from multiple upcoming paths, and finally output the hourly optimal operation mode within the preset optimization time domain.

[0090] For example, divide the next 12 hours into several time periods (e.g., in hours), and the possible state changes within each time period are used as nodes in the path. The transition of nodes is restricted by factors such as energy consumption, electricity price, load change, and chilled water storage capacity.

[0091] Among them, using the dynamic programming algorithm, gradually solve the optimal decision-making scheme for each time period through recursive calculation, which specifically includes the following processes:

[0092] Based on the building cooling load prediction and electricity price curve, dynamically calculate the optimal chilled water storage and release strategy for each time period;

[0093] Recursively optimize the decision-making in stages to ensure that each step of the decision complies with the overall optimal principle of the system;

[0094] Output the finally optimized operation mode, including the chilled water storage time, chilled water release time, and power distribution for each time period.

[0095] The dynamic programming algorithm is an optimization algorithm commonly used to solve multi-stage decision-making problems. It can decompose complex problems into several sub-problems and gradually solve to obtain the global optimal solution. In the optimization problem of ice storage air-conditioning systems with multiple constraints and multiple states, the dynamic programming algorithm can effectively balance multiple operation objectives, such as minimizing electricity cost and maximizing system energy efficiency. By applying the dynamic programming algorithm to the optimization of the operation mode of ice storage air-conditioning systems, it can achieve real-time response to building cooling load and electricity price changes, dynamically adjust the system's chilled water storage and release strategy, significantly improve the energy-saving effect, and can be applied to a variety of load scenarios:

[0096] High-load scenario during the day: Prioritize using the chilled water release mode to reduce peak energy consumption;

[0097] Low-load scenario at night: Prioritize using the chilled water storage mode to reduce operating costs;

[0098] Scenario with significant electricity price fluctuations: Dynamically adjust the chilled water storage and release strategy to adapt to peak-valley electricity price changes.

[0099] Preferably, the specific process of using the dynamic programming algorithm to calculate the cumulative cost of each upcoming path hour by hour includes:

[0100] Use the dynamic programming algorithm to calculate the multi-step cumulative cost J of each upcoming path. This multi-step cumulative cost J is obtained by accumulating the single-step cost g of each stage. The specific calculation formula is as follows:

[0101] ;

[0102] where k is the stage index, x k represents the system state, u k represents the decision variable, and u k is selected from the set of decisions U k given at stage k that depends on x k ; N represents the total number of stages and is equal to the total number of optimization times;

[0103] The single-step cost g is calculated by the following formula:

[0104] ;

[0105] where g k,p represents the electricity price cost, which is obtained by multiplying the electricity price at stage k by the system energy consumption, and g k,com represents the comfort cost, which is determined by the chilled water outlet temperature of the chiller or the building terminal temperature.

[0106] Furthermore, the method further includes:

[0107] Real-time monitoring of the operating state of the system, dynamically updating the state space, and recalculating the operating cost of the system. If the operating cost is higher than the preset cost threshold, the dynamic programming algorithm is immediately re-triggered to generate a new optimal operating mode.

[0108] After the system executes the control strategy, it real-time monitors the operating state, dynamically updates the remaining ice amount, outdoor wet-bulb temperature, and load data, and re-evaluates the operating cost. If significant changes occur in the external conditions (such as a sharp increase in load or a significant rise in wet-bulb temperature), the dynamic programming algorithm is immediately re-triggered to generate a new optimal operating mode.

[0109] Furthermore, the method further includes:

[0110] Performing hyperparameter settings for the dynamic programming algorithm, specifically including:

[0111] Taking the current remaining ice amount, outdoor wet-bulb temperature, and system load in the state space as the main state variables;

[0112] Adjusting the weight parameter of the cost function according to the actual electricity price fluctuation curve;

[0113] Setting the constraint conditions of the control strategy, and the constraint conditions of the control strategy include: the system control time interval shall not be less than 60 minutes / time, and the threshold of the remaining ice amount is set according to the total system chilled water storage capacity and demand.

[0114] For example: the system control time interval shall not be less than 60 minutes / time; the threshold of the remaining ice amount is set according to the total system chilled water storage capacity and demand, and generally the value range is 0%-15%.

