Intelligent regulation and control energy storage optimization method and system for distributed energy system

Abstract

The invention relates to the technical field of energy storage optimization, and discloses an intelligent regulation and control energy storage optimization method and system for a distributed energy system, and the method comprises the steps: generating a reference scheduling strategy sample set based on historical operation data; constructing a model predictive control framework, and initializing parameters of the model predictive control framework; setting an optimization objective function by combining the energy utilization rate, the operation cost, the system stability and the energy storage life, and training the model prediction control framework by using the reference scheduling strategy sample set to obtain an intelligent regulation and control energy storage model; and acquiring real-time operation data, performing rolling optimization on the intelligent regulation and control energy storage model by using the real-time operation data, and generating a regulation and control energy storage scheme according to an optimization result. The renewable energy consumption rate is improved, the system operation cost is reduced, the power supply stability is guaranteed, the load fluctuation influence is reduced, the service life of energy storage equipment is prolonged, and an energy storage regulation and control scheme is provided under multi-target cooperation through real-time rolling optimization and adaptation to dynamic changes of power generation and power utilization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage optimization, in particular to an intelligent regulation and control energy storage optimization method and system for a distributed energy system. BACKGROUND

[0002] With the rapid development of distributed energy systems, energy storage optimization and intelligent regulation and control technology have gradually become the key to improving system economy, stability and energy self-consistency. The intermittency and uncertainty of renewable energy (such as photovoltaic and wind power) and the volatility of multi-element load in the distributed energy system have put forward higher requirements for the intelligent control of the energy storage system. However, the existing energy storage optimization and intelligent regulation and control methods still have significant deficiencies in multi-time scale collaborative optimization, dynamic response capability and adaptability to complex scenarios, which affects the overall performance of the distributed energy system.

[0003] In the prior art, the optimal charging and discharging power of the energy storage power station in the intelligent micro-grid is calculated to realize the optimal scheduling of electric energy, fully considering the operating characteristics of the energy storage device, avoiding overcharging, over-discharging and exceeding the rated operating condition, and prolonging the service life of the storage battery while reducing the user's electricity cost. However, the existing technical solution mainly aims at the static optimization of enterprise energy storage power stations, and lacks real-time response capability to multi-time scale dynamic changes. In addition, the optimization process does not fully consider the multi-element load fluctuation and intermittency of renewable energy in the distributed energy system, which may lead to difficulties in coping with complex operating scenarios in actual application.

[0004] The existing energy storage optimization and intelligent regulation and control method for distributed energy systems still has certain deficiencies in multi-time scale collaborative optimization, complex scenario adaptability and comprehensive management of multiple energy storage forms. SUMMARY

[0005] The present application provides an intelligent regulation and control energy storage optimization method and system for a distributed energy system to solve the problems of poor multi-time scale collaborative optimization effect and poor complex scenario adaptability of the distributed energy system.

[0006] In a first aspect, the present application provides an intelligent regulation and control energy storage optimization method for a distributed energy system, the method comprising: obtaining historical operation data of the distributed energy system, and generating a benchmark scheduling strategy sample set based on the historical operation data; constructing a model predictive control framework based on a double-layer optimization architecture, and initializing parameters of the model predictive control framework; setting an optimization objective function in combination with energy utilization rate, operating cost, system stability and energy storage life, and training the model predictive control framework using the benchmark scheduling strategy sample set to obtain an intelligent regulation and control energy storage model; Acquire real-time operational data of distributed energy systems, use the real-time operational data to perform rolling optimization of intelligent regulation and energy storage models, and generate regulation and energy storage schemes based on the optimization results.

[0007] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention achieves intelligent regulation and energy storage optimization of distributed energy systems by generating a benchmark scheduling strategy sample set, constructing a model prediction and control framework with a two-layer optimization architecture, and training an intelligent regulation and energy storage model. This significantly improves the renewable energy absorption rate and reduces system operating costs. At the same time, it ensures stable power supply, reduces the impact of load fluctuations, and extends the lifespan of energy storage equipment. Through real-time rolling optimization, it adapts to the dynamic changes in power generation, power consumption, and electricity prices, providing an efficient, economical, reliable, and sustainable energy storage regulation solution for distributed energy systems under multi-objective collaboration.

[0008] In one optional implementation, historical operating data includes: photovoltaic power generation, wind power generation, user load power, and dynamic electricity price. A benchmark dispatch strategy sample set is generated based on this historical operating data, including: Obtain the boundary constraints of the energy storage device, and use the Monte Carlo model to generate multiple scheduling strategy sequences that meet the boundary constraints; Calculate the objective function value of each scheduling strategy sequence, and sort the scheduling strategy sequences from largest to smallest based on the objective function value; Based on the sorting results, the first preset proportion of scheduling strategy sequences are taken as the baseline scheduling strategy sample set.

[0009] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention obtains the boundary constraints of energy storage devices, generates multiple sets of scheduling strategy sequences that meet the constraints using a Monte Carlo model, and then combines the high-quality sequences with a preset proportion of optimization objective function values ​​as a benchmark scheduling strategy sample set. This ensures that the generated scheduling strategies are within the safe operating range of the energy storage devices, and also retains efficient and economical high-quality strategies through quantitative screening, providing a high-quality and diverse sample foundation for subsequent model training and improving the training effect of the intelligent regulation and energy storage model.

