A multi-scene-oriented wall-type energy storage resource aggregation optimization method and system

Abstract

The application relates to a multi-scene-oriented wall-type energy storage resource aggregation optimization method and system, which comprises the following steps: obtaining the operation parameters of various wall-type energy storage devices to be optimized by arranging intelligent sensors; performing feature extraction on the operation parameters based on a nonlinear feature extraction function to generate standardized energy features; obtaining historical fault data of the wall-type energy storage devices to be optimized, constructing a device health assessment model according to the historical fault data and the energy features, identifying the change trend of the device health state, and outputting an index matrix representing the device health degree; constructing a resource function based on the energy features and the index matrix, and outputting a control strategy of the wall-type energy storage device based on the resource function. Compared with the prior art, the application can dynamically adjust the control strategy according to the actual operation of the wall-type energy storage device under different scenes, improve the utilization efficiency of the energy storage resource, and guarantee the stable and reliable operation of the device.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, and in particular to a method and system for the aggregation and optimization of wall-mounted energy storage resources for multiple scenarios. Background Technology

[0002] With the large-scale integration of renewable energy into the grid, its intermittent and fluctuating characteristics pose severe challenges to the stable supply and flexible regulation of the power system. Energy storage technology has become a key support for balancing supply and demand, smoothing output, and improving grid reliability. Wall-mounted energy storage is designed to match the intermittent nature of renewable energy (such as solar and wind power) and solve the problem of unstable power generation.

[0003] For example, in industrial settings where high energy consumption fluctuations, continuous equipment operation, and energy conservation are crucial, wall-mounted energy storage can assist in peak shaving, waste heat recovery, and stable power supply. In commercial settings, load regulation and emergency power supply are key concerns, and wall-mounted energy storage can improve energy efficiency and reduce operating costs. In transportation settings, the concentrated charging load and high grid pressure need to be addressed, and wall-mounted energy storage can enable dynamic charging scheduling and energy feedback. However, in practical applications, the management and control of wall-mounted energy storage systems are easily affected by the health of the equipment. Furthermore, electrochemical energy storage (especially lithium-ion batteries) carries the risk of fire due to thermal runaway, resulting in relatively low efficiency and reliability in the management and control process.

[0004] Therefore, how to dynamically adjust the control strategy based on the actual operation of wall-mounted energy storage devices in different scenarios to improve the efficiency and reliability of the management process is an urgent technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the existing technology and provide a method and system for the aggregation and optimization of wall-mounted energy storage resources for multiple scenarios, thereby solving the problem of low efficiency and reliability in the management and control process of wall-mounted energy storage resources to at least a certain extent.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A method for resource aggregation and optimization of wall-mounted energy storage for multiple scenarios includes the following steps:

[0008] By deploying smart sensors, the operating parameters of various wall-mounted energy storage devices to be optimized are obtained;

[0009] The operating parameters are feature-extracted based on a nonlinear feature extraction function to generate standardized energy features;

[0010] Historical fault data of the wall-mounted energy storage device to be optimized is obtained. Based on the historical fault data and the energy characteristics, an equipment health assessment model is constructed to identify the changing trend of the equipment health status and output an index matrix representing the health of the equipment.

[0011] Based on the energy characteristics and the exponential matrix, a resource function is constructed, and a control strategy for the wall-mounted energy storage device is output based on the resource function.

[0012] Furthermore, based on a nonlinear feature extraction function, features are extracted from the operating parameters to generate standardized energy features, specifically including:

[0013] The time series of the operating parameters is decomposed in the frequency domain to generate the first feature in the time dimension, so as to capture the periodic and transient features of the equipment when responding to the power grid peak shaving.

[0014] The running parameters are mapped to a second feature through a non-linear feature extraction function;

[0015] The first feature and the second feature are fused to generate a standardized energy feature.

[0016] Furthermore, the time series is decomposed in the frequency domain using a time series extraction function, and the expression for the first feature obtained is as follows:

[0017]

[0018] In the formula, express t The first feature corresponding to time moment f This represents the frequency domain data corresponding to the operating parameters. T Represents the transpose of a vector;

[0019] The calculation expression for the standardized energy feature is generated by fusing the first feature and the second feature:

[0020]

[0021] In the formula, Indicates energy characteristics, An embedding matrix representing the device space topology. Indicates the Kronecker product; Represents the reference power vector. Represents the feature weight coefficients. Indicates the first k Operational data generated by wall-type energy storage devices Nonlinear feature extraction function, n This represents the total number of categories of wall-mounted energy storage devices.

[0022] Furthermore, the process of generating the index matrix characterizing the health of the equipment is as follows:

[0023] The energy characteristics are mapped to quantum state basis vectors;

[0024] The probability amplitude of the qubit is determined based on the historical fault data.

[0025] A device health assessment model is constructed based on the quantum state basis vector and the quantum bit probability amplitude, and an exponential matrix characterizing the device health is output through the device health assessment model.

[0026] Furthermore, the calculation expression for the equipment health assessment model is as follows:

[0027]

[0028] In the formula, For the first i A health index matrix for wall-mounted energy storage devices. N The standardization factor is the total number of basis vectors. M The square root of; M The total number of basis vectors representing a quantum state; Denotes the probability amplitude of a qubit, and denotes the probability amplitude of the first qubit. j The weights of the basis vectors in the superposition state; The quantum state basis vectors are represented using Bloch spheres to represent the first quantum state of a wall-mounted energy storage device. j Typical operating states; Indicates the first i The device in time t Spatial state d The energy characteristics below; Indicates the first j Reference feature vector of class state; Represents the variance of the Gaussian function; This represents the Euclidean distance operator.