[0115] The mathematical description of the dynamic programming algorithm is as follows:

[0116] ;

[0117] where k is the time period index, x k represents the system state, u k represents the decision variable, and u k is selected from the set of decisions U k that depends on x k at stage k; f k represents the function of (x k , u k ) and describes the mechanism for updating the state from stage k to stage k + 1; N represents the total number of time periods, and the total number of time periods is equal to the total number of optimization times;

[0118] Decisions can only be made under the state x k . For example, if stage k is in the pure chiller mode, there is no frequency setting for the ethylene glycol pump in the decision set. If it is in the ice melting mode, there is a frequency setting for the ethylene glycol pump;

[0119] The cost function that accumulates with the progress of the stage is denoted as g k (x k , u k ), where g is the single-step cost and J is the multi-step cumulative cost:

[0120] ;

[0121] The optimal value is obtained by minimizing the cost function of all sequences {u0,..., u N-1} that satisfy the control constraint conditions through the dynamic programming algorithm:

[0122] ;

[0123] In the formula, " " represents the optimal solution of all states and decisions at the k-th stage; g k represents the single-step cost of the state x k adopting the strategy u k ; represents the multi-step cumulative minimum cost from stage k to stage m. Before entering the next stage from stage k, calculate the multi-step cumulative minimum cost of all states x k,i at stage k;

[0124] k is the stage number, and g N (x N ) is the cost of k = N (i.e., the last optimization), indicating that the cumulative cost is calculated by adding up the single-step costs of each stage, and starting from the n-th stage, it is accumulated in reverse order to the k-th stage.

[0125] Obtain a function , and construct an optimal control sequence starting from the initial state x0 through the following formula and the corresponding state trajectory :

[0126]

[0127] where represents the optimal control variable at the i-th stage, arg min means to find the control strategy u that minimizes the subsequent expression i value; represents the cost from the current stage i to the next stage i + 1, which is related to the current control strategy u i value and the system state x i ; is the optimal cost function starting from stage i + 1 based on the state x i+1 to the subsequent final stage.

[0128] where the state is a combination of the current remaining ice volume, outdoor wet-bulb temperature, and current load. The first subscript of X represents the stage, and the second subscript is the number of states. Assuming there are k states in each stage, X 1,1 represents the first state of stage 1. In the embodiment of the present invention, the control duration is set to 12 hours, the time step is 1 hour, and N = 12.

[0129] In step S4, based on the shortest path, generate a control strategy for the ice storage air-conditioning system and send it to the system execution layer to dynamically adjust the operation mode to achieve the goals of minimizing the electricity cost and maximizing the system operation efficiency.

[0130] According to the optimization strategy, the operation state of the ice storage system is controlled in real time. When environmental changes (such as electricity price fluctuations, cold load prediction deviations, etc.) occur during the actual operation process, the dynamic programming algorithm will recalculate the optimization strategy based on the latest data and adjust the operation mode.

[0131] Energy efficiency evaluation and feedback optimization are used to evaluate the energy efficiency and economy of the actual operation of the ice storage system, and further optimize the parameter settings of the dynamic programming model by collecting historical data, such as the granularity of state space division, cold load prediction accuracy, etc.

[0132] The present invention optimizes the charging and discharging operation modes of an ice storage air-conditioning system by using a dynamic programming algorithm. Compared with the existing fixed strategies, it has the following remarkable advantages: By dynamically adjusting the operation strategy, the electricity cost is significantly reduced, and at the same time, the operation efficiency of the equipment is improved; The collaborative optimization of the ice storage device and other subsystems of the air-conditioning system is realized, and the overall energy-saving potential of the system is fully exerted; Based on real-time data for dynamic optimization, the system can adapt to the complex changes of building cooling load and electricity price; By flexibly adjusting the algorithm parameters and constraint conditions, it can be widely applied to ice storage air-conditioning systems of different scales and types.

[0133] In the practical application of the embodiment of the present invention in a commercial complex, a mathematical model of the system is constructed, and parameters such as ice storage capacity, air-conditioning load, and electricity price are incorporated into state variables, and an optimization function with the goal of minimizing the electricity cost is set. The dynamic programming algorithm is used, combined with the time discretization and state space discretization methods, to solve the optimization problem and generate the global optimal operation strategy of the system, that is, by dynamically adjusting the operation modes of the system (ice melting, semi-ice melting, chiller), the efficient matching of ice storage and load demand is realized, the coefficient of performance (COP) of the system is significantly improved, the electricity demand during peak electricity price periods is reduced, and the comprehensive electricity cost is significantly reduced.

