Method and system for estimating available energy of prefabricated cabin type energy storage system

Abstract

The invention discloses an available energy estimation method and system for a prefabricated cabin type energy storage system, and belongs to the field of energy storage systems.The method comprises the steps that probability distribution of environmental parameters is constructed; historical operation data of equipment is collected, a probability relation between the environment temperature and equipment energy consumption is established, and an equipment energy consumption confidence interval is generated according to the probability relation; determining a confidence interval of the SOH by combining the battery aging experiment data and the real-time monitoring error; inputting the probability distribution of the environmental parameters, the equipment energy consumption confidence interval and the battery health state confidence interval into a probability model to generate a probability interval of available energy; and the optimal confidence level is selected in combination with the power grid dispatching requirement and the risk tolerance, and the available energy of the prefabricated cabin type energy storage system is obtained on the basis of the optimal confidence level according to the probability interval of the available energy. According to the method, confidence analysis is introduced, environmental parameters, equipment energy consumption and uncertainty of battery attenuation are quantified through a probability model, a probability interval of available energy is generated, and a basis is provided for scheduling decision making.

Description

Technical Field

[0001] The present invention proposes a method and system for estimating available energy of a prefabricated cabin type energy storage system. The present invention relates to the field of energy storage systems, and in particular to the field of available energy evaluation of prefabricated cabin type energy storage systems. Background Art

[0002] As an integrated, modular energy storage solution, prefabricated pod energy storage systems have been widely used in power system peak and frequency regulation, renewable energy integration, microgrids, and emergency power supplies. Evaluating available energy is a key step in measuring system performance, optimizing operating strategies, and ensuring power supply reliability. This evaluation comprehensively considers battery characteristics, environmental factors, and operating strategies, using static, dynamic, and online evaluation methods to accurately predict system performance.

[0003] In particular, available energy assessments for lithium-ion battery energy storage power stations are often based on deterministic models, considering only the rated capacity and a fixed attenuation coefficient, while ignoring the uncertainties of factors such as environmental parameter fluctuations, dynamic changes in equipment operating conditions, and measurement errors. For example, air conditioning energy consumption is significantly affected by errors in ambient temperature predictions, while real-time monitoring data for battery state of health (SOH)—calculated as the ratio of the battery's actual capacity to its rated capacity—also exhibits certain volatility. Existing technologies fail to incorporate probabilistic statistical methods into energy estimation, resulting in a lack of quantitative support for uncertainty in scheduling strategies, potentially leading to output deviations or the risk of equipment misuse.

[0004] This results in existing technologies failing to quantify the impact of environmental parameter prediction errors on energy consumption. For example, temperature prediction bias leads to inaccurate air conditioning energy consumption estimates. They also fail to consider the volatility of actual battery health conditions, leading to overly idealized estimates of available capacity. Existing deterministic models fail to reflect the uncertainty of available energy, making it difficult to support risk prediction and dynamic optimization of scheduling systems. In short, existing scheduling decisions suffer from inaccuracies and are unable to estimate the available energy of prefabricated pod-type energy storage systems. Summary of the Invention

[0005] To address the problems existing in the prior art, the present invention proposes a method and system for estimating the available energy of a prefabricated cabin energy storage system. This method introduces confidence analysis, quantifies the uncertainty of environmental parameters, equipment energy consumption, and battery degradation through a probabilistic model, and generates a probability interval for available energy, providing a basis for scheduling decisions.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: In a first aspect, the present invention provides a method for estimating available energy of a prefabricated cabin-type energy storage system, comprising: Construct the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results; Collect historical equipment operation data, establish a probabilistic relationship between ambient temperature and equipment energy consumption, and generate a confidence interval for equipment energy consumption based on the probabilistic relationship; Combining battery aging test data with real-time monitoring errors, the confidence interval of SOH is determined; The probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status are input into the probability model to generate the probability interval of available energy; The optimal confidence level is selected in combination with the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy.

[0007] As a further improvement of the present invention, the construction of the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results includes: The temperature sensor collects real-time temperature data of the energy storage system's environment and accesses the forecast data from the meteorological platform; Calculate the predicted value of temperature prediction error based on historical data, calculate the mean and standard deviation of the error, and obtain the error distribution; Combine the predicted values and the error distribution to generate a probability distribution of future temperatures.

[0008] As a further improvement of the present invention, the collecting of historical operation data of the equipment, establishing a probabilistic relationship between the ambient temperature and the energy consumption of the equipment, and generating a confidence interval of the energy consumption of the equipment according to the probabilistic relationship include: The historical operation data of the equipment is collected, and a temperature-energy consumption probability regression model is established through the probability mapping of the equipment energy consumption. The energy consumption ranges under different confidence levels are output according to the temperature-energy consumption probability regression model.

[0009] As a further improvement of the present invention, the method of combining battery aging experimental data with real-time monitoring error to determine the confidence interval of SOH includes: Based on the real-time monitoring data of the battery management system and combined with the aging test data, the confidence interval of SOH is calculated using a statistical inference model.