[0029] Furthermore, a resource function is constructed based on the energy characteristics and the exponential matrix, and a control strategy for the wall-mounted energy storage device is output based on the resource function, specifically including:

[0030] The health parameters are determined based on the exponential matrix, the efficiency parameters are determined based on the energy characteristics, and the decay parameters are determined through the exponential decay function according to the aggregation strategy of the wall-mounted energy storage device.

[0031] A resource function is constructed based on the efficiency parameter, the health parameter, and the decay parameter, and a control strategy is output through the resource function.

[0032] Furthermore, the calculation expression for the health parameters, determined based on the aforementioned index matrix, is as follows:

[0033]

[0034] In the formula, Indicates wall-mounted energy storage equipment i Health parameters, Indicates health factors, Indicates wall-mounted energy storage equipment i Operating cost coefficient, Indicates the first i A health index matrix for wall-mounted energy storage devices;

[0035] The calculation expression for the efficiency parameter based on the energy characteristics is as follows:

[0036]

[0037] In the formula, Indicates wall-mounted energy storage equipment i Efficiency parameters, Represents the efficiency factor. Indicates wall-mounted energy storage equipment i The efficiency degradation of each energy storage unit in the energy characteristics. Indicates wall-mounted energy storage equipment i The initial efficiency in the energy characteristics. i and N These represent the equipment identifier and the total number of equipment, respectively.

[0038] Based on the aggregation strategy of wall-mounted energy storage devices, the calculation expression for the decay parameter, determined by the exponential decay function, is as follows:

[0039]

[0040] In the formula, Indicates wall-mounted energy storage equipment i The attenuation parameter, Indicates wall-mounted energy storage equipment i Reliability degradation factor Indicates wall-mounted energy storage equipment i The aggregation strategy.

[0041] Furthermore, the resource function integrates the health parameter, efficiency parameter, and decay parameter through weighted fusion, and adjusts the weights according to different scenario requirements through a dynamic weighting mechanism.

[0042] Furthermore, the method also includes sending the control strategy to the control terminal of the wall-mounted energy storage device.

[0043] This invention also provides a wall-mounted energy storage resource aggregation and optimization system based on the above-described multi-scenario wall-mounted energy storage resource aggregation and optimization method, comprising:

[0044] The acquisition module is used to acquire the operating parameters of various wall-mounted energy storage devices to be optimized by deploying smart sensors;

[0045] The feature module is used to extract features from the operating parameters based on a nonlinear feature extraction function to generate standardized energy features;

[0046] The index module is used to acquire historical fault data of the wall-mounted energy storage device to be optimized, construct an equipment health assessment model based on the historical fault data and the energy characteristics, identify the changing trend of the equipment health status, and output an index matrix representing the health of the equipment.

[0047] The strategy module is used to construct a resource function based on the energy characteristics and the exponential matrix, and output the control strategy of the wall-mounted energy storage device based on the resource function;

[0048] The control module is used to send the control strategy to the control terminal.

[0049] Compared with the prior art, the present invention has the following advantages:

[0050] (1) Based on nonlinear feature extraction, the present invention generates standardized energy features, which can better mine data characteristics. Combined with the health assessment model constructed by historical fault data, it can effectively assess the health of the equipment. Based on this, a resource function is constructed to output the control strategy and send it to the terminal. It can dynamically adjust the control strategy according to the actual operation of the wall-mounted energy storage equipment in different scenarios, improve the utilization efficiency of energy storage resources, and ensure the stable and reliable operation of the equipment.

[0051] (2) This invention generates a first feature in the time dimension by frequency domain decomposition of the time series composed of operating parameters, thereby uncovering the inherent patterns of the parameters in the time series. The device attribute information is mapped to a second feature, fully considering the characteristics of the device itself. The first and second features are fused to generate standardized energy features, making the energy features of different devices and scenarios comparable and universal. This provides a unified and standardized feature input for the subsequent construction of health assessment models and resource functions, improving the accuracy and adaptability of the model.

[0052] (3) The exponential matrix of device health generated by this invention integrates quantum state optimization results with historical failure mode analysis to quantitatively evaluate the reliability level of each device in aggregated scheduling. For example, devices with high health are assigned higher weights in grid peak shaving and valley filling tasks, which not only ensures safe operation but also improves the overall utilization efficiency of energy storage resources, forming a complete closed loop from data acquisition to strategy generation.

[0053] The output index matrix can intuitively represent the health of the equipment. This index matrix allows for timely understanding of the equipment's health status, early detection of potential health problems, and provides an important basis for developing reasonable control strategies, thus facilitating preventative maintenance and optimized operation of the equipment.

[0054] (4) The resource function constructed in this invention starts from the dimensions of economy, efficiency and reliability, and determines the parameters from three aspects: equipment health, energy utilization efficiency and reliability decay. The health parameter reflects the impact of the equipment's health status on resource aggregation, the efficiency parameter reflects the equipment's performance in energy conversion and utilization, and the decay parameter considers the changes in equipment reliability over time or other factors.

[0055] Furthermore, a dynamic weighting mechanism balances conflicts between objectives. For example, during peak electricity price periods, the weight of the economic objective is automatically increased, prioritizing the allocation of energy storage resources to reduce electricity costs; when equipment is operating under high load, the reliability weight is enhanced to prevent overuse that could damage the equipment. This dynamic adjustment mechanism ensures that the optimization model always adapts to the needs of the actual scenario. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating a multi-scenario-oriented wall-mounted energy storage resource aggregation and optimization method provided in an embodiment of the present invention.