[0134] The embodiment of the present invention provides an intelligent optimized operation solution for high-energy-consuming buildings through the combination of the dynamic programming algorithm and the ice storage air-conditioning system, effectively improving the energy-saving performance and economy of the system, and at the same time significantly reducing the complexity of manual operation. It is not only applicable to ice storage air-conditioning systems, but also can be extended to other types of energy storage systems, such as water storage cooling systems or heat storage systems, to achieve the energy-saving optimization goal in multiple scenarios.

[0135] In a third aspect, the embodiment of the present invention also provides a computing device, which includes a processor or calculator and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor or calculator is configured to call the program instructions to execute the method as described above.

[0136] In a fourth aspect, the embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor or calculator, the processor or calculator is caused to execute the method as described above.

[0137] As Figure 3As shown, an embodiment of the present application provides a computing device. The computing device 1000 includes a processor or calculator (not shown in the figure) 1001 and a memory 1002. The processor or calculator 1001 and the memory 1002 can be interconnected through a communication bus 1003. The communication bus 1003 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1003 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the memory 1002 is used to store a computer program. The computer program includes program instructions. The processor 1001 is configured to call the program instructions. The above program includes instructions for performing some or all of the steps included in the foregoing methods.

[0138] The processor 1001 can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the above programs.

[0139] The memory 1002 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can exist independently and be connected to the processor through a bus. The memory can also be integrated with the processor.

[0140] The computing device 1000 can further include a communication module 1004 and a display 1005. The communication module 1004 can be communicatively connected to an optical tracking device. The communication module 1004 can be a wireless communication module (such as a WiFi module, a Bluetooth module, etc.) or a wired communication module.

[0141] In addition, the computing device 1000 may further include general components such as a communication interface (such as a USB interface, a microphone interface, etc.), an antenna, etc., which will not be elaborated here.

[0142] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0143] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not elaborated in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0144] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0145] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, the functional units in the respective embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software program modules.

[0147] When the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs.

[0148] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories, random access memories, magnetic disks, or optical discs, etc.

[0149] The above has introduced the embodiments of this application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application. It should be noted that the above embodiments can be freely combined as needed.

[0150] The above is only the preferred implementation manner of the present invention. It should be pointed out that for those of ordinary skill in the art of this technology, without departing from the principle of the present invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An optimized control method for an ice storage air conditioning system based on a dynamic programming algorithm, characterized in that, The method includes: Collecting the operation data of the ice storage air-conditioning system in real time, where the operation data includes but is not limited to the current remaining ice volume, outdoor wet bulb temperature, current system load, electricity price curve, and historical operation data; Constructing a directed graph model, which includes directed graph nodes and directed edges between the nodes, where: Each node represents the state of the system within a preset optimization time domain, and the state is defined by a triple of the current remaining ice volume, outdoor wet bulb temperature, and system load; the interconnection weight between the nodes represents the operation cost corresponding to the state transition; Based on the directed graph model, calculating the shortest path by backward recursion using the dynamic programming algorithm, and transforming the cold storage and release operation state transition of the ice storage air-conditioning system within the preset optimization time domain into solving the shortest path of the directed graph model. Among them, the specific process of calculating the shortest path by backward recursion using the dynamic programming algorithm includes: Starting from the optimized terminal state at the end of the time domain, the optimal cumulative cost of each node is calculated backward stage by stage : ； where k is the stage index, x k represents the system state, u k represents the decision variable, and the state transition satisfies the constraint conditions of the decision variable: The remaining ice volume S in the (k + 1)-th stage k+1 should be less than the remaining ice volume S in the k-th stage k , or the remaining ice volume in the (k + 1)-th stage is equal to the remaining ice volume in the k-th stage. At the end of the current optimization time domain, the remaining ice volume should be less than or equal to the set threshold and the minimum control time interval for equipment startup and shutdown; Generating a control strategy for the ice storage air-conditioning system based on the shortest path and sending it to the system execution layer. The control strategy includes but is not limited to the switching decision of the cold storage and release operation mode and the start-stop state of the equipment in each time period of the optimization time domain.

2. The optimized control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to claim 1, wherein, The method further includes: Using the operation data to establish the state space of the ice storage air-conditioning system to feedback the state information of the system, where the state information includes but is not limited to the current remaining ice volume, outdoor wet bulb temperature, current load, energy consumption feedback value, and electricity price.

