Semantic constraint-based energy storage cabinet EMS adaptive energy scheduling method

Abstract

The embodiment of the invention discloses an energy storage cabinet EMS adaptive energy scheduling method based on semantic constraint, and relates to the technical field of intelligent control. The method comprises the following steps: encoding industrial design elements, thermal rules and economic targets related to a target energy storage cabinet into a semantic constraint dictionary, and constructing a target semantic library; taking the semantic constraint dictionary as a boundary condition, carrying out rolling solution by adopting a multi-objective optimization algorithm, and generating an optimal scheduling strategy comprising a charging and discharging strategy and temperature control setting parameters; loading the optimal scheduling strategy, and collecting SOC, temperature and countercurrent power of the target energy storage cabinet; comparing the SOC, the temperature and the countercurrent power with a preset condition, and performing real-time fine adjustment according to a comparison result; when monitoring that the system runs abnormally, triggering a semantic rollback mechanism, switching to a standby scheduling strategy, and reporting an abnormal event at the same time; and updating the multi-target coupling model based on historical operation data, and adjusting weight parameters of the semantic constraint dictionary so as to realize adaptive optimization of a scheduling strategy.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and more specifically, to an adaptive energy scheduling method for energy storage cabinets (EMS) based on semantic constraints. Background Technology

[0002] Energy storage cabinets are an important component of modern energy management systems. They are primarily used to store electrical energy and release it when needed, thereby balancing power supply and demand, improving grid stability, and optimizing energy utilization efficiency. With the rapid development of new energy technologies, the application scenarios for energy storage cabinets are becoming increasingly widespread.

[0003] An EMS (Energy Management System) is an intelligent control system that integrates hardware and software, specifically designed to monitor, control, and optimize the operation of single or multiple integrated energy storage units (typically forming a small to medium-sized energy storage system). It manages the charging (storage) and discharging (release) processes of electrical energy, ensuring the system operates safely, stably, and efficiently, and maximizing economic benefits.

[0004] However, traditional energy management strategies for energy storage cabinets (EMS) mostly rely on fixed rules or experience models, making it difficult to cope with complex and ever-changing actual operating conditions (such as different demand control parameters or adaptive designs for different installation environments) and changes in the external environment (such as ambient temperature). Furthermore, they lack the ability to adaptively manage based on their own design. Therefore, it is necessary to design a more intelligent and flexible energy dispatching method for energy storage cabinets to improve their adaptability and management efficiency in different application scenarios. Summary of the Invention

[0005] To achieve the above objectives, embodiments of this specification provide an adaptive energy scheduling method for energy storage cabinets (EMS) based on semantic constraints. This method includes: The industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet are encoded into a semantic constraint dictionary. Then, a target semantic library corresponding to the target energy storage cabinet is constructed based on the semantic constraint dictionary. Using the semantic constraint dictionary as boundary conditions, a multi-objective optimization algorithm is used for rolling solution to generate an optimal scheduling strategy that includes charging and discharging strategies and temperature control setting parameters; The optimal scheduling strategy is loaded, and the SOC, temperature, and reverse current power of the target energy storage cabinet are collected in real time. The SOC, temperature, and reverse current power are compared with preset conditions, and then the optimal scheduling strategy is fine-tuned in real time based on the comparison results. When an abnormal system operation is detected, a semantic rollback mechanism is triggered to switch to a suboptimal backup scheduling strategy and report the abnormal event. The multi-objective coupling model is updated based on historical operational data, and the weight parameters of the semantic constraint dictionary are automatically adjusted to achieve adaptive optimization of the scheduling strategy.

[0006] In some embodiments, the industrial design elements include cabinet dimensions, temperature control method, cabinet color, heat dissipation fin angle, and air inlet and outlet direction. The thermal rules are used to describe the constraints that the target energy storage cabinet needs to follow in the thermal management process and the physical laws related to the industrial design elements. The economic objectives include peak-valley arbitrage revenue, demand control parameters, and backflow prevention indicators.

[0007] In some embodiments, encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary includes: mapping the industrial design elements to physical parameters related to the thermal management of the energy storage cabinet, and quantifying the economic objectives into a revenue function, wherein the physical parameters include thermal resistance coefficient and wind resistance coefficient, and the physical parameters are obtained by mapping the industrial design elements according to the thermal rules. 4. The semantically constrained EMS adaptive energy dispatch design method for energy storage cabinets as described in claim 3, characterized in that the thermal resistance coefficient is obtained based on the following formula: in, This represents the thermal resistance coefficient corresponding to the target energy storage cabinet, which is used to reflect the total resistance of the target energy storage cabinet during the heat dissipation process; This represents the normalization operation; The effective heat dissipation area of ​​the target energy storage cabinet is obtained based on the cabinet dimensions. The convective heat transfer coefficient of the target energy storage cabinet is obtained based on the temperature control method, the angle of the heat dissipation fins, and the direction of air inlet and outlet. The radiative heat transfer coefficient corresponding to the target energy storage cabinet is obtained based on the color of the cabinet. The drag coefficient is obtained based on the following formula: in, This represents the drag coefficient corresponding to the target energy storage cabinet, which reflects the flow resistance when air flows through the target energy storage cabinet. This represents the normalization operation; This represents the basic drag coefficient corresponding to the target energy storage cabinet, which is obtained based on the cabinet dimensions.

[0008] In some embodiments, the revenue function is as follows: in, Represents total revenue; This indicates the profit from peak-valley arbitrage. This represents the cost corresponding to the anti-backflow indicator; This indicates the electricity price during peak hours. This indicates the electricity price during off-peak hours; Indicates the amount of discharge. Indicates the amount of charge. , For energy storage efficiency; and Determined based on the aforementioned demand control parameters.

[0009] In some embodiments, the multi-objective optimization algorithm includes an improved NSGA-III algorithm. The step of using the semantic constraint dictionary as boundary conditions and employing a multi-objective optimization algorithm for rolling solution to generate an optimal scheduling strategy including charging / discharging strategies and temperature control setting parameters includes: A thermal risk function is constructed based on the demand control parameters, the thermal resistance coefficient, and the wind resistance coefficient. The optimal solution on the Pareto front is obtained by rolling the solution with the goal of minimizing the thermal risk function and / or maximizing the benefit function. The optimal solution on the Pareto front is then used to generate the charging and discharging strategy and temperature control setting parameters corresponding to the target time period.

[0010] In some embodiments, the thermal risk function is as follows: in, Indicates the thermal risk value; Indicates ambient temperature; This indicates the demand control parameters. Indicates the first The window demand parameter corresponding to each charge / discharge time window Indicates the first The duration corresponding to each charge / discharge time window Indicates the total number of charge / discharge time windows; Indicates the loss coefficient; This represents the thermal resistance coefficient corresponding to the target energy storage cabinet. This indicates the drag coefficient corresponding to the target energy storage unit; These are the conversion factors; This indicates the safe temperature threshold of the target energy storage cabinet.

[0011] In some embodiments, comparing the SOC, temperature, and reverse current power with preset conditions, and then fine-tuning the optimal scheduling strategy in real time based on the comparison results, includes: A PID control algorithm is used to calculate the deviations of the SOC, temperature, and reverse current power, and the charging and discharging power and the operating parameters of the temperature control device are dynamically adjusted based on the calculation results to ensure that the system operating state is closer to the preset conditions.

[0012] In some embodiments, the criteria for determining abnormal system operation include: the difference between the actual temperature and the safe temperature threshold is greater than 3°C or the reverse current power at the grid connection point exceeds 0.5% of the rated power.