[0010] In one optional implementation, the model prediction control framework based on a two-layer optimization architecture includes: an upper-layer optimization module and a lower-layer optimization module. The framework is constructed, and its parameters are initialized, including: The first parameter range of the upper-level optimization module and the second parameter range of the lower-level optimization module are generated using a random normal distribution. Based on preset constraints, upper-level optimization parameters are selected from the first parameter range, and lower-level optimization parameters are selected from the second parameter range.

[0011] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention generates parameter ranges for upper and lower optimization modules through random normal distribution, and then selects reasonable parameters by combining preset constraints. This provides scientific and reliable initial parameters for the model predictive control framework of the two-layer optimization architecture, ensuring the randomness and diversity of the parameters. The constraints ensure the rationality of the parameters, making the coordination between the upper-layer global allocation and the lower-layer local control more efficient, thereby improving the regulation accuracy and efficiency of the model predictive control framework in the energy storage optimization of distributed energy systems.

[0012] In one optional implementation, an optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, including: Obtain the calculation logic formulas for multiple state variables that affect the system's operating state, and initialize the initial weights of each state variable. The state variables include: energy utilization rate, operating cost, system stability, and energy storage lifetime. The objective function is obtained by weighted summation based on the calculation logic formulas of each state variable and the corresponding initial weights.

[0013] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention clarifies the calculation logic of multiple state variables and assigns initial weights, and obtains the optimization objective function by weighted summation, thereby achieving synergistic optimization of multi-dimensional objectives and quantitatively evaluating the comprehensive performance of distributed energy systems in terms of energy consumption, economic cost, power supply reliability and equipment durability.

[0014] In one optional implementation, the model predictive control framework is trained using a benchmark scheduling strategy sample set to obtain an intelligent regulation energy storage model, including: The baseline scheduling strategy sample set is divided into a training set and a validation set according to a preset ratio; Based on the training set, the model predictive control framework is jointly trained using deep learning algorithms, with the output of the upper-level optimization module in the model predictive control framework serving as the input of the lower-level optimization module. During training, the parameters of the upper-layer optimization module and the lower-layer optimization module are adjusted based on the optimization objective function value. The optimization objective function value after each round of training is calculated using the validation set until the optimization objective function value converges or reaches the optimization objective function threshold, thus obtaining the intelligent regulation energy storage model.

[0015] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention uses a deep learning algorithm to jointly train a two-layer optimization architecture model predictive control framework. The upper layer output is used as the lower layer input, and the parameters are adjusted based on the optimization objective function value. The model fully learns the rules of high-quality scheduling strategies, and the coordination between the upper-layer global allocation and the lower-layer local control is more accurate, thereby improving the performance of the intelligent regulation and energy storage model in multi-objective optimization of energy utilization, operating cost, system stability, and energy storage life.

[0016] In one optional implementation, real-time operating data of the distributed energy system is acquired, and the intelligent regulation and storage model is continuously optimized using the real-time operating data, including: Real-time operation data of the distributed energy system is collected according to a preset scheduling cycle, and the type of real-time operation data is consistent with that of historical operation data. Real-time operating data is input into the intelligent control and energy storage model to update the real-time state variables. Based on the updated real-time state variables, a preliminary control scheme for the current scheduling cycle is generated by solving the optimization problem. Determine whether the preliminary control scheme meets the boundary constraints. If it does, then the preliminary control scheme is taken as the optimal control energy storage scheme. If the conditions are not met, the weight coefficients of each state variable are adjusted, and a new control scheme is generated by solving the optimization problem until the obtained control scheme satisfies the boundary constraints.

[0017] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention collects real-time data according to the scheduling cycle, inputs it into the model to update state variables and generate a preliminary regulation scheme, and combines boundary constraints to judge and adjust weight coefficients to generate a compliant scheme. This ensures that the regulation scheme can adapt to the dynamic changes in power generation, power consumption and electricity price of the distributed energy system in real time, and ensures the safety of energy storage equipment operation through constraint verification, thereby achieving real-time optimization under multiple objectives.

[0018] In one optional implementation, during the rolling optimization process, the number of times the control scheme fails to meet the boundary constraints is recorded. If the number of times exceeds a preset threshold, the reason why each control scheme fails to meet the boundary constraints is obtained. Based on the reasons why each regulation scheme fails to meet the boundary constraints, the parameters of the model prediction control framework are adjusted or the type of historical operating data is changed, and a personalized regulation energy storage model is retrained. Real-time operating data is input into a personalized energy storage control model for rolling optimization, generating a control scheme that meets boundary constraints.

[0019] The intelligent regulation and energy storage optimization method for distributed energy systems provided by this invention records the number of times the regulation scheme fails to meet boundary constraints, analyzes the reasons, adjusts model parameters or historical data types, and retrains a personalized model. This effectively solves the problem of insufficient model adaptability in special scenarios, enabling the intelligent regulation and energy storage model to achieve self-optimization and iteration for different operating conditions, continuously generating regulation schemes that meet boundary constraints, and further improving the robustness and adaptability of energy storage regulation in distributed energy systems.