[0057] Figure 2 This is a schematic diagram of a process for generating energy features provided in an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram of a wall-mounted energy storage resource aggregation and optimization system for multiple scenarios provided in an embodiment of the present invention;

[0059] Figure 4 This is a schematic diagram of the structure of a computer system used to implement an electronic device according to an embodiment of the present invention. Detailed Implementation

[0060] 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, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0061] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0062] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0063] Example 1

[0064] Figure 1 A flowchart of a multi-scenario wall-mounted energy storage resource aggregation and optimization method according to an embodiment of this application is shown. (Refer to...) Figure 1 As shown, this multi-scenario wall-mounted energy storage resource aggregation and optimization method includes at least steps S110 to S150, which are detailed below:

[0065] The S110 acquires operating parameters of various wall-mounted energy storage devices by deploying intelligent sensors.

[0066] In one embodiment of this application, during the installation phase of the wall-mounted energy storage device, a sensor deployment scheme is pre-planned based on the device type and scenario requirements. For example, in residential scenarios where temperature rise monitoring is emphasized, a miniature temperature sensor array is uniformly deployed on the surface of the energy storage unit; in industrial scenarios where current fluctuations are of concern, high-precision current sensors are installed at critical line nodes. During deployment, a dual fixing method combining magnetic attraction and thermally conductive adhesive is employed to ensure stable contact of the sensors even when the device vibrates or experiences temperature changes, thus preventing data drift.

[0067] In this embodiment, the wall-mounted energy storage device may include, but is not limited to, power generation equipment, integrated batteries, inverters, and energy storage converters.

[0068] A sensor network or self-organizing network is constructed among smart sensors. Sensor data acquisition employs adaptive sampling rate technology, dynamically adjusting the sampling frequency based on the device's operating status. When the energy storage device is in standby mode, the sampling rate is reduced to decrease energy consumption; when a sudden change in charging / discharging current is detected, the sampling rate is immediately increased to the millisecond level to capture transient parameter changes. All sensors are networked via a low-power Bluetooth mesh network, enabling self-organizing data transmission. This avoids the impact of wiring complexity on device aesthetics and installation efficiency, achieving industrial big data acquisition and providing a data foundation for industrial big data processing.

[0069] The data transmission process employs edge computing-based preprocessing technology. Sensor nodes have built-in microprocessors and other edge computing modules, or the raw data can be preliminarily filtered and compressed directly by deploying edge computing nodes. For example, temperature sensors will remove abnormal data with ambient temperature fluctuations exceeding ±2℃, while current sensors will smooth short-term noise using a sliding window algorithm. The preprocessed data is then transmitted to the central processing unit via an encrypted tunnel, ensuring both security and real-time performance during transmission.

[0070] The sensor network and the central system maintain data consistency through a dynamic calibration mechanism. The central system periodically sends calibration commands to the sensors, which adjust their measurement zero point and range accordingly, ensuring that sensor data from different devices and batches can be compared horizontally. When a sensor's data is detected to deviate from the average value by more than a preset threshold, a redundant sensor replacement mechanism is automatically triggered, switching to a backup sensor channel to ensure the continuity and reliability of parameter acquisition.

[0071] The above process, through the appropriate deployment of smart sensors, enables the comprehensive and accurate acquisition of various operating parameters of the wall-mounted energy storage device, providing a rich data foundation for subsequent analysis and optimization. These parameters cover key information about the device's operation, helping to gain a deeper understanding of the device's actual operating status.

[0072] S120 extracts features from operating parameters based on a nonlinear feature extraction function to generate standardized energy features.

[0073] In one embodiment of this application, the original operating parameters collected by the sensor are dynamically nonlinearly mapped using multi-dimensional data fusion technology. First, heterogeneous parameters such as temperature rise and current fluctuation are spatiotemporally aligned and noise is filtered out. Then, an adaptive nonlinear transformation network is used to deeply mine the implicit correlations between parameters. Finally, the feature space is compressed to a standardized energy dimension through normalization mapping to generate a unified feature vector that retains the dynamic characteristics of the original parameters and adapts to the optimization needs of multiple scenarios.

[0074] like Figure 2 As shown, in one embodiment of this application, features are extracted from the operating parameters based on a nonlinear feature extraction function to generate standardized energy features, including:

[0075] S210, perform frequency domain decomposition on the time series composed of operating parameters to generate the first feature in the time dimension;

[0076] S220 maps the running parameters to a second feature through a non-linear feature extraction function;

[0077] S230, the first and second features are fused to generate a standardized energy feature.

[0078] In one embodiment of this application, a time series composed of operating parameters is decomposed in the frequency domain to generate a first feature in the time dimension. Specifically, a time series extraction function is used to decompose the time series in the frequency domain to generate... t The first feature corresponding to time moment for:

[0079]

[0080] in, f This represents the frequency domain data corresponding to the operating parameters. T This represents the transpose of a vector. The aforementioned time-series extraction function is used to capture the periodic characteristics (such as daily periodic load fluctuations) and transient characteristics (such as fault impacts) of equipment responding to grid peak shaving.