[0013] In some embodiments, updating the multi-objective coupling model based on historical running data and automatically adjusting the weight parameters of the semantic constraint dictionary to achieve adaptive optimization of the scheduling strategy includes: training the historical running data using machine learning methods to update the parameters of the multi-objective coupling model and feeding back to adjust the weights of each semantic constraint dictionary in the target semantic library.

[0014] The beneficial effects of the semantically constrained adaptive energy dispatch design method for energy storage cabinets (EMS) provided in this specification include at least the following: by encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, using the semantic constraint dictionary as boundary conditions, and employing a multi-objective optimization algorithm for rolling solution, an optimal dispatch strategy containing charging and discharging strategies and temperature control setting parameters is generated. Then, during the loading of the optimal dispatch strategy, system operation anomalies are monitored in real time, and the multi-objective coupling model is updated based on the operation data corresponding to the anomaly events. This allows the energy storage cabinet (EMS) to automatically generate an energy dispatch strategy that adapts to its own design elements and to achieve adaptive optimization of the dispatch strategy based on actual operating conditions, thereby greatly improving the adaptability and management efficiency of the energy storage cabinet in different application scenarios.

[0015] Additional features will be set forth in part in the description which follows. They will become apparent to those skilled in the art upon consulting the following description and the accompanying drawings, or may be learned by the generation or operation of examples. The features of this specification can be realized and obtained through practice or by using various aspects of the methods, tools, and combinations illustrated in the following detailed examples. Attached Figure Description

[0016] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein: Figure 1 This is a schematic diagram illustrating an exemplary application scenario of a semantically constrained EMS adaptive energy dispatching system for energy storage cabinets, according to some embodiments of this specification. Figure 2 This is an exemplary block diagram of a semantically constrained energy storage cabinet EMS adaptive energy dispatching system according to some embodiments of this specification; Figure 3 This is an exemplary flowchart of an adaptive energy scheduling method for an energy storage cabinet EMS based on semantic constraints, as shown in some embodiments of this specification. Detailed Implementation

[0017] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0018] It should be understood that the terms "system," "device," "unit," and / or "module" as used in this specification are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0019] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0021] The following describes in detail, with reference to the accompanying drawings, the semantically constrained EMS adaptive energy dispatch design method and system for energy storage cabinets provided in the embodiments of this specification.

[0022] Figure 1 This is a schematic diagram illustrating an exemplary application scenario of an EMS adaptive energy dispatching system for energy storage cabinets based on semantic constraints, as shown in some embodiments of this specification.

[0023] Reference Figure 1In some embodiments, the application scenario 100 of the semantically constrained energy storage cabinet EMS adaptive energy dispatch design system may include a data acquisition device 110, a storage device 120, a processing device 130, a management terminal 140, a network 150, and an energy storage cabinet 160. The various components in application scenario 100 can be connected in multiple ways. For example, the data acquisition device 110 can be connected to the storage device 120 and / or the processing device 130 via the network 150, or it can be directly connected to the storage device 120 and / or the processing device 130. As another example, the storage device 120 can be directly connected to the processing device 130 or connected via the network 150. Similarly, the management terminal 140 can be connected to the storage device 120 and / or the processing device 130 via the network 150, or it can be directly connected to the storage device 120 and / or the processing device 130.

[0024] The data acquisition device 110 can be used to acquire the operating status parameters of the energy storage cabinet 160, such as key data like charging and discharging current, voltage, temperature, SOC (State of charge), and reverse current power. Specifically, in this embodiment, the energy storage cabinet 160 can be equipped with a meter (e.g., a bidirectional meter) and various sensors (e.g., temperature sensors, current sensors, voltage sensors, etc.), which can monitor the operating status parameters of each battery module in the energy storage cabinet in real time.

[0025] In the embodiments of this application, the data acquisition device 110 can obtain relevant data by connecting to these sensors and meters, or transmit the data to the processing device 130 for further analysis to obtain the required data. For example, in some embodiments of this application, the data collected by the current sensor can be transmitted to the processing device 130, and then the charging and discharging current collected by the current sensor can be calculated based on the Coulomb counting method to obtain the aforementioned SOC data. As another example, in some embodiments of this application, the data collected by the voltage sensor can also be transmitted to the processing device 130, and then the SOC can be estimated by measuring the relationship between the battery voltage and the nominal voltage. Yet another example, in some embodiments of this application, the data collected by the aforementioned meters can also be transmitted to the processing device 130, and then the aforementioned reverse current power can be obtained by calculating the ratio of reverse metering data to forward metering data.

[0026] In some embodiments, the data processed by the processing device 130 and the data collected by the sensors can be stored in the storage device 120, and the data acquisition device 110 can obtain the corresponding data from the storage device 120 to obtain the operating status parameters of the energy storage cabinet 160.

[0027] In some embodiments, the data acquisition device 110 can send the acquired operating status parameters of the energy storage cabinet 160 to the processing device 130, management terminal 140, etc., via the network 150. In some embodiments, the processing device 130 can further process the operating status parameters of the energy storage cabinet 160 acquired by the data acquisition device 110. For example, the processing device 130 can determine whether there is an operational abnormality in the energy storage cabinet 160 based on the operating status parameters, and perform corresponding energy scheduling operations when an operational abnormality is detected.

[0028] Network 150 can facilitate the exchange of information and / or data. Network 150 may include any suitable network capable of facilitating the exchange of information and / or data in application scenario 100. In some embodiments, at least one component of application scenario 100 (e.g., data acquisition device 110, storage device 120, processing device 130, management terminal 140) can exchange information and / or data with at least one other component in application scenario 100 via network 150. For example, processing device 130 can obtain operating status parameters collected for energy storage cabinet 160 from data acquisition device 110 and / or storage device 120 via network 150. As another example, processing device 130 can obtain user operation instructions from management terminal 140 via network 150. Exemplary operation instructions may include, but are not limited to, retrieving operating status parameters of energy storage cabinet 160, reading abnormal system operation conditions of energy storage cabinet 160 determined based on the operating status parameters of energy storage cabinet 160, etc.

[0029] In some embodiments, network 150 can be any form of wired or wireless network, or any combination thereof. By way of example only, network 150 may include cable networks, wired networks, fiber optic networks, telecommunications networks, internal networks, the Internet, local area networks (LANs), wide area networks (WANs), wireless local area networks (WLANs), metropolitan area networks (MANs), public switch telephone networks (PSTNs), Bluetooth networks, ZigBee networks, near field communication (NFC) networks, etc., or any combination thereof. In some embodiments, network 150 may include at least one network access point, through which at least one component of application scenario 100 can connect to network 150 to exchange data and / or information.

[0030] Storage device 120 can store data, instructions, and / or any other information. In some embodiments, storage device 120 can store data obtained from data acquisition device 110, processing device 130, and / or management terminal 140. For example, storage device 120 can store operating status parameters of energy storage cabinet 160 acquired by data acquisition device 110; or, for example, storage device 120 can store data calculated by processing device 130. In some embodiments, storage device 120 can store data and / or instructions used by processing device 130 to perform or complete the exemplary methods described herein. In some embodiments, storage device 120 may include mass storage, removable storage, volatile read-write storage, read-only storage (ROM), etc., or any combination thereof. Exemplary mass storage may include disks, optical disks, solid-state drives, etc. In some embodiments, storage device 120 can be implemented on a cloud platform. By way of example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-layer cloud, etc., or any combination thereof.