[0020] Secondly, this invention provides an intelligent regulation and energy storage optimization system for distributed energy systems, the system comprising: The sample generation module is used to acquire historical operating data of distributed energy systems and generate a benchmark scheduling strategy sample set based on the historical operating data. The model framework building module is used to build a model prediction and control framework based on a two-layer optimization architecture and initialize the parameters of the model prediction and control framework. The model training module is used to set the optimization objective function by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, and to train the model predictive control framework using the benchmark scheduling strategy sample set to obtain the intelligent regulation energy storage model. The energy storage scheme generation module is used to acquire real-time operating data of distributed energy systems, use the real-time operating data to perform rolling optimization of the intelligent energy storage model, and generate energy storage schemes based on the optimization results.

[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the intelligent regulation and energy storage optimization method for distributed energy systems according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the second process of the intelligent regulation and energy storage optimization method for distributed energy systems according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the model prediction control framework of the two-layer optimization architecture in the intelligent regulation and energy storage optimization method for distributed energy systems according to an embodiment of the present invention. Figure 5 This is a structural block diagram of an intelligent regulation and energy storage optimization system for distributed energy systems according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] As an optional application scenario of this invention, such as Figure 1 As shown, this intelligent regulation and energy storage optimization system for distributed energy systems may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0029] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0030] This invention provides an intelligent regulation and energy storage optimization method for distributed energy systems. By generating a benchmark scheduling strategy sample set, constructing a two-layer optimization architecture model prediction and control framework, and training an intelligent regulation and energy storage model, the method achieves the effects of intelligent regulation and energy storage optimization of distributed energy systems, improving the renewable energy absorption rate, and reducing system operating costs.

[0031] According to an embodiment of the present invention, an embodiment of an intelligent regulation and energy storage optimization method for distributed energy systems is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] This embodiment provides an intelligent regulation and energy storage optimization method for distributed energy systems, which can be used in the aforementioned computer system. Figure 2 This is a flowchart of an intelligent regulation and energy storage optimization method for distributed energy systems according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain historical operating data of the distributed energy system and generate a benchmark scheduling strategy sample set based on the historical operating data.

[0033] Specifically, historical operating data of distributed energy systems includes, but is not limited to: photovoltaic power generation {PPV,t}, wind power generation {PWT,t}, user load power {PL,t}, and dynamic electricity price {Ct}. Different types of operating data at the same historical moment are taken as a set of historical data. For example, in an actual distributed energy system containing photovoltaic panels, wind turbines, and lithium-ion battery energy storage devices, hourly power generation data can be obtained through sensors installed on the photovoltaic panels and wind turbines, and user electricity load and grid dynamic electricity price information can be recorded through smart meters. This is just an example and is not a limitation. After preprocessing, the historical operating data is stored in a database for subsequent use. The preprocessing process is a mature existing technology and will not be elaborated here. Several superior control and storage schemes are selected from multiple sets of historical data as a benchmark scheduling strategy sample set.

[0034] Step S202: Construct a model predictive control framework based on a two-layer optimization architecture and initialize the parameters of the model predictive control framework.

[0035] Specifically, based on the operating characteristics of distributed energy systems and energy storage regulation objectives, a model predictive control framework based on a two-layer optimization architecture is constructed, and the parameters of the model predictive control framework are initialized to determine the regulation and energy storage model to be trained and optimized.

[0036] In step S203, an optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, and the model predictive control framework is trained using a benchmark scheduling strategy sample set to obtain an intelligent regulation energy storage model.

[0037] Specifically, an optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, which serves as the target for training the predictive control framework of the model. The model predictive control framework is trained using a benchmark scheduling strategy sample set to obtain an intelligent regulation energy storage model.

[0038] Step S204: Obtain real-time operating data of the distributed energy system, use the real-time operating data to perform rolling optimization of the intelligent regulation and energy storage model, and generate a regulation and energy storage scheme based on the optimization results.

[0039] Specifically, within each scheduling cycle, the state variables of the model predictive control framework are updated based on the real-time operational data of the distributed energy system. The parameters of the model predictive control framework are then continuously optimized by solving an optimization problem, and a control and storage scheme is generated based on the optimization results. State variables include, but are not limited to: energy utilization rate, operating cost, system stability, and energy storage lifetime. Energy utilization rate measures the proportion of renewable energy consumption; operating cost is used to calculate the total operating cost of the system; system stability is used to assess the impact of load fluctuations on the system; and energy storage lifetime considers the cyclic lifespan loss of energy storage devices.

[0040] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment generates a benchmark scheduling strategy sample set, constructs a model predictive control framework with a two-layer optimization architecture, and trains an intelligent regulation and energy storage model to achieve intelligent regulation and energy storage optimization for distributed energy systems. This significantly improves the renewable energy absorption rate and reduces system operating costs. At the same time, it ensures stable power supply, reduces the impact of load fluctuations, and extends the lifespan of energy storage equipment. Through real-time rolling optimization, it adapts to the dynamic changes in power generation, power consumption, and electricity prices, providing an efficient, economical, reliable, and sustainable energy storage regulation solution for distributed energy systems under multi-objective collaboration.

[0041] This embodiment provides an intelligent regulation and energy storage optimization method for distributed energy systems, which can be used in the aforementioned computer system. Figure 3 This is a flowchart of an intelligent regulation and energy storage optimization method for distributed energy systems according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain historical operating data of the distributed energy system and generate a benchmark scheduling strategy sample set based on the historical operating data.