[0081] In one embodiment of this application, operating parameters are mapped to a second feature using a nonlinear feature extraction function. For example, a nonlinear feature extraction function is designed; for instance, a curve mapping function is used in lithium batteries to extract capacitance features from operating parameters as the second feature. V for:

[0082]

[0083] in, V This represents the real-time voltage value, reflecting the current output capability of the device, and is derived from the battery electrochemical model. This represents the initial voltage reference, used for standardization to eliminate individual device variations. R This represents the internal resistance coefficient, which characterizes the degree of battery aging; a larger value indicates more severe degradation. I This indicates the operating current, which is directly related to the charging and discharging power and affects the voltage dynamic response. K The SOC coupling coefficient is used to quantify the nonlinear effect of the state of charge on the voltage; SOC represents the state of charge (range 0-1) and is used to determine the available energy of the battery. This represents the temperature compensation term, which corrects the voltage deviation caused by ambient temperature through a thermodynamic model, ensuring the accuracy of feature extraction. The above calculations generate the spatiotemporal feature vector of the lithium battery, which serves as the second feature. Its output V, along with parameters such as SOC and temperature, constitutes the input for health assessment, realizing the mathematical modeling of the device's physical characteristics.

[0084] In one embodiment of this application, the first feature and the second feature are fused to obtain the vital energy feature. for:

[0085]

[0086] in, This represents the first feature obtained through the temporal extraction function. This is the matrix corresponding to the spatial location topology of the wall-mounted energy storage device. Indicates the Kronecker product; Represents the reference power vector. Represents the feature weight coefficients. Indicates the first k Operating data generated by such devices Nonlinear feature extraction functions, such as the curve mapping function of lithium batteries and the equivalent circuit model of supercapacitors, are used. The first term of the life energy feature is the first feature, and the second term represents the second feature. This encoding breaks through the traditional static feature extraction and achieves dynamic coupling representation of spatiotemporal energy attributes.

[0087] The above process captures the fluctuation characteristics of the power grid load in real time by extracting frequency domain characteristics. For example, the load difference between the morning peak (7:00-9:00) and the evening peak (18:00-20:00) is automatically distinguished in the feature vector. The embedding matrix of the equipment spatial topology preserves the physical connection relationship between the equipment. For example, the topological distance between the wall-mounted energy storage cabinet in the community and the electric vehicle charging pile directly affects their coordinated scheduling priority. The physical characteristics of the equipment are transformed into mathematical characteristics through nonlinear feature extraction functions. For example, the SOC-voltage curve mapping of lithium batteries ensures that the charging and discharging strategy meets the equipment safety boundary.

[0088] This process nonlinearly fuses dynamic features from the temporal dimension with topological features from the spatial dimension to generate a comprehensive feature vector that possesses both spatiotemporal attributes. A dynamic weighting mechanism balances the differences in characteristics across different devices in the spatiotemporal dimensions; for example, the weighting of the high energy density of lithium batteries and the high power density of supercapacitors during fusion. The resulting standardized feature vector set comprehensively reflects the energy state and interaction capabilities of devices in the spatiotemporal dimensions, providing unified and dynamic data support for subsequent device health assessments and scheduling strategy generation.

[0089] The above process, by performing frequency domain decomposition on the time series of operating parameters to generate the first feature in the time dimension, uncovers the inherent patterns of the parameters in the time series. Mapping device attribute information to the second feature fully considers the characteristics of the device itself. The first and second features are then fused to generate standardized energy features, making energy features from different devices and scenarios comparable and universal. This provides a unified and standardized feature input for subsequent construction of health assessment models and resource functions, improving the accuracy and adaptability of the model.

[0090] S130: Acquire historical fault data, construct an equipment health assessment model based on historical fault data and energy characteristics, and output an index matrix representing the health of the equipment through the equipment health assessment model.

[0091] In one embodiment of this application, a health assessment model is dynamically constructed by integrating historical fault modes and real-time energy characteristics. First, a multi-dimensional correlation analysis is performed on historical fault data to uncover the evolution pattern of energy characteristics before the fault occurs. Then, the standardized energy characteristics collected in real time are dynamically matched with historical patterns. Through a hybrid learning mechanism of unsupervised clustering and supervised classification, the changing trend of equipment health status is automatically identified. Finally, an index matrix containing multi-dimensional health indicators is output, realizing a leapfrog upgrade from single fault warning to full life cycle health management.

[0092] In one embodiment of this application, historical fault data is acquired, and an equipment health assessment model is constructed based on the historical fault data and energy characteristics. The equipment health assessment model outputs an index matrix characterizing the equipment health, including:

[0093] Map energy characteristics to quantum state basis vectors;

[0094] Acquire historical fault data and determine the probability amplitude of qubits based on the historical fault data;

[0095] A device health assessment model is constructed based on quantum state basis vectors and qubit probability amplitudes, and an exponential matrix characterizing the device health is output through the device health assessment model.

[0096] In one embodiment of this application, the health assessment of a distributed wall-mounted energy storage device first involves quantum state encoding of the generated standardized energy characteristics. By simulating the superposition characteristics of a quantum system, the device's operational characteristics in the time-space dimension are mapped to qubit states. For example, dynamic behaviors such as the device's charge-discharge cycle and temperature fluctuations are converted into probability distributions of qubits, providing a basic state representation for subsequent quantum optimization calculations. The energy characteristics representing the device's spatiotemporal features are mapped to quantum state basis vectors, with each quantum state corresponding to a device's operational state, such as normal, slightly degraded, or severely degraded. For example, the SOC-voltage curve of a lithium battery is mapped to a Bloch sphere, and its state probability distribution is represented by qubits.

[0097] In one embodiment of this application, historical fault data is acquired, and the probability amplitude of qubits is determined based on this data. The selection, crossover, and mutation operations in a quantum genetic algorithm are simulated. By iteratively adjusting the angle parameters of the qubits, the device state vector gradually approaches the optimal health state. Then, an index matrix representing the device's health is determined based on the parameter tuning under the optimal health state. For example, for devices with frequent start-stop cycles, the weight allocation of their fatigue resistance characteristics is enhanced to improve the accuracy of health assessment. The probability amplitude of qubits is dynamically optimized through a quantum rotating door adjustment mechanism. The rotating door angle is adjusted in real time based on historical fault data; for example, devices with high failure rates correspond to larger rotation angles, accelerating the convergence of the health index.