[0031] In some embodiments, storage device 120 may be connected to network 150 to communicate with at least one other component in application scenario 100 (e.g., data acquisition device 110, processing device 130, management terminal 140). At least one component in application scenario 100 may access data, instructions, or other information stored in storage device 120 via network 150. In some embodiments, storage device 120 may be directly connected to or communicate with one or more components in application scenario 100 (e.g., data acquisition device 110, management terminal 140). In some embodiments, storage device 120 may be part of data acquisition device 110 and / or processing device 130.

[0032] The processing device 130 can process data and / or information obtained from the data acquisition device 110, storage device 120, management terminal 140, and / or other components of the application scenario 100. In some embodiments, the processing device 130 can obtain operating status parameters of the energy storage cabinet 160 from any one or more of the data acquisition device 110, storage device 120, or management terminal 140, and process these operating status parameters to determine abnormal system operation conditions of the energy storage cabinet 160. In some embodiments, the processing device 130 can retrieve pre-stored computer instructions from the storage device 120 and execute the computer instructions to implement at least one step in the semantically constrained energy storage cabinet EMS adaptive energy dispatch design method described in this specification.

[0033] In some embodiments, the processing device 130 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, the processing device 130 may be local or remote. For example, the processing device 130 may access information and / or data from the data acquisition device 110, storage device 120, and / or management terminal 140 via network 150. Alternatively, the processing device 130 may be directly connected to the data acquisition device 110, storage device 120, and / or management terminal 140 to access information and / or data. In some embodiments, the processing device 130 may be implemented on a cloud platform. For example, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, etc., or any combination thereof.

[0034] The management terminal 140 can receive, send, and / or display data. The received data may include data collected by the data acquisition device 110, data stored in the storage device 120, and system operation anomalies of the energy storage cabinet 160 processed by the processing device 130. The sent data may include user (e.g., administrator) input data and instructions. For example, the management terminal 140 can send user-inputted operation instructions to the data acquisition device 110 via the network 150 to control the data acquisition device 110 to perform corresponding data acquisition. As another example, the management terminal 140 can send user-inputted system operation status evaluation instructions to the processing device 130 via the network 150.

[0035] In some embodiments, the management terminal 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, or any combination thereof. For example, the mobile device 141 may include a mobile phone, a personal digital assistant (PDA), a dedicated mobile terminal, or any combination thereof. In some embodiments, the management terminal 140 may include input devices (such as a keyboard, a touchscreen), output devices (such as a display, a speaker), etc. In some embodiments, the processing device 130 may be part of the management terminal 140.

[0036] It should be noted that the above description of application scenario 100 is merely for illustration and explanation, and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to application scenario 100 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. In some embodiments, application scenario 100 may include more or fewer functional components. For example, in some possible embodiments, the aforementioned management terminal 140 may not be included. In the embodiments of this application, the aforementioned data acquisition device 110, storage device 120, and processing device 130 may be part of the energy storage cabinet EMS.

[0037] Figure 2This is a schematic diagram of a semantically constrained energy storage cabinet EMS adaptive energy dispatching system according to some embodiments of this specification. In some embodiments, Figure 2 The semantically constrained energy storage cabinet EMS adaptive energy dispatching system 200 shown can be applied in software and / or hardware. Figure 1 The application scenario 100 shown, for example, can be configured in the form of software and / or hardware to the processing device 130 and / or management terminal 140 to determine the optimal scheduling strategy based on industrial design elements, thermal rules and economic objectives related to the energy storage cabinet, then load the optimal scheduling strategy, and determine the abnormal system operation of the energy storage cabinet 160 through the operating status parameters collected in real time by the data acquisition device 110, and finally optimize the scheduling strategy and energy scheduling based on the abnormal system operation.

[0038] Reference Figure 2 In some embodiments, the semantically constrained energy storage cabinet EMS adaptive energy dispatching system 200 may include a target semantic library construction module 210, an optimal dispatching strategy determination module 220, a dispatching strategy loading module 230, a real-time fine-tuning module 240, an anomaly monitoring module 250, and a dispatching strategy optimization module 260. Wherein: The target semantic library construction module 210 can be used to encode the industrial design elements, thermal rules and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, and then construct a target semantic library corresponding to the target energy storage cabinet based on the semantic constraint dictionary.

[0039] The optimal scheduling strategy determination module 220 can be used to generate an optimal scheduling strategy that includes charging and discharging strategies and temperature control setting parameters by using the semantic constraint dictionary as boundary conditions and employing a multi-objective optimization algorithm for rolling solution.

[0040] The scheduling strategy loading module 230 can be used to load the optimal scheduling strategy and collect the SOC, temperature and reverse power of the target energy storage cabinet in real time.

[0041] The real-time fine-tuning module 240 can be used to compare the SOC, temperature and reverse current power with preset conditions, and then fine-tune the optimal scheduling strategy in real time based on the comparison results.

[0042] The anomaly monitoring module 250 can be used to trigger a semantic rollback mechanism when an anomaly is detected in the system operation, switch to a suboptimal backup scheduling strategy, and report the anomaly event.

[0043] The scheduling strategy optimization module 260 can be used to update the multi-objective coupled model based on historical running data and automatically adjust the weight parameters of the semantic constraint dictionary to achieve adaptive optimization of the scheduling strategy.

[0044] For more details about the above modules, please refer to other parts of this manual (e.g., Figure 3 (Parts and related descriptions), which will not be repeated here.

[0045] It should be understood that Figure 2 The semantically constrained energy storage cabinet EMS adaptive energy dispatch system 200 and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above methods can be implemented using computer-executable instructions and / or included in processor control code, for example, on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules in this specification can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the above hardware circuits and software (e.g., firmware).

[0046] It should be noted that the above description of the semantically constrained EMS adaptive energy dispatch design system 200 for energy storage cabinets is provided for illustrative purposes only and is not intended to limit the scope of this specification. It will be understood that those skilled in the art can, based on the description in this specification, arbitrarily combine the various modules, or construct subsystems and connect them with other modules, without departing from this principle. For example, Figure 2 The target semantic library construction module 210, optimal scheduling strategy determination module 220, scheduling strategy loading module 230, real-time fine-tuning module 240, anomaly monitoring module 250, and scheduling strategy optimization module 260 described herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. Such variations are all within the scope of this specification. In some embodiments, the aforementioned modules may be part of the processing device 130 and / or management terminal 140.

[0047] Figure 3This is an exemplary flowchart of a semantically constrained EMS adaptive energy scheduling method for energy storage cabinets, as shown in some embodiments of this specification. In some embodiments, the semantically constrained EMS adaptive energy scheduling method for energy storage cabinets can be executed by processing logic, which may include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to execute hardware simulations), and any combination thereof. In some embodiments, Figure 3 One or more operations in the flowchart of the semantically constrained EMS adaptive energy dispatch design method for energy storage cabinets shown can be performed through... Figure 1 The processing device 130 and / or management terminal 140 shown are implemented. For example, the semantically constrained EMS adaptive energy scheduling design method for energy storage cabinets can be stored in the storage device 120 in the form of computer programs and / or instructions, and can be called and / or executed by the processing device 130 and / or management terminal 140.

[0048] Reference Figure 3 The semantically constrained EMS adaptive energy dispatch design method for energy storage cabinets provided in this application embodiment may include the following steps S310~S360: Step S310 involves encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, and then constructing a target semantic library corresponding to the target energy storage cabinet based on the semantic constraint dictionary. In some embodiments, step S310 can be performed by the target semantic library construction module 210.