[0042] Specifically, historical operating data includes: photovoltaic power generation, wind power generation, user load power, and dynamic electricity price. Step S301 above includes: Step S3011: Obtain the boundary constraints of the energy storage device, and use the Monte Carlo model to generate multiple scheduling strategy sequences that meet the boundary constraints.

[0043] Specifically, the charging and discharging power boundaries of each energy storage device constituting the distributed energy storage system are set as [Pmin, Pmax] and the state of charge boundary is set as [SoCmin, SoCmax]. Then, the Monte Carlo model is used to simulate and generate multiple scheduling strategy sequences that meet the constraints.

[0044] Step S3012: Calculate the optimization objective function value of each scheduling strategy sequence, and sort the scheduling strategy sequences from largest to smallest based on the optimization objective function value.

[0045] Specifically, for each scheduling strategy sequence, the corresponding comprehensive optimization objective function value is calculated, and the scheduling strategy sequences are sorted from largest to smallest according to the size of the optimization objective function value.

[0046] Step S3013: Based on the sorting results, take the first preset proportion of scheduling strategy sequences as the benchmark scheduling strategy sample set.

[0047] Specifically, based on the ranking results, the top 20% of scheduling strategy sequences are selected as the baseline scheduling strategy sample set. For example, in a certain experiment, the charging and discharging power boundary of the energy storage device is set to [-5, 5] kW, and the state of charge boundary is set to [20%, 80%]. After generating 1000 scheduling strategy sequences through Monte Carlo simulation, the comprehensive optimization objective function value of each sequence is calculated and ranked. The top 200 sequences are selected as the baseline scheduling strategy sample set. This is just an example, but not a limitation.

[0048] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment obtains the boundary constraints of energy storage devices, generates multiple sets of scheduling strategy sequences that meet the constraints using a Monte Carlo model, and then combines the high-quality sequences with a preset proportion of optimization objective function values ​​as a benchmark scheduling strategy sample set. This ensures that the generated scheduling strategies are within the safe operating range of the energy storage devices, while also retaining efficient and economical high-quality strategies through quantitative screening. This provides a high-quality and diverse sample foundation for subsequent model training, thereby improving the training effect of the intelligent regulation and energy storage model.

[0049] Step S302: Construct a model predictive control framework based on a two-layer optimization architecture and initialize the parameters of the model predictive control framework.

[0050] Specifically, the model prediction control framework based on a two-layer optimization architecture includes: an upper-layer optimization module and a lower-layer optimization module, and step S302 above includes: Step S3021: Generate the first parameter range of the upper-level optimization module and the second parameter range of the lower-level optimization module using a random normal distribution.

[0051] Specifically, in the two-layer optimization architecture of a distributed energy system, the upper-layer optimization module is responsible for global energy allocation (e.g., energy allocation strategies for photovoltaic, wind power, grid power, and energy storage), while the lower-layer optimization module is responsible for the fine-grained control of local energy storage devices (e.g., specific scheduling of charging and discharging power and time). During initialization, the parameter set of the upper-layer optimization module (the global energy allocation strategy formulation layer) is generated using a random normal distribution. The parameter set of the lower-level optimization module (the fine-grained control layer for local energy storage devices). and satisfy The constraints are defined. This initialization method ensures that the model parameters are within a reasonable range, avoiding training instability caused by initial values ​​that are too large or too small. The purpose of generating the parameter range is to provide an initial parameter selection space for these two modules, ensuring that the subsequently selected parameters are both diverse and cover possible reasonable value ranges, laying the parameter foundation for the efficient operation of the two-layer optimization architecture.

[0052] Step S3022: Based on preset constraints, select upper-level optimization parameters from the first parameter range and lower-level optimization parameters from the second parameter range.

[0053] Specifically, pre-defined constraints are established based on the actual operating rules and equipment safety requirements of the distributed energy system. For example, the parameters of the upper-level optimization module must meet constraints such as the renewable energy consumption ratio not being lower than a certain threshold and the grid purchase cost not exceeding the budget ratio; the parameters of the lower-level optimization module must meet constraints such as the energy storage charging and discharging power not exceeding the equipment's rated power and the energy storage state of charge (SOC) being within a safe range (e.g., 20%-80%). Through screening, parameters that do not meet the system's safety, economic, and technical requirements are eliminated, ensuring that the final upper-level and lower-level optimization parameters are feasible and reasonable.

[0054] For example, in a certain experimental scenario, the upper-level optimization module's It was initialized to [0.02, -0.01, 0.03], while the lower-level optimization module's... They are initialized to [-0.04, 0.01, 0.02], and these parameters will serve as the basis for subsequent offline training and online optimization.

[0055] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment generates parameter ranges for upper and lower optimization modules through random normal distribution, and then selects reasonable parameters by combining preset constraints. This provides scientific and reliable initial parameters for the model predictive control framework of the two-layer optimization architecture, ensuring the randomness and diversity of the parameters. The constraints ensure the rationality of the parameters, making the coordination between the upper-layer global allocation and the lower-layer local control more efficient, thereby improving the regulation accuracy and efficiency of the model predictive control framework in the energy storage optimization of distributed energy systems.

[0056] In step S303, an optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, and the model predictive control framework is trained using a benchmark scheduling strategy sample set to obtain an intelligent regulation energy storage model.

[0057] Specifically, step S303 includes: Step S3031: Obtain the calculation logic formulas for multiple state variables that affect the system's operating state, and initialize the initial weights of each state variable. The state variables include: energy utilization rate, operating cost, system stability, and energy storage lifetime.