[0098] In one embodiment of this application, the optimized quantum state is compared and analyzed with historical fault data of the device through a dynamic calibration mechanism. The current state of the device is matched against a preset reference state library to identify whether there is an abnormal degradation trend. The reference state library includes the correspondence between the operating data and state labels of each device. For example, by comparing the capacity decay curves of similar devices under the same operating cycle, potential fault risks are identified and marked, providing a basis for dynamic adjustment of the health index. A device health assessment model is constructed based on the quantum state basis vectors and qubit probability amplitudes. The device health assessment model outputs a characterization of the first quantum state. i Health index matrix of the device for:

[0099]

[0100] in, N The standardization factor is the total number of basis vectors. M The square root of the value ensures the normalization of the probability amplitude, which is derived from the superposition state normalization requirement in quantum computing; M This represents the total number of basis vectors of a quantum state, corresponding to the number of possible state categories of the device, such as normal, slightly degraded, or severely degraded. Denotes the probability amplitude of a qubit, and denotes the probability amplitude of the first qubit. j The weights of the basis vectors in the superposition state are dynamically optimized using a quantum rotation gate. The quantum state basis vectors are represented using the Bloch spherical representation device. j A typical operating state originates from the state vector representation in quantum computing; Indicates the first i The device in time t Spatial state d The energy characteristics below; Indicates the first j The reference feature vector for a class state is usually taken from the device's factory parameters or the average of its historical health status. This represents the variance of the Gaussian function, which controls the rate of exponential decay. The smaller the value, the more sensitive it is to state differences. This represents the Euclidean distance operator, which quantifies the difference between the current state of the device and the reference state.

[0101] In this embodiment, the generated device health index matrix integrates quantum state optimization results with historical failure mode analysis to quantitatively assess the reliability level of each device in aggregated scheduling. For example, devices with high health are assigned higher weights in grid peak shaving and valley filling tasks, ensuring safe operation while improving the overall utilization efficiency of energy storage resources, forming a complete closed loop from data acquisition to strategy generation.

[0102] Dynamic calibration of health status is achieved through a quantum rotating gate adjustment mechanism. Compared to traditional machine learning models, this evaluation method exhibits an exponential convergence advantage in capturing nonlinear degradation features. The quantum rotating gate adjustment mechanism makes the algorithm 1-2 orders of magnitude faster than traditional machine learning models in capturing nonlinear degradation features, reducing the fitting error of the lithium battery capacity decay curve. Through real-time optimization of the quantum bit probability amplitude, the health index can adapt to changes in device state; for example, accelerated degradation of the device under high-temperature environments will be captured by the dynamic calibration mechanism. The health index is directly used as a weighting coefficient in the scheduling strategy of step three. For example, devices with high health are assigned higher weights in peak shaving and valley filling tasks, improving the safety and efficiency of aggregated scheduling.

[0103] The above process, utilizing the properties of quantum states, can more accurately describe the complex relationship between energy characteristics and equipment health status. By determining the probability amplitude of qubits through historical fault data, it fully draws on past fault experience, enabling the model to better capture the changing trends of equipment health status. Taking into account both energy characteristics and historical fault data, the output exponential matrix can intuitively characterize the equipment's health. This exponential matrix allows for timely understanding of the equipment's health status, early detection of potential health problems, and provides an important basis for developing reasonable control strategies, facilitating preventative maintenance and optimized operation of the equipment.

[0104] S140 constructs a resource function based on energy characteristics and an exponential matrix, and outputs a control strategy through the resource function.

[0105] In one embodiment of this application, the process of constructing a resource function based on energy characteristics and an exponential matrix involves comprehensively analyzing the interaction between energy characteristics and multi-dimensional correlation matrices to form a function model that can dynamically reflect resource allocation efficiency. Then, based on the output trend and constraints of the function model, a control strategy adapted to the current operating state is derived to achieve the optimization objective.

[0106] In one embodiment of this application, a resource function is constructed based on energy characteristics and an exponential matrix, and a control strategy is output through the resource function, including:

[0107] Health parameters are determined based on the exponential matrix, efficiency parameters are determined based on energy characteristics, and decay parameters are determined through exponential calculations.

[0108] A resource function is constructed based on efficiency parameters, health parameters, and decay parameters, and a control strategy is output through the resource function.

[0109] In one embodiment of this application, a multi-objective collaborative optimization model is constructed based on the integrated feature vectors. From the dimensions of economy, efficiency, and reliability, a dynamic weighting mechanism balances the conflicts between the objectives. For example, during peak electricity price periods, the weight of the economy objective is automatically increased, prioritizing the scheduling of energy storage resources to reduce electricity costs; when equipment is operating under high load, the reliability weight is enhanced to prevent overuse leading to equipment damage. This dynamic adjustment mechanism ensures that the optimization model always adapts to the needs of the actual scenario.