[0049] In order to adapt to the installation environment, energy storage cabinets may adopt different cabinet sizes, cabinet colors, temperature control methods (such as air cooling, liquid cooling, natural cooling, etc.), heat dissipation fin angles, and air inlet and outlet directions in different application scenarios. These industrial design elements will affect the performance of energy storage cabinets to a certain extent (such as heat dissipation performance and maximum charging and discharging power).

[0050] In the actual scheduling process of energy storage cabinets (EMS), it is necessary not only to conduct scheduling control based on economic objectives such as demand and peak-valley arbitrage strategies, but also to consider the actual performance of the energy storage cabinets. However, currently, on-site commissioning by personnel is usually required based on the actual application scenario to ensure that the energy storage cabinets can operate stably in their usage scenarios.

[0051] Manual on-site commissioning is time-consuming and labor-intensive, and the accuracy, reliability, and consistency of the results are difficult to guarantee. Furthermore, due to significant differences in environmental factors and equipment parameters across different scenarios, traditional scheduling methods often fail to meet complex and ever-changing practical needs and lack universal applicability (which is the fundamental reason for the high time and labor costs of manual commissioning). Therefore, designing a more intelligent and flexible energy scheduling method for energy storage cabinets to improve their adaptability and management efficiency in different application scenarios has become an urgent technical problem to be solved.

[0052] In this embodiment of the application, in order to realize the adaptive energy scheduling of the energy storage cabinet EMS, it is first necessary to encode the industrial design elements, thermal rules and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, and then construct a target semantic library corresponding to the target energy storage cabinet based on the semantic constraint dictionary.

[0053] In this embodiment of the application, the industrial design elements may include cabinet size, temperature control method, cabinet color, heat dissipation fin angle and air inlet and outlet direction. The thermal rules are used to describe the constraints that the target energy storage cabinet needs to follow in the thermal management process and the physical laws related to the industrial design elements. The economic objectives may include peak-valley arbitrage revenue, demand control parameters and anti-backflow indicators.

[0054] Specifically, in some embodiments of this application, the aforementioned cabinet dimensions may include the approximate external shape, internal layout, and dimensional data of the energy storage cabinet, such as the length, width, and height of the cabinet, as well as the spatial distribution of internal battery modules and other key components (such as gaps between components, space utilization, etc.). In some embodiments, the cabinet dimensions may include the dimensions of the air inlet and outlet and the effective heat dissipation area. The choice of cabinet color usually involves environmental integration. Since different cabinet colors may have different heat absorption characteristics, in the embodiments of this application, in order to accurately evaluate the comprehensive heat dissipation performance of the energy storage cabinet, the cabinet dimensions and cabinet color can be considered together with major influencing factors such as temperature control method, heat dissipation fin angle, and air inlet and outlet direction as influencing variables.

[0055] In this embodiment, the temperature control method of the energy storage cabinet can include various forms such as natural air cooling, forced air cooling, liquid cooling, and combined cooling. Among them, natural air cooling mainly relies on natural air convection to achieve heat exchange; forced air cooling actively accelerates airflow through devices such as fans, thereby improving heat dissipation efficiency to a certain extent; liquid cooling utilizes the high specific heat capacity of liquid media to quickly remove heat; and combined cooling can combine the advantages of the above-mentioned cooling methods, dynamically switching or coordinating them according to the actual operating conditions of the energy storage cabinet to achieve better heat dissipation and energy consumption balance. Heat dissipation fins can be used to enhance the heat removal efficiency inside the energy storage cabinet, and their angle design directly affects the airflow state and heat exchange area when the air flows over the fins. For example, when the fins are tilted at a certain angle to the horizontal plane, it can reduce airflow resistance and increase the contact area with the air, thereby improving the heat dissipation capacity under natural convection or forced air cooling conditions.

[0056] The direction of airflow in and out usually needs to be designed in conjunction with the distribution of heat sources inside the energy storage cabinet. Different airflow directions may have different airflow organization characteristics, thus significantly affecting the heat dissipation effect. For example, when the heat source is mainly concentrated in the lower area of ​​the energy storage cabinet, a bottom-in, top-out airflow design can utilize the principle of natural rising of hot air, allowing cool air to enter from the bottom, fully contact the heat source, and absorb heat. The air carrying heat then flows upward and exits from the top, forming a complete convection cycle. However, if the heat source is more dispersed and there are localized high-temperature areas, a side-in, side-out approach may be more effective in guiding airflow specifically through key heat-generating components, preventing heat accumulation in localized areas. In some embodiments of this application, the airflow direction can be used to describe the relationship between the location of the air inlet / outlet and the corresponding airflow path of the heat dissipation duct.

[0057] In this embodiment, the aforementioned thermal rules can be understood as a series of scientific principles and boundary conditions used to regulate the generation, transfer, and dissipation of heat in energy storage cabinets during operation. These rules can cover the specific application of fundamental thermodynamic laws in the thermal management scenario of energy storage cabinets, and can also include temperature threshold limits for different operating conditions, such as the normal operating temperature range of battery modules, the maximum allowable temperature rise rate, and the upper limit of high temperature resistance for key components. In this embodiment, these thermal rules can also clarify the physical correlation between various industrial design elements, such as the relationship between temperature control methods, heat dissipation fin angles, air inlet and outlet directions and convective heat transfer coefficients, and the relationship between cabinet color and radiative heat transfer coefficients.

[0058] In this embodiment, the aforementioned economic objectives may include peak-valley arbitrage revenue, demand control parameters, and anti-reverse flow indicators. Peak-valley arbitrage revenue can be understood as the difference in revenue generated by storing electrical energy during off-peak hours and releasing it during peak hours. This revenue can be calculated by combining local time-of-use pricing policies, the charging and discharging efficiency of the energy storage unit, and the actual charging and discharging volume. Demand control parameters mainly involve limiting the maximum power and electricity consumption of the energy storage unit within a specific time period (e.g., one week, one month), aiming to avoid additional costs due to excessive instantaneous power or total electricity consumption. In this embodiment, the demand control parameters can be dynamically adjusted based on the power company's demand billing standards and the user's load characteristics. Anti-reverse flow indicators ensure that the electrical energy fed back to the grid by the energy storage system does not exceed a specified threshold, preventing interference with the stable operation of the grid. In this embodiment, the setting of the anti-reverse flow indicator can refer to the grid company's access specifications and the collaborative operation strategy of the energy storage unit and distributed power sources.

[0059] In this embodiment of the application, the cabinet size, temperature control method, cabinet color, heat dissipation fin angle and air inlet and outlet direction included in the above-mentioned industrial design elements, the peak and valley arbitrage revenue, demand control parameters and anti-backflow indicators included in the above-mentioned economic objectives, and the above-mentioned thermal rules, etc., can be stored in the storage device 120 in the form of configuration files (such as product information configuration files, system parameter configuration files, etc.), or can be manually entered by staff during on-site debugging for configuration.

[0060] Furthermore, in this embodiment, after obtaining the aforementioned industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet, these elements are encoded into a semantic constraint dictionary. Then, a target semantic library corresponding to the target energy storage cabinet is constructed based on this semantic constraint dictionary. This semantic constraint dictionary can be understood as a set of semantic units that transform the information contained in the aforementioned industrial design elements, thermal rules, and economic objectives into computer-recognizable and processable semantic units through specific encoding rules. These semantic units can cover the key constraints of the target energy storage cabinet in multiple dimensions, including design, operation, and economic evaluation. Each semantic unit can contain clear attribute definitions, value ranges, and descriptions of relationships. The target semantic library can be understood as a systematic knowledge base formed on the basis of the semantic constraint dictionary by establishing a hierarchical structure and logical mapping relationship between semantic units. This knowledge base can provide comprehensive and accurate semantic support for the subsequent construction of the energy storage cabinet's EMS adaptive energy dispatch model (i.e., the multi-objective coupling model mentioned later), thereby ensuring that the dispatch strategy meets thermal safety requirements while maximizing the achievement of economic objectives.