3. The optimized control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to claim 2, wherein The specific process of calculating the optimal cumulative cost of each node stage by stage starting from the terminal state at the end of the optimization time domain includes: Taking the current state information of the system as the initial node; Dividing the preset optimization time domain into several time periods, with each time period as a stage in the dynamic programming algorithm calculation, and all possible system states within each time period as the nodes in the path; Using the dynamic programming algorithm to calculate the cumulative cost of each upcoming path hourly; Starting from the terminal state, through backward recursion calculation using the dynamic programming algorithm, selecting the path with the minimum cost from multiple upcoming paths, and finally outputting the hourly optimal operation mode within the preset optimization time domain.

4. The optimized control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to claim 3, wherein, The specific process of using the dynamic programming algorithm to calculate the cumulative cost of each upcoming path hourly includes: Using the dynamic programming algorithm to calculate the multi-step cumulative cost J of each upcoming path, and the multi-step cumulative cost J is obtained by accumulating the single-step cost g of each stage. The specific calculation formula is as follows: ； where k is the stage index, x k represents the system state, u k represents the decision variable, u k is selected from the set of decisions U k given at stage k and depending on x k ; N represents the total number of stages and is equal to the total number of optimization times; The single-step cost g is calculated by the following formula: ； Among them, g k,p represents the electricity price cost, which is obtained by multiplying the electricity price in the k stage by the system energy consumption. g k,com represents the comfort cost, which is determined by the chilled water outlet temperature of the chiller or the temperature at the building terminal.

5. The optimized control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to claim 2, wherein The method further includes: Real-time monitoring the operation state of the system, dynamically updating the state space, and recalculating the operation cost of the system. If the operation cost is higher than the preset cost threshold, immediately trigger the dynamic programming algorithm again to generate a new optimal operation mode.

6. The optimized control method for an ice storage air-conditioning system based on the dynamic programming algorithm according to claim 2, wherein The method further includes: Performing hyperparameter settings on the dynamic programming algorithm, specifically including: Taking the current remaining ice volume, outdoor wet bulb temperature, and system load in the state space as the main state variables; Adjusting the weight parameter of the cost function according to the actual electricity price fluctuation curve; Setting the constraint conditions of the control strategy, where the constraint conditions of the control strategy include: the system control time interval shall not be less than 60 minutes / time, and the threshold of the remaining ice volume is set according to the total cold storage capacity and demand of the system.

7. An optimized control system for an ice storage air-conditioning system based on a dynamic programming algorithm, characterized in that The system includes: A data acquisition module, which is used to collect the operation data of the ice storage air-conditioning system in real time, and the operation data includes but is not limited to the current remaining ice volume, outdoor wet bulb temperature, current system load, electricity price curve and historical operation data; A model construction module, which is used to construct a directed graph model. The directed graph model includes directed graph nodes and directed edges between the nodes, where: Each node represents the state of the system within a preset optimization time domain, and the state is defined by a triple of the current remaining ice volume, outdoor wet bulb temperature and system load; the interconnection weight between the nodes represents the operation cost corresponding to the state transition; A calculation module, which is used to recursively calculate the shortest path in reverse based on the directed graph model through a dynamic programming algorithm, and convert the cold storage and release operation state transition of the ice storage air-conditioning system within a preset optimization time domain into solving the shortest path of the directed graph model. Among them, the specific process of recursively calculating the shortest path in reverse through the dynamic programming algorithm includes: Starting from the optimized terminal state at the end of the time domain, calculate the optimal cumulative cost of each node in reverse order stage by stage : ； where k is the stage index, x k represents the system state, u k represents the decision variable, and the state transition satisfies the constraint conditions of the decision variable: The remaining ice volume S in the (k + 1)-th stage k+1 should be less than the remaining ice volume S in the k-th stage k , or the remaining ice volume in the (k + 1)-th stage is equal to that in the k-th stage. At the end of this optimization time domain, the remaining ice volume should be less than or equal to the set threshold and the minimum control time interval for equipment startup and shutdown; A control module, which is used to generate a control strategy for the ice storage air-conditioning system based on the shortest path and send it to the system execution layer. The control strategy includes but is not limited to the switching decision of the cold storage and release operation mode and the start-stop state of the equipment in each time period.

8. A computing device, characterized in that, The computing device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

Images