[0110] In one embodiment of this application, the device is first determined based on the exponent matrix. i health parameters for:

[0111]

[0112] in, Indicates health factors, Indicates device i Operating cost coefficient, Indicates the first i A matrix of health indexes for the devices;

[0113] In one embodiment of this application, the device is determined based on energy characteristics. i Efficiency parameters for:

[0114]

[0115] in, Represents the efficiency factor. Indicates device i The efficiency degradation of each energy storage unit in the energy characteristics. Indicates device i The initial efficiency in the energy characteristics. i and N These represent the device identifier and the total number of devices, respectively. The above calculations couple the efficiency degradation of each energy storage unit with its initial efficiency using a multiplicative approach, capturing the impact of the "weakest link" effect on overall efficiency. When the efficiency degradation of any unit exceeds a threshold, this term decreases exponentially, forcibly prioritizing the operation of high-efficiency units.

[0116] In one embodiment of this application, the device is determined by exponential calculation. i attenuation parameters for:

[0117]

[0118] in, Indicates the reliability degradation factor. This indicates the aggregation strategy.

[0119] The above process determines parameters from three aspects: equipment health, energy utilization efficiency, and reliability degradation, comprehensively considering the key factors affecting the optimization of energy storage resource aggregation. Health parameters reflect the impact of equipment health status on resource aggregation, efficiency parameters reflect the equipment's performance in energy conversion and utilization, and degradation parameters consider the changes in equipment reliability over time or other factors.

[0120] Construct a resource function based on efficiency parameters, health parameters, and decay parameters. for:

[0121]

[0122] In this embodiment, the resource function integrates health parameters, efficiency parameters, and degradation parameters, enabling a comprehensive and dynamic evaluation of the state and performance of energy storage resources. Using this resource function as a constraint, an aggregation strategy is derived under extreme conditions of the resource function, serving as the control strategy. The control strategy output by this resource function can rationally allocate energy storage resources based on the actual situation and operational needs of the equipment, optimize the equipment's operating mode, improve the overall performance and reliability of the energy storage system, and achieve the goal of energy storage resource aggregation and optimization across multiple scenarios.

[0123] In one embodiment of this application, during the execution of the optimization model, it is continuously verified whether the strategy meets physical constraints. These constraints include total energy storage capacity limits, upper limits for charge and discharge rates, and scenario adaptability requirements. For example, it ensures that the energy storage strategy will not exceed the maximum charge and discharge rate of the device in any scenario to avoid mechanical stress damage; at the same time, through element-wise matching of scenario feature vectors and strategies, it ensures that the energy storage strategy in the home scenario will not simply replicate the industrial scenario pattern, but rather adapt to the specific power consumption characteristics of the scenario.

[0124] After model building and constraint verification are completed, self-optimization is achieved through a closed-loop feedback mechanism. When deviations occur between real-time running data and the prediction model, a dynamic correction process is triggered to adjust optimization parameters to adapt to changes in the actual scenario. This adaptive mechanism ensures that the optimized model maintains high efficiency in long-term operation, avoiding the performance degradation problem caused by scenario changes in traditional static models. The entire execution process, through a cascaded architecture of scenario recognition, optimization modeling, strategy verification, and closed-loop correction, achieves intelligent aggregation and efficient scheduling of energy storage resources in multiple scenarios.

[0125] S150 sends the control policy to the control terminal.

[0126] In one embodiment of this application, after the control strategy is generated, the strategy data is converted into an instruction format recognizable by the control terminal through a standardized interface. Modular data encapsulation technology is employed to categorize and package parameters such as charging / discharging power and runtime in the strategy according to scenario type, ensuring that home scenario strategies focus on power comfort, while industrial scenario strategies prioritize production continuity, thus avoiding execution deviations caused by mismatches between cross-scenario strategies.

[0127] The transmission process employs a dual-link redundant communication mechanism. The primary link pushes policy commands in real time via a 5G low-latency network, while the backup link utilizes power line carrier communication as a fallback. Dynamic checksums are embedded during transmission, automatically comparing the integrity of data packets between the sending and receiving ends every second. For example, when a data loss rate exceeding 3% is detected, a retransmission mechanism is triggered, and the transmission bandwidth is adjusted to ensure that control commands accurately reach the terminal.

[0128] After receiving policy instructions, the control terminal performs localized parsing through edge computing nodes. The terminal's built-in intelligent decision-making module first verifies whether the instructions comply with the device's physical constraints, such as whether the battery charging and discharging rate exceeds a safety threshold, and then performs fine-tuning and optimization based on real-time operating status. For example, in the event of a sudden power outage in an industrial setting, the terminal automatically increases the energy storage discharge power to maintain the operation of critical equipment, while simultaneously feeding back adjustment logs, forming a closed-loop chain of execution and feedback.

[0129] During strategy execution, the terminal response status is continuously monitored through an IoT platform. Utilizing non-intrusive load monitoring technology, real-time data on terminal execution performance can be collected without the need for additional sensors. When the actual execution deviation exceeds a preset threshold, a dynamic correction process is triggered, regenerating a control strategy adapted to the current scenario and redistributing it via an optimized communication link. This ensures that the control strategy remains dynamically aligned with scenario requirements and device status.

[0130] The above process sends the generated control strategy to the control terminal, enabling the terminal to control the wall-mounted energy storage device in real time according to the strategy. This ensures that the optimized strategy can be applied to the actual operation of the device in a timely manner, realizing the transformation from theoretical optimization to practical operation. It guarantees that the energy storage device operates according to the optimal strategy in different scenarios, improving the implementation effect of energy storage resource aggregation and optimization.