[0061] Specifically, in some embodiments of this application, the industrial design elements can be mapped to physical parameters related to the thermal management of the energy storage cabinet, and the economic objective can be quantified as a benefit function. The physical parameters may include thermal resistance coefficient and wind resistance coefficient. In embodiments of this application, the physical parameters can be obtained by mapping the industrial design elements according to the thermal rules.

[0062] Specifically, in some embodiments of this application, the thermal resistance coefficient can be obtained based on the following formula: in, This represents the thermal resistance coefficient corresponding to the target energy storage cabinet, which reflects the total resistance of the target energy storage cabinet during the heat dissipation process (the larger the thermal resistance coefficient, the weaker the heat dissipation capacity of the energy storage cabinet, and the higher the risk of heat accumulation inside the cabinet). This indicates the normalization operation (i.e., normalization). This refers to the effective heat dissipation area of ​​the target energy storage cabinet, which can be obtained based on the cabinet dimensions. The convective heat transfer coefficient of the target energy storage cabinet can be obtained based on the temperature control method, the angle of the heat dissipation fins, and the direction of air inlet and outlet. This represents the radiative heat transfer coefficient corresponding to the target energy storage cabinet, which can be obtained based on the color of the cabinet.

[0063] It should be noted that, in the embodiments of this application, the aforementioned effective heat dissipation area refers to the cabinet surface area that can actually participate in heat exchange, and the effective value is the result after deducting the area that cannot be exposed due to the installation method. For example, when the energy storage cabinet is installed with its side against the wall, the side area in contact with the wall will not be included in the effective heat dissipation area. In some embodiments of this application, the calculation of the effective heat dissipation area can also be combined with the thermal conductivity characteristics of the cabinet material. If different areas of the cabinet use materials with different thermal conductivity coefficients (such as metal side panels and insulating back panels), the effective heat exchange area of ​​each area needs to be calculated separately and then weighted and summed to ensure the accuracy of the thermal resistance coefficient calculation.

[0064] Furthermore, in some embodiments of this application, the above-mentioned convective heat transfer coefficient... The calculation process can be represented as follows: in, This represents the basic convective heat transfer coefficient, which can be taken as an empirical value based on the temperature control method. For example, in some embodiments, when the temperature control method is liquid cooling, The value can be set to 10; when the temperature control method is air cooling. The value can be set to 5; when the temperature control method is natural cooling. The value can be set to 1.

[0065] This indicates the convective heat transfer coefficient due to the angle of the heat sink fins. Influence coefficient, Indicates the convective heat transfer coefficient of the air inlet and outlet directions. The influence coefficient. In some embodiments of this application, when the temperature control method is liquid cooling, A constant value of 1 can be used. When the temperature control method is air cooling or natural cooling, It can be represented as ,in, Indicates the angle between the fins and the direction of airflow; An empirical value can be taken based on the smoothness of the airflow path. For example, when the airflow path caused by the inlet and outlet airflow direction is a short path (e.g., less than 1 meter) or there are no vortices, A value of 1 can be set when the airflow path caused by the inlet / outlet direction is a long path (e.g., greater than or equal to 1 meter) or when there are vortices. The value can be 0.6. In some embodiments, when there are multiple air inlets and outlets, the smoothness of the airflow path of each air inlet and outlet can be evaluated separately, and a corresponding value can be assigned to each airflow path. The values ​​are then calculated using a weighted average to determine the overall value. The comprehensive influence coefficient is determined by the weight of each airflow path, which can be determined based on the airflow volume ratio of each airflow path.

[0066] Furthermore, in some embodiments of this application, the above-mentioned radiative heat transfer coefficient... This can be determined by the cabinet's color. For example, when the cabinet surface uses a high-emissivity color (such as black or dark gray), its radiative heat exchange capacity is stronger (i.e., the energy storage cabinet exchanges its own heat with the outside environment more efficiently through electromagnetic radiation). In this case, it can... The mapping is to a higher value; however, when the cabinet surface is a low-emissivity color (such as white or silver-white), the radiative heat transfer effect is weaker, so it can be... The mapping is to a lower value. In practical applications, this can be achieved by establishing a relationship between cabinet color and radiative heat transfer coefficient. The corresponding relationship table is used, and then the corresponding radiative heat transfer coefficient is obtained by mapping the cabinet color. By way of example only, in some embodiments, common colors can be divided into different radiation levels, each level corresponding to a specific... Value range. For example, black can be defined as radiation level 1, corresponding to... The value is 10 for level 2; dark gray is level 2 with a value of 8; silver-white is level 3 with a value of 5; white is level 4 with a value of 3... and so on, thus obtaining the relationship between the cabinet color and the radiative heat transfer coefficient. A table showing the correspondence between them. It should be noted that, in this embodiment, when the cabinet uses multiple color combinations, the comprehensive radiative heat transfer coefficient can be obtained by weighted calculation based on the surface area ratio of each color region. .

[0067] Furthermore, in some embodiments of this application, the aforementioned drag coefficient can be calculated based on the following formula: in, This represents the drag coefficient corresponding to the target energy storage cabinet, which reflects the flow resistance when air flows through the target energy storage cabinet (the greater the resistance, the larger the contact area between the air and the energy storage cabinet (the longer the contact time between the air and the energy storage cabinet during the airflow process), and the higher the heat exchange efficiency). Represents the normalization operation (i.e.) (Normalization) This represents the basic drag coefficient corresponding to the target energy storage cabinet, which can be obtained based on the cabinet dimensions.

[0068] Specifically, in the embodiments of this application, This can be obtained from the effective heat dissipation area within the cabinet dimensions. For example, this effective heat dissipation area can be correlated with the basic drag coefficient. The mapping relationship between them is then obtained through mapping. In this embodiment of the application, the basic drag coefficient is... The coefficient of friction is directly proportional to the effective heat dissipation area of ​​the energy storage cabinet. In other words, the larger the effective heat dissipation area of ​​the energy storage cabinet, the lower the drag coefficient of the foundation. The larger.

[0069] As an example only, in some embodiments of this application, the effective heat dissipation area is related to the basic drag coefficient. The mapping relationship between them can be represented as: ,in The weighting coefficient corresponding to the j-th heat dissipation surface (this weighting coefficient is positively correlated with the area of ​​the heat dissipation surface), and its value can be determined by fitting a large amount of experimental data; represents the effective heat dissipation area of ​​the j-th heat dissipation surface of the energy storage cabinet; m represents the total number of effective heat dissipation surfaces of the energy storage cabinet.

[0070] In some embodiments, the above It can be represented as: Where, exp( ) represents the natural exponential function; The larger, the better The closer to 1; The smaller, the better The closer it is to 0.5.

[0071] It should be noted that the specific values ​​of the above parameters in this specification are merely illustrative and are not intended to limit the parameters. In the embodiments of this application, the above values ​​can be adjusted according to actual needs.

[0072] Furthermore, in the embodiments of this application, the above-mentioned revenue function can be expressed as follows: in, Represents total revenue; This indicates the profit from peak-valley arbitrage. This represents the cost corresponding to the anti-backflow indicator; This indicates the electricity price during peak hours. This indicates the electricity price during off-peak hours; Indicates the amount of discharge. Indicates the amount of charge. , For energy storage efficiency. In the embodiments of this application, and It can be determined based on the demand control parameters. In some embodiments, when When the value is less than the demand control parameter, it indicates that charging is required during peak hours.