[0010] As a further improvement of the present invention, the probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status are input into the probability model to generate the probability interval of available energy, including: Input the temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval into the probability model; Randomly extract N temperature samples from the temperature probability distribution. For each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval and randomly select the SOH value from the battery health status confidence interval. The available energy is calculated based on the SOH value of each sample, the distribution of all available energy is statistically analyzed, the quantile results are output, and the probability intervals of available energy under different confidence levels are output.

[0011] As a further improvement of the present invention, the calculation of available energy based on the SOH value of each sample includes: The available energy is calculated for each sample using the following formula: E 可用,i = E 额定 ·SOH i -( E 空调,i + E 其他站用电 ) in, E 其他站用电 It is the energy consumption of auxiliary equipment, including integrated power supply system, lighting system, security system, fire alarm system, environmental system, HVAC system and automation system.

[0012] As a further improvement of the present invention, the selecting the optimal confidence level includes: For the first scenario: select the lower limit of the 90% confidence interval E 5% ; For the second scenario: select the 95% confidence interval median E 50% .

[0013] As a further improvement of the present invention, obtaining the available energy of the prefabricated cabin-type energy storage system further includes dynamically adjusting the energy using a real-time update mechanism. The dynamic adjustment using the real-time update mechanism specifically includes: Dynamically update the input optimal confidence level at set intervals; If the optimal confidence level deviates from the historical value by more than a threshold, an alarm is triggered and the scheduling strategy is adjusted.

[0014] In a second aspect, the present invention provides a system for estimating available energy of a prefabricated cabin-type energy storage system, comprising: Environmental parameter probability distribution construction module, used to construct the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results; The equipment energy consumption probability relationship construction module is used to collect historical equipment operation data, establish a probabilistic relationship between ambient temperature and equipment energy consumption, and generate equipment energy consumption confidence intervals based on the probabilistic relationship; The SOH confidence interval determination module is used to combine battery aging test data with real-time monitoring errors to determine the SOH confidence interval; The available energy probability interval generation module is used to input the probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status into the probability model to generate the probability interval of available energy; The optimal confidence level selection module is used to select the optimal confidence level based on the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy.

[0015] Optionally, the environmental parameter probability distribution construction module is specifically used to: The temperature sensor collects real-time temperature data of the energy storage system's environment and accesses the forecast data from the meteorological platform; Calculate the predicted value of temperature prediction error based on historical data, calculate the mean and standard deviation of the error, and obtain the error distribution; Combine the predicted values and the error distribution to generate a probability distribution of future temperatures.

[0016] Optionally, the device energy consumption probability relationship building module is specifically used to: The historical operation data of the equipment is collected, and a temperature-energy consumption probability regression model is established through the probability mapping of the equipment energy consumption. The energy consumption ranges under different confidence levels are output according to the temperature-energy consumption probability regression model.

[0017] Optionally, the SOH confidence interval determination module is specifically configured to: Based on the real-time monitoring data of the battery management system and combined with the aging test data, the confidence interval of SOH is calculated using a statistical inference model.

[0018] Optionally, the available energy probability interval generation module is specifically configured to: Input the temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval into the probability model; Randomly extract N temperature samples from the temperature probability distribution. For each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval and randomly select the SOH value from the battery health status confidence interval. The available energy is calculated based on the SOH value of each sample, the distribution of all available energy is statistically analyzed, the quantile results are output, and the probability intervals of available energy under different confidence levels are output.

[0019] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for estimating available energy of the prefabricated cabin energy storage system when executing the computer program.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for estimating available energy of the prefabricated cabin energy storage system.

[0021] In a fifth aspect, the present invention provides a computer program product, which includes computer instructions, and the computer instructions instruct a computer to execute the method for estimating available energy of the prefabricated cabin energy storage system.

[0022] The beneficial effects of the present invention compared to the prior art are: The present invention provides a probabilistic method for evaluating the available energy of an energy storage system, which takes into account the different energy consumption of auxiliary equipment such as air conditioners under environmental influences and the SOH of the energy storage system. It can select the optimal confidence level in combination with the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy. Specifically, the temperature probability distribution, the equipment energy consumption confidence interval, and the battery health status confidence interval are input into the Monte Carlo simulation to generate the probability distribution of available energy; the available energy intervals under different confidence levels can be output; the optimal confidence level is selected in combination with the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy. By constructing a probability mapping model, the present invention integrates confidence and confidence interval analysis into the available energy estimation of the energy storage system for the first time, quantifies the uncertainty of environmental parameters and equipment operating conditions; realizes dynamic risk prediction, and supports the dispatching system to select different confidence levels according to risk preferences through probability interval output, avoiding output anomalies caused by estimation bias; realizes data-driven optimization, and uses a probability model to improve the model's adaptability to complex nonlinear relationships. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present invention or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 A flow chart of a method for estimating available energy of a prefabricated cabin energy storage system provided by the present invention; Figure 2 Schematic diagram of a method for estimating available energy of a prefabricated cabin-type energy storage system provided by an embodiment of the present invention; Figure 3 The present invention provides a device for estimating available energy of a prefabricated cabin-type energy storage system; Figure 4 This is a schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0026] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0027] Explanation of terms: Monte Carlo simulation is a computational simulation technique based on random sampling and statistical methods. Its core concept is to approximate the solution to a problem using a probabilistic statistical approach through a large number of random sampling and repeated experiments. Monte Carlo simulation can effectively handle uncertainties in the system, such as generator failures, transmission line failures, load fluctuations, and the intermittent nature of renewable energy generation. Through random sampling, Monte Carlo simulation can simulate the impact of these uncertainties on available energy. Through a large number of random simulation experiments, Monte Carlo simulation can obtain multiple possible values of available energy and calculate the frequency of these values, thereby generating a probability distribution of available energy. Based on this generated probability distribution, Monte Carlo simulation can further calculate the confidence interval of the available energy—estimate the range of values of the available energy at a certain confidence level.