[0058] Specifically, the calculation formulas for energy utilization rate, operating cost, system stability, and energy storage lifetime are as follows:

[0059] in, Indicates energy utilization rate, Indicates operating costs, Indicates system stability. Indicates energy storage lifespan. This indicates the power purchased from the main power grid. This indicates the charging and discharging power of the energy storage device. Indicates the cycle life of energy storage devices. Indicates the rated capacity of the energy storage device. This represents the average load power of the user. This represents the photovoltaic power generation at time t. This represents the wind power generation capacity at time t. This represents the user load power at time t. This represents the dynamic electricity price at time t.

[0060] Step S3032: Based on the calculation logic formula of each state variable and the corresponding initial weight, perform weighted summation to obtain the optimization objective function.

[0061] Specifically, based on the calculation logic formulas of each state variable and the corresponding initial weights, a weighted sum is performed to obtain the expression for the optimization objective function:

[0062] in, These are the weighting coefficients for each state variable indicator, used to adjust the importance of each indicator.

[0063] Within a certain scheduling period T=24 hours, assuming the photovoltaic power generation {PPV,t} and wind power generation {PWT,t} are [5, 6, 7, ...] kW and [3, 4, 5, ...] kW respectively, the user load power {PL,t} is [8, 9, 10, ...] kW, and the dynamic electricity price {Ct} is [0.5, 0.6, 0.7, ...] yuan / kWh, the specific values ​​of each indicator can be calculated according to the above formula, and the weighting coefficients can be adjusted accordingly. , , , To optimize the overall objective function J.

[0064] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment clarifies the calculation logic of multiple state variables and assigns initial weights, and obtains the optimization objective function by weighted summation, thereby achieving synergistic optimization of multi-dimensional objectives and quantitatively evaluating the comprehensive performance of distributed energy systems in terms of energy consumption, economic cost, power supply reliability and equipment durability.

[0065] Step S3033: Divide the baseline scheduling strategy sample set into a training set and a validation set according to a preset ratio.

[0066] Specifically, the baseline scheduling strategy sample set is divided into a training set and a validation set according to a preset ratio (e.g., 8:2 or 7:3). The training set is used for the model to learn the patterns of high-quality scheduling strategies, and the validation set is used to verify whether the model has truly mastered multi-objective optimization capabilities after training, thus avoiding overfitting, i.e., avoiding performance that is only good on historical data but fails in real-world scenarios.

[0067] Step S3034: Based on the training set, the model predictive control framework is jointly trained using a deep learning algorithm, with the output of the upper-level optimization module in the model predictive control framework serving as the input of the lower-level optimization module.

[0068] Specifically, such as Figure 4 The diagram illustrates the structure of a two-layer optimization architecture for model predictive control. The upper-layer optimization module is responsible for global energy allocation (e.g., the energy allocation ratio between photovoltaic, wind power, grid power, and energy storage), and its output (e.g., the energy storage needs to store 50kWh of electricity) directly serves as the input to the lower-layer optimization module. The lower-layer optimization module is responsible for fine-grained control of energy storage (e.g., at what power and for how long to complete the storage of 50kWh). Through joint training where the upper-layer output drives the lower-layer input, the model learns the optimal logic for the collaborative work of the two layers. For example, the upper layer allocates more grid power to energy storage during off-peak electricity prices, while the lower layer matches low-power, long-term charging to protect battery life, thereby achieving collaborative optimization of multiple objectives (energy utilization, cost, stability, and lifespan).

[0069] Step S3035: During the training process, the parameters of the upper-layer optimization module and the lower-layer optimization module are adjusted based on the optimization objective function value, and the optimization objective function value after each round of training is calculated using the validation set until the optimization objective function value converges or reaches the optimization objective function threshold, thereby obtaining the intelligent regulation energy storage model.

[0070] Specifically, during training, the parameters of the upper and lower optimization modules are continuously adjusted (e.g., the energy allocation weights in the upper layer and the charging and discharging power limit parameters in the lower layer) to make the scheduling scheme output by the model more optimized for the objective function value (e.g., higher energy utilization and lower cost). After each round of adjustment, the objective function value of the model is calculated using the validation set. If the value converges (no longer changes significantly) or reaches a preset threshold (e.g., the overall optimization effect exceeds 90% of the industry level), it indicates that the model has mastered the core principles of multi-objective optimization, and the intelligent regulation energy storage model is finally obtained.

[0071] For example, in a training iteration, the training set contains 160 samples and the validation set contains 40 samples. Through deep reinforcement learning algorithms, the model progressively learns how to generate the optimal scheduling strategy based on different input conditions. After training, the model achieves high prediction accuracy on the validation set, thus laying the foundation for subsequent online optimization.

[0072] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment uses a deep learning algorithm to jointly train a two-layer optimization architecture model predictive control framework. The upper layer output is used as the lower layer input, and the parameters are adjusted based on the optimization objective function value. The model fully learns the rules of high-quality scheduling strategies, and the coordination between the upper-layer global allocation and the lower-layer local control is more accurate, thereby improving the performance of the intelligent regulation and energy storage model in multi-objective optimization of energy utilization, operating cost, system stability, and energy storage life.