[0073] Specifically, in this embodiment of the application, the demand control parameter can be used as a boundary condition to determine the maximum charging amount required to prevent reverse current from occurring in the energy storage system under that demand. and the corresponding backflow prevention cost In the specific calculation process, the maximum power consumption of the energy storage system within a specific time period can be limited by this demand control parameter. Based on this boundary condition, and combined with the inherent properties of the energy storage system such as rated capacity and charge / discharge rate, an iterative optimization algorithm is used to solve for the maximum charging amount that meets the demand control requirements and effectively avoids the risk of reverse current. The range of values ​​for . Also, The determination of the backflow prevention device needs to comprehensively consider its operating losses, maintenance costs, and potential opportunity costs caused by demand control. Generally speaking, its value is positively correlated with the strictness of the demand control parameters; that is, the stricter the demand control, the higher the cost required to ensure that the backflow prevention index meets the standard. The higher the value, the better. In practical applications, this can be achieved by establishing demand control parameters and... , The mapping relationship model between them enables dynamic evaluation and optimization of the total revenue S, thereby providing a scientific basis for the energy dispatch strategy of energy storage system.

[0074] In this embodiment, a target semantic library corresponding to the target energy storage cabinet can be constructed based on the aforementioned thermal resistance coefficient, wind resistance coefficient, revenue function, and the semantic constraint dictionary corresponding to the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet. In subsequent processes, energy scheduling strategies for the energy storage cabinet can be further formulated and optimized based on the information contained in this target semantic library.

[0075] Step S320 involves using the semantic constraint dictionary as boundary conditions and employing a multi-objective optimization algorithm for rolling solution to generate an optimal scheduling strategy that includes charging / discharging strategies and temperature control setting parameters. In some embodiments, step S320 can be executed by the optimal scheduling strategy determination module 220.

[0076] In this application embodiment, the aforementioned multi-objective optimization algorithm includes an improved NSGA-III algorithm. Specifically, in some embodiments, a thermal risk function can be constructed based on the demand control parameters, the thermal resistance coefficient, and the wind resistance coefficient; then, a rolling solution is performed with the optimization objective of minimizing the thermal risk function and / or maximizing the profit function (e.g., performing an iteration every preset time period) to obtain the optimal solution on the Pareto front, and the charging / discharging strategy and temperature control setting parameters corresponding to the target time period are generated based on the optimal solution on the Pareto front. In some embodiments of this application, the optimal solution can be obtained by training to find a balance between the thermal risk function and the profit function.

[0077] For example, in some embodiments of this application, the thermal risk function can be expressed as follows: in, This indicates the thermal risk value (used to measure the degree of safety risk caused by abnormal temperatures during the operation of an energy storage system). Indicates ambient temperature; This indicates the demand control parameters. Indicates the first The window demand parameter corresponding to each charge / discharge time window Indicates the first The duration corresponding to each charge / discharge time window Indicates the total number of charge / discharge time windows; This represents the loss coefficient (related to the internal resistance and efficiency of the energy storage unit). This can roughly represent the power loss of the energy storage cabinet (which directly determines the heat generated by the energy storage cabinet during operation). This represents the thermal resistance coefficient corresponding to the target energy storage cabinet. This indicates the drag coefficient corresponding to the target energy storage unit; It is the conversion coefficient between heat generation and temperature change, which can be calculated based on the equivalent mass and equivalent specific heat capacity of the energy storage cabinet (the equivalent mass and equivalent specific heat capacity can be obtained by fitting a large amount of experimental data). This indicates the safe temperature threshold for the target energy storage cabinet (e.g., 60°C or other values).

[0078] In this embodiment, the NSGA-III algorithm is a multi-objective optimization algorithm that helps a machine learning model find the optimal solution set among multiple objectives through non-dominated sorting and reference point mechanisms. Specifically, in this embodiment, the machine learning model may include a neural network model (i.e., the multi-objective coupled model described below) for optimizing energy scheduling of energy storage cabinets. This network model may include an input layer, a hidden layer, and an output layer. The input layer may receive data such as industrial design elements, thermal rules, and semantic constraint dictionaries corresponding to economic objectives related to the target energy storage cabinet. The hidden layer may perform linear / nonlinear mapping and feature extraction on the aforementioned input features through a multilayer perceptron structure. The output layer may generate an optimal scheduling strategy containing charging and discharging strategies and temperature control setting parameters based on the extracted features. During the model training phase, rolling solutions may be performed with the optimization objectives of minimizing the aforementioned thermal risk function and / or maximizing the aforementioned benefit function. The NSGA-III algorithm is used to iteratively optimize the network parameters. By continuously adjusting the connection weights and bias terms of each neuron, the model can dynamically adapt to the operating requirements of energy storage cabinets under different operating conditions while meeting the safety temperature constraints, thereby achieving the optimal allocation of demand parameters in the time dimension.

[0079] For example, in this embodiment, the charging and discharging strategy may include the charging and discharging power and duration of the energy storage cabinet at different times (e.g., peak and off-peak periods). The charging and discharging power can be dynamically adjusted based on real-time electricity price fluctuations and the current state of charge (SOC) of the energy storage battery. For instance, during off-peak electricity periods, a higher charging power threshold can be set (while meeting safety temperature constraints) to improve the economic efficiency of energy procurement. Temperature control settings may include, but are not limited to, the target temperature range of the energy storage cabinet during operation, the temperature sampling frequency, the start / stop threshold of the heat dissipation system, and the operating parameters of the temperature control equipment. The target temperature range can be differentiated based on the characteristic curves of the battery type (e.g., lithium iron phosphate batteries, ternary lithium batteries) to ensure the battery operates within its optimal temperature range to extend cycle life. The temperature sampling frequency can be dynamically adjusted according to the rate of change of ambient temperature; when the ambient temperature fluctuates significantly, the sampling frequency can be increased to enhance the temperature control response sensitivity. The start / stop threshold of the heat dissipation system needs to be optimized in conjunction with the charging and discharging power. For example, during high-power discharge, the heat dissipation start-up temperature threshold can be appropriately lowered to prevent the battery from exceeding local temperature limits due to excessive instantaneous heat generation.

[0080] In this embodiment, the aforementioned machine learning model can be preliminarily trained before being put into use. After it meets certain conditions (e.g., the scheduling strategy it generates meets the actual requirements), it can be officially put into use. During use, the model parameters are continuously updated based on the historical operating data of the energy storage cabinet to achieve self-evolution of the scheduling strategy. Further details regarding the NSGA-III algorithm and model training process can be considered prior art and will not be discussed in detail in this specification.

[0081] Step S330: Load the optimal scheduling strategy and collect the SOC, temperature, and reverse current power of the target energy storage cabinet in real time. In some embodiments, step S330 can be executed by the scheduling strategy loading module 230.

[0082] In this embodiment of the application, after the above-mentioned machine learning model is put into use, an optimal scheduling strategy can be obtained based on the industrial design elements, thermal rules and economic objectives related to the target energy storage cabinet (the optimal scheduling strategy is the best result obtained by the machine learning model under the current capability level, and there may be better scheduling strategies in fact).

[0083] As an example only, in some embodiments of this application, the optimal scheduling strategy can be expressed as: [P1(t), P2(t), ..., Pm(t), T1(t), T2(t), ..., Tk(t)...], where Pi(t) represents the charging and discharging power command of the i-th battery module at time t, and Tj(t) represents the operating parameter settings of the j-th temperature control device at time t.