[0131] This technical solution acquires operating parameters of various wall-mounted energy storage devices by deploying smart sensors; extracts features from these operating parameters using a nonlinear feature extraction function to generate standardized energy characteristics; acquires historical fault data; constructs an equipment health assessment model based on the historical fault data and energy characteristics; outputs an index matrix representing the equipment's health level through the equipment health assessment model; constructs a resource function based on the energy characteristics and the index matrix; and outputs a control strategy through the resource function. The control strategy is then sent to the control terminal. This solution generates standardized energy characteristics based on nonlinear feature extraction, which better mines data characteristics. The health assessment model constructed combined with historical fault data can effectively assess the equipment's health level. Based on this, a resource function is constructed to output a control strategy and send it to the terminal. This allows for dynamic adjustment of the control strategy according to the actual operating conditions of the wall-mounted energy storage devices in different scenarios, improving the utilization efficiency of energy storage resources and ensuring the stable and reliable operation of the equipment.

[0132] Example 2

[0133] This embodiment provides a wall-mounted energy storage resource aggregation and optimization system based on the multi-scenario wall-mounted energy storage resource aggregation and optimization method of Embodiment 1, used to execute the multi-scenario wall-mounted energy storage resource aggregation and optimization method in the above embodiments of this application. It is understood that the multi-scenario wall-mounted energy storage resource aggregation and optimization system can be a computer program (including program code) running on a computer device; for example, the multi-scenario wall-mounted energy storage resource aggregation and optimization system is an application software; the multi-scenario wall-mounted energy storage resource aggregation and optimization system can be used to execute the corresponding steps in the method provided in the embodiments of this application. For details not disclosed in the embodiments of the multi-scenario wall-mounted energy storage resource aggregation and optimization system of this application, please refer to the embodiments of the multi-scenario wall-mounted energy storage resource aggregation and optimization method of this application described above.

[0134] Figure 3 A block diagram of a wall-mounted energy storage resource aggregation and optimization system for multiple scenarios, according to an embodiment of this application, is shown.

[0135] Reference Figure 3 As shown, a wall-mounted energy storage resource aggregation and optimization system for multiple scenarios according to an embodiment of this application includes:

[0136] The acquisition module 310 is used to acquire the operating parameters of various wall-mounted energy storage devices by deploying smart sensors;

[0137] Feature module 320 is used to extract features from the running parameters based on a nonlinear feature extraction function to generate standardized energy features;

[0138] The index module 330 is used to acquire historical fault data, construct an equipment health assessment model based on historical fault data and energy characteristics, and output an index matrix representing the health of the equipment through the equipment health assessment model.

[0139] Strategy module 340 is used to construct resource functions based on energy characteristics and exponential matrix, and output control strategies through resource functions;

[0140] The control module 350 is used to send the control strategy to the control terminal.

[0141] In this application, based on the aforementioned scheme, features are extracted from the operating parameters using a nonlinear feature extraction function to generate standardized energy features, including: performing frequency domain decomposition on the time series composed of the operating parameters to generate a first feature in the time dimension; mapping the operating parameters to a second feature using a nonlinear feature extraction function; and fusing the first and second features to generate standardized energy features.

[0142] In this application, based on the aforementioned scheme, historical fault data is obtained, and an equipment health assessment model is constructed based on the historical fault data and energy characteristics. The equipment health assessment model outputs an index matrix characterizing the equipment health, including: mapping energy characteristics to quantum state basis vectors; obtaining historical fault data and determining the probability amplitude of qubits based on the historical fault data; constructing an equipment health assessment model based on the quantum state basis vectors and qubit probability amplitudes, and outputting an index matrix characterizing the equipment health through the equipment health assessment model.

[0143] In this application, based on the aforementioned scheme, a resource function is constructed based on energy characteristics and an exponential matrix, and a control strategy is output through the resource function. This includes: determining health parameters based on the exponential matrix, determining efficiency parameters based on energy characteristics, and determining decay parameters through exponential operations; constructing a resource function based on the efficiency parameters, health parameters, and decay parameters, and outputting a control strategy through the resource function.

[0144] In this application, based on the aforementioned scheme, determining health parameters according to an index matrix includes: determining the device based on the index matrix. i health parameters for:

[0145]

[0146] in, Indicates health factors, Indicates device i Operating cost coefficient, Indicates the first i An index matrix of device health.

[0147] In this application, based on the aforementioned scheme, efficiency parameters are determined based on energy characteristics, including: determining the equipment based on energy characteristics. i Efficiency parameters for:

[0148]

[0149] in, Represents the efficiency factor. Indicates device i The efficiency degradation of each energy storage unit in the energy characteristics. Indicates device i The initial efficiency in the energy characteristics. i and N These represent the device identifier and the total number of devices, respectively.

[0150] In this application, based on the aforementioned scheme, the attenuation parameter is determined by exponential calculation, including: determining the device through exponential calculation. i attenuation parameters for:

[0151]

[0152] in, Indicates device i Reliability degradation factor Indicates device i The aggregation strategy.

[0153] This technical solution acquires operating parameters of various wall-mounted energy storage devices by deploying smart sensors; extracts features from these operating parameters using a nonlinear feature extraction function to generate standardized energy characteristics; acquires historical fault data; constructs an equipment health assessment model based on the historical fault data and energy characteristics; outputs an index matrix representing the equipment's health level through the equipment health assessment model; constructs a resource function based on the energy characteristics and the index matrix; and outputs a control strategy through the resource function. The control strategy is then sent to the control terminal. This solution generates standardized energy characteristics based on nonlinear feature extraction, which better mines data characteristics. The health assessment model constructed combined with historical fault data can effectively assess the equipment's health level. Based on this, a resource function is constructed to output a control strategy and send it to the terminal. This allows for dynamic adjustment of the control strategy according to the actual operating conditions of the wall-mounted energy storage devices in different scenarios, improving the utilization efficiency of energy storage resources and ensuring the stable and reliable operation of the equipment.