[0073] Step S304: Obtain real-time operating data of the distributed energy system, use the real-time operating data to perform rolling optimization of the intelligent regulation and energy storage model, and generate a regulation and energy storage scheme based on the optimization results.

[0074] Specifically, step S304 includes: Step S3041: Collect real-time operation data of the distributed energy system according to the preset scheduling cycle. The type of real-time operation data is consistent with that of historical operation data.

[0075] Specifically, the real-time photovoltaic power generation, real-time wind power generation, real-time user load power, and real-time dynamic electricity price of the distributed energy system are collected according to the preset scheduling cycle. Among them, the real-time photovoltaic power generation and real-time wind power generation reflect the real-time output of renewable energy, the real-time user load power reflects the real-time changes in electricity demand, and the real-time dynamic electricity price reflects the real-time fluctuations in electricity purchase costs.

[0076] Step S3042: Input the real-time operating data into the intelligent control energy storage model, update the real-time state variables, and generate a preliminary control scheme for the current scheduling cycle by solving the optimization problem based on the updated real-time state variables.

[0077] Specifically, after real-time operational data is input into the intelligent regulation and control energy storage model, the model updates real-time state variables (such as the current total renewable energy generation, the current total load demand, and the cost coefficient corresponding to the current electricity price). Based on the updated state variables, the model generates a preliminary regulation scheme by solving an optimization problem, that is, how the energy storage device should charge and discharge for the current cycle (e.g., how much charging power and how long the discharge time), in order to achieve a multi-objective synergy of maximizing energy utilization, minimizing operating costs, maximizing system stability, and minimizing energy storage lifespan loss.

[0078] Step S3043: Determine whether the preliminary control scheme meets the boundary constraints. If it does, then the preliminary control scheme is taken as the optimal control energy storage scheme.

[0079] Specifically, boundary constraints may include: the energy storage charging and discharging power cannot exceed the rated power of the equipment; the energy storage state of charge must be maintained within a safe range of 20%-80%; and the system power supply must not experience stability issues such as excessive voltage fluctuations or power outages. If the preliminary control scheme meets the boundary constraints, it indicates that the preliminary control scheme is feasible and safe, and it can be directly implemented as the optimal energy storage control scheme.

[0080] If the condition is not met in step S3044, the weight coefficients of each state variable are adjusted, and a new control scheme is generated by solving the optimization problem until the obtained control scheme satisfies the boundary constraints.

[0081] Specifically, if the initial solution does not meet the boundary constraints (e.g., energy storage discharge power exceeds the limit, state of charge is too low), the weight coefficients of each state variable are adjusted (e.g., the weights of system stability or energy storage safety are temporarily increased), and the optimization problem is solved again. Based on the real-time state and within the safety boundary constraints, a new control scheme is generated using the algorithm. This process is repeated until the solution meets all boundary constraints, ensuring that the final control scheme optimizes multiple objectives while remaining safe and compliant.

[0082] For example, during a certain scheduling cycle, real-time data shows that photovoltaic power generation is 6 kW, wind power generation is 4 kW, user load power is 10 kW, and the dynamic electricity price is 0.6 yuan / kWh. Based on this data, the model predictive control framework generates a charging / discharging command for the energy storage device of -2 kW (i.e., discharging 2 kW). If this command does not meet the state of charge constraints of the energy storage device, the weighting coefficients are adjusted and the solution is recalculated until a command that meets the constraints is generated.

[0083] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment collects real-time data according to the scheduling cycle, inputs it into the model to update state variables and generate a preliminary regulation scheme, and combines boundary constraints to judge and adjust weight coefficients to generate a compliant scheme. This ensures that the regulation scheme can adapt to the dynamic changes in power generation, power consumption and electricity price of the distributed energy system in real time. The constraint verification ensures the safety of the operation of the energy storage device and realizes real-time optimization under multiple objectives.

[0084] In some optional implementations, during the rolling optimization process, the number of times the control scheme fails to meet the boundary constraints is recorded. If the number of times the failure exceeds a preset threshold, the reason why each control scheme fails to meet the boundary constraints is obtained.

[0085] Specifically, during the rolling optimization process, the system records the number of times the control scheme fails to meet the boundary constraints (e.g., multiple consecutive instances of energy storage overcharging or excessive power supply voltage fluctuations). If this number exceeds a preset threshold (e.g., five consecutive instances of failing to meet the constraints), it is necessary to analyze the specific reasons for each constraint conflict. For example, aging of the energy storage equipment may result in actual charging and discharging capacity being lower than the model's preset parameters; extreme weather (e.g., continuous rain causing a sharp drop in photovoltaic output) may exceed the coverage of historical data; or user load may experience a sudden increase (e.g., large-scale events leading to a surge in electricity demand).

[0086] By analyzing the reasons why various control schemes do not meet the boundary constraints, we can identify specific scenarios where the model's adaptability is insufficient, providing a basis for subsequent model iterations.

[0087] Based on the reasons why each regulation scheme fails to meet the boundary constraints, the parameters of the model prediction control framework are adjusted or the type of historical operating data is changed, and a personalized regulation energy storage model is obtained through retraining.