[0084] Furthermore, the optimal scheduling strategy can be loaded (i.e., energy scheduling is performed according to the optimal scheduling strategy). In other words, in this embodiment, by converting the optimal scheduling strategy into specific execution instructions and issuing them to each execution unit of the energy storage cabinet, coordinated control of the battery charging and discharging process and the thermal management system can be achieved, thereby realizing energy scheduling of the energy storage cabinet. Simultaneously, the SOC, temperature, and reverse current power of the target energy storage cabinet can be collected in real time to evaluate the accuracy and reliability of the optimal scheduling strategy.

[0085] Step S340 involves comparing the SOC, temperature, and reverse current power with preset conditions, and then fine-tuning the optimal scheduling strategy in real time based on the comparison results. In some embodiments, step S340 can be executed by the real-time fine-tuning module 240.

[0086] In this embodiment, during the operation of the energy storage cabinet, the SOC data (including the SOC value of each individual battery and the total SOC of the battery pack), key area temperature data (such as the surface temperature of the battery module and the internal ambient temperature of the cabinet), and reverse current power data (including the real-time current and voltage product of the charging and discharging circuit) of the target energy storage cabinet can be continuously collected at a preset sampling frequency (such as once every 500ms). These real-time monitoring data are compared with preset conditions to provide data support for subsequent strategy adjustments.

[0087] In some embodiments of this application, a PID control algorithm can be used to calculate the deviations of the SOC, temperature, and reverse current power, and the charging and discharging power and the operating parameters of the temperature control device can be dynamically adjusted according to the calculation results to ensure that the system operating state is closer to the preset conditions.

[0088] Specifically, the system first compares real-time monitoring data (i.e., the aforementioned SOC, temperature, and reverse current power) with preset thresholds to determine the SOC deviation (the difference between the current SOC and the target SOC), temperature deviation (the difference between the temperature of the critical area and the safe temperature threshold), and reverse current power deviation (the difference between the actual reverse current power and the rated power). These deviations are then used as inputs to the PID controller. After calculations by the proportional (directly adjusting the output based on the deviation), integral (eliminating static errors, accumulating deviations, and continuously correcting them), and derivative (predicting trends based on the rate of change of deviation and adjusting in advance), the corresponding charging / discharging power adjustment and temperature control equipment operating parameter adjustment are generated. For example, when the SOC deviation is positive and exceeds the set range, the PID controller can output instructions to reduce charging power or increase discharging power; if the temperature deviation remains positive and shows an upward trend, the derivative will increase the heat dissipation power of the temperature control equipment in advance to prevent the temperature from further rising and exceeding the safe threshold.

[0089] In step S350, when a system malfunction is detected, a semantic rollback mechanism is triggered to switch to a suboptimal backup scheduling strategy, and the abnormal event is reported. In some embodiments, step S350 can be executed by the abnormality monitoring module 250.

[0090] In this embodiment, when an anomaly is detected in the system operation, it indicates that the optimal scheduling strategy obtained through the aforementioned process still has room for optimization. At this time, a semantic rollback mechanism can be triggered to further reduce the hot risk function value by lowering the benefit function value, thereby obtaining a suboptimal but safer backup scheduling strategy.

[0091] For example, in some embodiments of this application, the conditions for determining abnormal system operation may include: the difference between the actual temperature and the safe temperature threshold is greater than 3°C or the reverse current power at the grid connection point exceeds 0.5% of the rated power.

[0092] It should be noted that the above-mentioned system operation abnormality determination conditions are only illustrative examples. In this application embodiment, the determination conditions can be adjusted according to actual needs.

[0093] In this embodiment of the application, when an abnormality is detected in the system operation, the abnormal event can be reported, and the operation data corresponding to the abnormal event can be used as a new training sample, thereby optimizing the aforementioned machine learning model through the continuous accumulation of new training samples.

[0094] Step S360 involves updating the multi-objective coupling model based on historical operational data and automatically adjusting the weight parameters of the semantic constraint dictionary to achieve adaptive optimization of the scheduling strategy. In some embodiments, step S360 can be executed by the scheduling strategy optimization module 260.

[0095] Specifically, in this embodiment, the historical operational data may include operational data corresponding to the aforementioned abnormal events. In this embodiment, the historical operational data can be trained using machine learning methods to update the parameters of the multi-objective coupling model (i.e., the aforementioned machine learning model) and to adjust the weights of each semantic constraint dictionary in the target semantic library.

[0096] It should be noted that, in the embodiments of this application, by performing correlation analysis between the abnormal event features in historical operating data and the weight parameters of the semantic constraint dictionary, a semantic rollback mechanism and a dynamic adjustment mechanism are constructed. This enables the aforementioned semantic constraint dictionary to continuously adapt to changes in the operating environment of the energy storage cabinet, fundamentally realizing the self-evolution of the multi-objective coupling model, and ultimately allowing the energy scheduling strategy to achieve a dynamic balance between safety, economy and stability, effectively improving the adaptive adjustment accuracy and overall operating efficiency of the EMS under complex operating conditions.

[0097] Specifically, in the embodiments of this application, when the system detects a new abnormal pattern, the machine learning model can identify and extract relevant features, thereby automatically increasing the weight of the corresponding semantic constraint terms to ensure that the scheduling strategy has a higher priority response capability when dealing with similar anomalies. Meanwhile, in some embodiments of this application, for anomaly types that have not appeared for a long time or problem scenarios that have been verified to be optimized and resolved, the model will gradually reduce the weight of their corresponding semantic constraints, thereby avoiding interference from redundant rules on normal scheduling decisions.

[0098] It should also be noted that, in this embodiment, by encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, and using the semantic constraint dictionary as boundary conditions, a multi-objective optimization algorithm is employed for rolling solution to generate an optimal scheduling strategy that includes charging and discharging strategies and temperature control setting parameters. Then, during the loading of the optimal scheduling strategy, system operation anomalies are monitored in real time, and the multi-objective coupling model is updated based on the operation data corresponding to the anomaly events. This allows the energy storage cabinet EMS to automatically generate an energy scheduling strategy that is adapted to its own design elements, and to achieve adaptive optimization of the scheduling strategy based on the actual operation. This greatly improves the adaptability and management efficiency of the energy storage cabinet in different application scenarios, and can also improve the peak-valley arbitrage benefits of the energy storage cabinet to a certain extent, simplify the installation and commissioning process of the energy storage cabinet, and shorten the on-site commissioning time.

[0099] In summary, the beneficial effects that the embodiments of this specification may bring include, but are not limited to: (1) In the semantic constraint-based adaptive energy scheduling design method for energy storage cabinets (EMS) provided in some embodiments of this specification, by encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary, and using the semantic constraint dictionary as boundary conditions, a multi-objective optimization algorithm is used to perform rolling solution to generate an optimal scheduling strategy that includes charging and discharging strategies and temperature control setting parameters. Then, during the loading of the optimal scheduling strategy, the system operation anomalies are monitored in real time, and the multi-objective coupling model is updated based on the operation data corresponding to the anomaly events. This allows the energy storage cabinet (EMS) to automatically generate an energy scheduling strategy that is adapted to its own design elements, and to achieve adaptive optimization of the scheduling strategy according to the actual operation, thereby greatly improving the energy storage cabinet in different application scenarios. (2) In the semantic constraint-based adaptive energy scheduling design method of energy storage cabinet EMS provided in some embodiments of this specification, by associating the abnormal event features in historical operating data with the weight parameters of the semantic constraint dictionary, a semantic rollback mechanism and a dynamic adjustment mechanism are constructed, which enables the aforementioned semantic constraint dictionary to continuously adapt to the changes in the operating environment of the energy storage cabinet, fundamentally realize the self-evolution of the multi-objective coupling model, and ultimately enable the energy scheduling strategy to achieve a dynamic balance between safety, economy and stability, effectively improving the adaptive adjustment accuracy and overall operating efficiency of EMS under complex working conditions; (3) Through the semantic constraint-based adaptive energy scheduling design method of energy storage cabinet EMS provided in the embodiments of this specification, the peak-valley arbitrage income of the energy storage cabinet can also be improved to a certain extent, the installation and commissioning process of the energy storage cabinet can be simplified, and the on-site commissioning time can be shortened.