[0154] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0155] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not impose any limitations on the function and scope of use of the embodiments of this application.

[0156] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes based on a program stored in the read-only memory 402 or a program loaded from the storage section 408 into the random access memory 403, such as executing the multi-scenario wall-mounted energy storage resource aggregation and optimization method described in the above embodiment. The random access memory 403 also stores various programs and data required for system operation. The central processing unit 401, the read-only memory 402, and the random access memory 403 are interconnected via a bus 404. An input / output interface 405 is also connected to the bus 404.

[0157] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 410 as needed so that computer programs read from it can be installed into the storage section 408 as needed.

[0158] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit 401, it performs various functions defined in the system of this application.

[0159] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0160] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0161] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0162] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0163] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the multi-scenario wall-mounted energy storage resource aggregation and optimization method in the above embodiments.

[0164] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0165] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0166] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0167] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for resource aggregation and optimization of wall-mounted energy storage for multiple scenarios, characterized in that, Includes the following steps: By deploying smart sensors, the operating parameters of various wall-mounted energy storage devices to be optimized are obtained; The operating parameters are feature-extracted based on a nonlinear feature extraction function to generate standardized energy features; Historical fault data of the wall-mounted energy storage device to be optimized is obtained. Based on the historical fault data and the energy characteristics, an equipment health assessment model is constructed to identify the changing trend of the equipment health status and output an index matrix representing the health of the equipment. Based on the energy characteristics and the exponential matrix, a resource function is constructed, and based on the resource function, a control strategy for the wall-mounted energy storage device is output. Based on the energy characteristics and the exponential matrix, a resource function is constructed. Based on the resource function, a control strategy for the wall-mounted energy storage device is output, specifically including: The health parameters are determined based on the exponential matrix, the efficiency parameters are determined based on the energy characteristics, and the decay parameters are determined through the exponential decay function according to the aggregation strategy of the wall-mounted energy storage device. A resource function is constructed based on the efficiency parameter, the health parameter, and the decay parameter, and a control strategy is output through the resource function. The calculation expression for health parameters, determined based on the aforementioned index matrix, is as follows: In the formula, Indicates wall-mounted energy storage equipment i Health parameters, Indicates health factors, Indicates wall-mounted energy storage equipment i Operating cost coefficient, Indicates the first i A health index matrix for wall-mounted energy storage devices; The resource function integrates the health parameters, efficiency parameters, and decay parameters through a weighted fusion method, and adjusts the weights according to different scenario requirements through a dynamic weighting mechanism.

2. The wall-mounted energy storage resource aggregation and optimization method for multiple scenarios according to claim 1, characterized in that, Based on a nonlinear feature extraction function, features are extracted from the operating parameters to generate standardized energy features, specifically including: The time series of the operating parameters is decomposed in the frequency domain to generate the first feature in the time dimension, so as to capture the periodic and transient features of the equipment when responding to the power grid peak shaving. The running parameters are mapped to a second feature through a non-linear feature extraction function; The first feature and the second feature are fused to generate a standardized energy feature.

3. The wall-mounted energy storage resource aggregation and optimization method for multiple scenarios according to claim 1, characterized in that, The specific process for generating the index matrix characterizing the health of the equipment is as follows: The energy characteristics are mapped to quantum state basis vectors; The probability amplitude of the qubit is determined based on the historical fault data. A device health assessment model is constructed based on the quantum state basis vector and the quantum bit probability amplitude, and an exponential matrix characterizing the device health is output through the device health assessment model.

4. The wall-mounted energy storage resource aggregation and optimization method for multiple scenarios according to claim 1, characterized in that, The calculation expression for the efficiency parameter based on the energy characteristics is as follows: In the formula, Indicates wall-mounted energy storage equipment i Efficiency parameters, Represents the efficiency factor. Indicates wall-mounted energy storage equipment i The efficiency degradation of each energy storage unit in the energy characteristics. Indicates wall-mounted energy storage equipment i The initial efficiency in the energy characteristics. i and N These represent the device identifier and the total number of devices, respectively.

5. The wall-mounted energy storage resource aggregation and optimization method for multiple scenarios according to claim 1, characterized in that, Based on the aggregation strategy of wall-mounted energy storage devices, the calculation expression for the decay parameter, determined by the exponential decay function, is as follows: In the formula, Indicates wall-mounted energy storage equipment i The attenuation parameter, Indicates wall-mounted energy storage equipment i Reliability degradation factor Indicates wall-mounted energy storage equipment i The aggregation strategy.

6. The wall-mounted energy storage resource aggregation and optimization method for multiple scenarios according to claim 1, characterized in that, The method also includes sending the control strategy to the control terminal of the wall-mounted energy storage device.

7. A wall-mounted energy storage resource aggregation and optimization system based on the wall-mounted energy storage resource aggregation and optimization method for multiple scenarios as described in any one of claims 1-6, characterized in that, include: The acquisition module is used to acquire the operating parameters of various wall-mounted energy storage devices to be optimized by deploying smart sensors; The feature module is used to extract features from the operating parameters based on a nonlinear feature extraction function to generate standardized energy features; The index module is used to acquire historical fault data of the wall-mounted energy storage device to be optimized, construct an equipment health assessment model based on the historical fault data and the energy characteristics, identify the changing trend of the equipment health status, and output an index matrix representing the health of the equipment. The strategy module is used to construct a resource function based on the energy characteristics and the exponential matrix, and output the control strategy of the wall-mounted energy storage device based on the resource function; The control module is used to send the control strategy to the control terminal.

Images