[0088] Specifically, based on the reasons why each control scheme fails to meet the boundary constraints, the model undergoes targeted iterative optimization. For example, if the discrepancy between equipment parameters and actual conditions is the cause, parameters in the model's predictive control framework related to energy storage charging and discharging power and state of charge range are adjusted. If insufficient historical data coverage is the cause, historical operating data from extreme scenarios (such as photovoltaic data during continuous rainy periods or electricity consumption data during sudden large loads) are supplemented to expand the diversity of the baseline scheduling strategy sample set. Subsequently, the model is retrained based on the adjusted parameters or new data to obtain a personalized energy storage control model. This model can adapt to the current system's equipment status and operating scenario, resolving previous constraint conflict issues.

[0089] Real-time operating data is input into a personalized energy storage control model for rolling optimization, generating a control scheme that meets boundary constraints.

[0090] Specifically, real-time operational data is input into a personalized energy storage control model for rolling optimization. Since the model has already iterated to address the causes of constraint conflicts, it can generate control schemes in real-time scenarios that satisfy multiple objectives of energy utilization, operating costs, system stability, and energy storage lifespan optimization, while also fully complying with boundary constraints such as energy storage device safety and system power supply stability. This enables continuous and reliable optimization of distributed energy systems in complex scenarios.

[0091] The intelligent regulation and energy storage optimization method for distributed energy systems provided in this embodiment records the number of times the regulation scheme fails to meet boundary constraints, analyzes the reasons, adjusts model parameters or historical data types, and retrains the personalized model. This effectively solves the problem of insufficient model adaptability in special scenarios, enabling the intelligent regulation and energy storage model to achieve self-optimization and iteration for different operating conditions, continuously generating regulation schemes that meet boundary constraints, and further improving the robustness and adaptability of energy storage regulation in distributed energy systems.

[0092] This embodiment also provides an intelligent regulation and energy storage optimization system for distributed energy systems. This system is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] This embodiment provides an intelligent regulation and energy storage optimization system for distributed energy systems, such as... Figure 5 As shown, it includes: The sample generation module 501 is used to acquire historical operating data of the distributed energy system and generate a benchmark scheduling strategy sample set based on the historical operating data.

[0094] The model framework building module 502 is used to build a model prediction control framework based on a two-layer optimization architecture and initialize the parameters of the model prediction control framework.

[0095] The model training module 503 is used to set the optimization objective function by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, and to train the model predictive control framework using the benchmark scheduling strategy sample set to obtain the intelligent regulation energy storage model.

[0096] The regulation and energy storage scheme generation module 04 is used to acquire real-time operating data of the distributed energy system, use the real-time operating data to perform rolling optimization of the intelligent regulation and energy storage model, and generate a regulation and energy storage scheme based on the optimization results.

[0097] In some alternative implementations, the sample generation module 501 includes: The scheduling strategy sequence generation unit is used to obtain the boundary constraints of the energy storage device and generate multiple scheduling strategy sequences that meet the boundary constraints using the Monte Carlo model.

[0098] The sequence sorting unit is used to calculate the optimization objective function value of each scheduling policy sequence and sort the scheduling policy sequences from largest to smallest based on the optimization objective function value.

[0099] The sample selection unit is used to select the first preset proportion of scheduling strategy sequences as the benchmark scheduling strategy sample set based on the sorting results.

[0100] In some alternative implementations, the model framework building module 502 includes: The parameter range generation unit is used to generate the first parameter range of the upper-level optimization module and the second parameter range of the lower-level optimization module using a random normal distribution.

[0101] The optimization parameter determination unit is used to select upper-level optimization parameters from a first parameter range and lower-level optimization parameters from a second parameter range based on preset constraints.

[0102] In some alternative implementations, the model training module 503 includes: The objective function initialization unit is used to obtain the calculation logic formulas for multiple state variables that affect the system's operating state, and to initialize the initial weights of each state variable. The state variables include: energy utilization rate, operating cost, system stability, and energy storage lifetime.

[0103] The objective function optimization unit is used to perform weighted summation based on the calculation logic formula of each state variable and the corresponding initial weight to obtain the optimized objective function.

[0104] The data partitioning unit is used to divide the baseline scheduling strategy sample set into a training set and a validation set according to a preset ratio.

[0105] The model training unit is used to jointly train the model predictive control framework based on the training set and using deep learning algorithms. The output of the upper-level optimization module in the model predictive control framework is used as the input of the lower-level optimization module.

[0106] The model optimization unit is used during training to adjust the parameters of the upper and lower optimization modules based on the optimization objective function value, and to calculate the optimization objective function value after each round of training using the validation set, until the optimization objective function value converges or reaches the optimization objective function threshold, thus obtaining the intelligent regulation energy storage model.

[0107] In some optional implementations, the energy storage scheme generation module 504 includes: The real-time data acquisition unit is used to collect real-time operating data of the distributed energy system according to a preset scheduling cycle. The type of real-time operating data is consistent with that of historical operating data.

[0108] The preliminary scheme generation unit is used to input real-time operating data into the intelligent regulation and energy storage model, update the real-time state variables, and generate a preliminary regulation scheme for the current scheduling cycle by solving optimization problems based on the updated real-time state variables.

[0109] The constraint judgment unit is used to determine whether the preliminary control scheme meets the boundary constraint conditions. If it does, the preliminary control scheme is taken as the optimal control energy storage scheme.

[0110] The weight adjustment unit is used to adjust the weight coefficients of each state variable if the conditions are not met, and to generate a new control scheme by solving the optimization problem until the obtained control scheme satisfies the boundary constraints.