[0100] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.

[0101] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0102] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0103] Furthermore, those skilled in the art will understand that various aspects of this specification can be described and illustrated in several patentable ways or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, various aspects of this specification can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a “data block,” “module,” “engine,” “unit,” “component,” or “system.” Furthermore, various aspects of this specification may be represented as a computer product located on one or more computer-readable media, including computer-readable program code.

[0104] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0105] The computer program code required for the operation of each part of this manual can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc.; conventional procedural programming languages ​​such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0106] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on existing processing devices or mobile devices.

[0107] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0108] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A semantically constrained adaptive energy scheduling method for energy storage cabinets (EMS), characterized in that, include: The industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet are encoded into a semantic constraint dictionary. Then, a target semantic library corresponding to the target energy storage cabinet is constructed based on the semantic constraint dictionary. Using the semantic constraint dictionary as boundary conditions, a multi-objective optimization algorithm is used for rolling solution to generate an optimal scheduling strategy that includes charging and discharging strategies and temperature control setting parameters; The optimal scheduling strategy is loaded, and the SOC, temperature, and reverse current power of the target energy storage cabinet are collected in real time. The SOC, temperature, and reverse current power are compared with preset conditions, and then the optimal scheduling strategy is fine-tuned in real time based on the comparison results. When an abnormal system operation is detected, a semantic rollback mechanism is triggered to switch to a suboptimal backup scheduling strategy and report the abnormal event. The multi-objective coupling model is updated based on historical operational data, and the weight parameters of the semantic constraint dictionary are automatically adjusted to achieve adaptive optimization of the scheduling strategy.

2. The semantically constrained EMS adaptive energy scheduling method for energy storage cabinets as described in claim 1, characterized in that, The industrial design elements include cabinet dimensions, temperature control method, cabinet color, heat dissipation fin angle, and air inlet and outlet direction. The thermal rules are used to describe the constraints that the target energy storage cabinet needs to follow in the thermal management process and the physical laws related to the industrial design elements. The economic objectives include peak-valley arbitrage revenue, demand control parameters, and backflow prevention indicators.

3. The semantically constrained EMS adaptive energy scheduling method for energy storage cabinets as described in claim 2, characterized in that, The step of encoding the industrial design elements, thermal rules, and economic objectives related to the target energy storage cabinet into a semantic constraint dictionary includes: mapping the industrial design elements to physical parameters related to the thermal management of the energy storage cabinet, and quantifying the economic objectives into a benefit function. The physical parameters include thermal resistance coefficient and wind resistance coefficient, and the physical parameters are obtained by mapping the industrial design elements according to the thermal rules.

4. The semantically constrained EMS adaptive energy dispatching method for energy storage cabinets as described in claim 3, characterized in that, The thermal resistance coefficient is obtained based on the following formula: ； in, This represents the thermal resistance coefficient corresponding to the target energy storage cabinet, which is used to reflect the total resistance of the target energy storage cabinet during the heat dissipation process; This represents the normalization operation; The effective heat dissipation area of ​​the target energy storage cabinet is obtained based on the cabinet dimensions. The convective heat transfer coefficient of the target energy storage cabinet is obtained based on the temperature control method, the angle of the heat dissipation fins, and the direction of air inlet and outlet. The radiative heat transfer coefficient corresponding to the target energy storage cabinet is obtained based on the color of the cabinet. The drag coefficient is obtained based on the following formula: ； in, This represents the drag coefficient corresponding to the target energy storage cabinet, which reflects the flow resistance when air flows through the target energy storage cabinet. This represents the normalization operation; This represents the basic drag coefficient corresponding to the target energy storage cabinet, which is obtained based on the cabinet dimensions.

5. The semantically constrained EMS adaptive energy dispatching method for energy storage cabinets as described in claim 3, characterized in that, The payoff function is as follows: ； ； in, Represents total revenue; This indicates the profit from peak-valley arbitrage. This represents the cost corresponding to the anti-backflow indicator; This indicates the electricity price during peak hours. This indicates the electricity price during off-peak hours; Indicates the amount of discharge. Indicates the amount of charge. , For energy storage efficiency; and Determined based on the aforementioned demand control parameters.

6. The semantically constrained EMS adaptive energy scheduling method for energy storage cabinets as described in claim 3, characterized in that, The multi-objective optimization algorithm includes an improved NSGA-III algorithm. Using the semantic constraint dictionary as boundary conditions, the multi-objective optimization algorithm performs a rolling solution to generate an optimal scheduling strategy that includes charging / discharging strategies and temperature control setting parameters, including: A thermal risk function is constructed based on the demand control parameters, the thermal resistance coefficient, and the wind resistance coefficient. The optimal solution on the Pareto front is obtained by rolling the solution with the goal of minimizing the thermal risk function and / or maximizing the benefit function. The optimal solution on the Pareto front is then used to generate the charging and discharging strategy and temperature control setting parameters corresponding to the target time period.

7. The semantically constrained EMS adaptive energy dispatching method for energy storage cabinets as described in claim 6, characterized in that, The thermal risk function is as follows: ； ； in, Indicates the thermal risk value; Indicates ambient temperature; This indicates the demand control parameters. Indicates the first The window demand parameter corresponding to each charge / discharge time window Indicates the first The duration corresponding to each charge / discharge time window Indicates the total number of charge / discharge time windows; Indicates the loss coefficient; This represents the thermal resistance coefficient corresponding to the target energy storage cabinet. This indicates the drag coefficient corresponding to the target energy storage unit; These are the conversion factors; This indicates the safe temperature threshold of the target energy storage cabinet.

8. The semantically constrained EMS adaptive energy dispatching method for energy storage cabinets as described in any one of claims 1 to 7, characterized in that, The step of comparing the SOC, temperature, and reverse current power with preset conditions, and then fine-tuning the optimal scheduling strategy in real time based on the comparison results, includes: A PID control algorithm is used to calculate the deviations of the SOC, temperature, and reverse current power, and the charging and discharging power and the operating parameters of the temperature control device are dynamically adjusted based on the calculation results to ensure that the system operating state is closer to the preset conditions.

9. The semantically constrained EMS adaptive energy scheduling method for energy storage cabinets as described in claim 8, characterized in that, The conditions for determining abnormal system operation include: the difference between the actual temperature and the safe temperature threshold is greater than 3°C or the reverse current power at the grid connection point exceeds 0.5% of the rated power.

10. The semantically constrained EMS adaptive energy scheduling method for energy storage cabinets as described in claim 8, characterized in that, The step of updating the multi-objective coupling model based on historical operation data and automatically adjusting the weight parameters of the semantic constraint dictionary to achieve adaptive optimization of the scheduling strategy includes: training the historical operation data through machine learning methods to update the parameters of the multi-objective coupling model and feeding back to adjust the weights of each semantic constraint dictionary in the target semantic library.

Images