[0111] The intelligent regulation and energy storage optimization system for distributed energy systems provided in this embodiment of the invention can execute the intelligent regulation and energy storage optimization method for distributed energy systems provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0112] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0113] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0114] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0115] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the intelligent regulation and energy storage optimization method for distributed energy systems according to embodiments of the present invention.

[0116] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0117] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the intelligent regulation and energy storage optimization method for distributed energy systems shown in the above embodiments is implemented.

[0118] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A smart regulation and energy storage optimization method for distributed energy systems, characterized in that, The method includes: Obtain historical operating data of the distributed energy system, and generate a benchmark scheduling strategy sample set based on the historical operating data; A model prediction control framework based on a two-layer optimization architecture is constructed, and the parameters of the model prediction control framework are initialized. An optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime. The model predictive control framework is trained using a benchmark scheduling strategy sample set to obtain an intelligent regulation energy storage model. The system acquires real-time operating data of the distributed energy system, uses the real-time operating data to perform rolling optimization of the intelligent regulation and energy storage model, and generates a regulation and energy storage scheme based on the optimization results.

2. The method according to claim 1, characterized in that, The historical operating data includes: photovoltaic power generation, wind power generation, user load power, and dynamic electricity price. Based on the historical operating data, a benchmark scheduling strategy sample set is generated, including: Obtain the boundary constraints of the energy storage device, and use the Monte Carlo model to generate multiple scheduling strategy sequences that meet the boundary constraints; Calculate the objective function value of each scheduling strategy sequence, and sort the scheduling strategy sequences from largest to smallest based on the objective function value; Based on the sorting results, the first preset proportion of scheduling strategy sequences are taken as the baseline scheduling strategy sample set.

3. The method according to claim 1, characterized in that, The model prediction control framework based on a two-layer optimization architecture includes: an upper-layer optimization module and a lower-layer optimization module. The framework is constructed and its parameters are initialized, including: The first parameter range of the upper-level optimization module and the second parameter range of the lower-level optimization module are generated using a random normal distribution. Based on preset constraints, upper-level optimization parameters are selected from the first parameter range, and lower-level optimization parameters are selected from the second parameter range.

4. The method according to claim 1, characterized in that, The optimization objective function is set by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, including: Obtain the calculation logic formulas for multiple state variables that affect the system's operating state, and initialize the initial weights of each state variable. The state variables include: energy utilization rate, operating cost, system stability, and energy storage lifetime. The objective function is obtained by weighted summation based on the calculation logic formulas of each state variable and the corresponding initial weights.

5. The method according to claim 1, characterized in that, The model predictive control framework is trained using a baseline scheduling strategy sample set to obtain an intelligent regulation and control energy storage model, including: The baseline scheduling strategy sample set is divided into a training set and a validation set according to a preset ratio; Based on the training set, the model prediction control framework is jointly trained using a deep learning algorithm, and the output of the upper-level optimization module in the model prediction control framework is used as the input of the lower-level optimization module. During training, the parameters of the upper-level optimization module and the lower-level optimization module are adjusted based on the optimization objective function value. The optimization objective function value after each round of training is calculated using the validation set until the optimization objective function value converges or reaches the optimization objective function threshold, thus obtaining the intelligent regulation energy storage model.

6. The method according to claim 1, characterized in that, Acquiring real-time operational data of the distributed energy system and using the real-time operational data to perform rolling optimization of the intelligent regulation and energy storage model includes: Real-time operation data of the distributed energy system is collected according to a preset scheduling cycle, and the type of the real-time operation data is consistent with that of the historical operation data. The real-time operating data is input into the intelligent control energy storage model to update the real-time state variables. Based on the updated real-time state variables, a preliminary control scheme for the current scheduling cycle is generated by solving the optimization problem. Determine whether the preliminary control scheme meets the boundary constraints. If it does, then the preliminary control scheme is taken as the optimal control energy storage scheme. If the conditions are not met, the weight coefficients of each state variable are adjusted, and a new control scheme is generated by solving the optimization problem until the obtained control scheme satisfies the boundary constraints.

7. The method according to claim 6, characterized in that, During the rolling optimization process, the number of times the control scheme fails to meet the boundary constraints is recorded. If the number of times exceeds a preset threshold, the reason why each control scheme fails to meet the boundary constraints is obtained. Based on the reasons why the various control schemes do not meet the boundary constraints, the parameters of the model prediction control framework are adjusted or the type of historical operating data is changed, and a personalized control energy storage model is retrained. The real-time operating data is input into the personalized control energy storage model for rolling optimization to generate a control scheme that meets the boundary constraints.

8. A smart regulation and energy storage optimization system for distributed energy systems, characterized in that, The system includes: The sample generation module is used to acquire historical operating data of the distributed energy system and generate a benchmark scheduling strategy sample set based on the historical operating data. The model framework construction module is used to construct a model prediction and control framework based on a two-layer optimization architecture and initialize the parameters of the model prediction and control framework. The model training module is used to set the optimization objective function by combining energy utilization rate, operating cost, system stability, and energy storage lifetime, and to train the model predictive control framework using the benchmark scheduling strategy sample set to obtain the intelligent regulation energy storage model. The energy storage scheme generation module is used to acquire real-time operating data of the distributed energy system, use the real-time operating data to perform rolling optimization of the intelligent energy storage model, and generate an energy storage scheme based on the optimization results.

9. An electronic device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images