[0028] A Bayesian network is a probabilistic graphical model that uses Bayes' theorem to describe and reason about conditional dependencies between variables. Bayesian networks effectively model the dependencies between available energy and other related variables, such as meteorological conditions, load demand, and power generation equipment status. By constructing a Bayesian network structure, the mutual influence of these variables can be clearly demonstrated. Based on Bayes' theorem, Bayesian networks can perform probabilistic reasoning—inferring the probability distribution of unknown variables based on the values of known variables. In the case of available energy forecasting, Bayesian networks can infer the probability distribution of future available energy based on historical and real-time data. Bayesian networks have the ability to integrate multi-source information, combining information from different data sources (such as meteorological data, load data, and power generation equipment status data) into a unified model, thereby improving forecast accuracy and reliability.

[0029] The bootstrap method, also known as the self-help method, is a non-parametric technique in statistics based on resampling, proposed by Bradley Efron in 1979. Its core idea is to generate multiple new samples (bootstrap samples) by repeatedly sampling with replacement from the original sample, thereby estimating the distribution characteristics of the statistic.

[0030] like Figure 1 As shown, the first object of the present invention is to provide a method for estimating available energy of a prefabricated cabin energy storage system, comprising: S1, construct the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results; Furthermore, the probability distribution of environmental parameters (such as temperature and humidity) is constructed through historical meteorological data and forecast error analysis results to capture the uncertainty of meteorological forecasts.

[0031] Furthermore, probabilistic graphical models (such as Bayesian networks) are used to analyze historical meteorological data and forecast errors, and statistical inference (such as kernel density estimation and parameter estimation) is used to construct the probability distribution of environmental parameters. This captures the uncertainty of meteorological forecasts and improves the reliability of environmental parameter estimates.

[0032] S2, collects historical equipment operation data, establishes a probabilistic relationship between ambient temperature and equipment energy consumption, and generates a confidence interval for equipment energy consumption based on the probabilistic relationship; Furthermore, based on historical operating data, a probabilistic relationship between ambient temperature and equipment energy consumption is established, and an energy consumption confidence interval is generated to reflect the impact of temperature fluctuations on energy consumption.

[0033] Furthermore, historical equipment operating data is collected and a relationship between ambient temperature and equipment energy consumption is established through regression analysis (such as probabilistic linear regression). Combined with probabilistic propagation methods, confidence intervals for energy consumption are generated. This quantifies the impact of temperature fluctuations on energy consumption and provides a basis for estimating available energy.

[0034] S3, combining battery aging experimental data with real-time monitoring errors to determine the confidence interval of SOH; Furthermore, battery state of health (SOH): combining aging experiments with real-time monitoring errors, the confidence interval of SOH is determined to quantify the uncertainty of the battery aging process.

[0035] Furthermore, by combining battery aging experimental data (such as cycle number-capacity decay curves) with real-time monitoring errors (such as voltage and internal resistance measurement errors), statistical methods (such as bootstrap and Bayesian estimation) are used to determine the confidence interval of the SOH. This quantifies the uncertainty of the battery aging process and improves the accuracy and reliability of the SOH estimate.

[0036] S4, inputting the probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status into the probability model to generate a probability interval of available energy; Furthermore, by integrating multiple sources of data, such as historical meteorological data, equipment operation data, and battery aging data, the redundancy of information can be exploited to improve estimation accuracy. For example, the distribution of environmental parameters is complementary to the equipment energy consumption model, and experimental and monitoring data are used to synergistically calibrate the SOH estimation.

[0037] Furthermore, environmental parameter distributions, device energy consumption ranges, and SOH ranges are fed into a probabilistic model (such as Monte Carlo simulation or Bayesian networks) to calculate the probability range of available energy through probability propagation. This comprehensively considers multiple sources of uncertainty and provides a more comprehensive estimate of available energy.

[0038] S5, combining the grid dispatching requirements and risk tolerance to select the optimal confidence level, based on the optimal confidence level, according to the probability interval of available energy, obtain the available energy of the prefabricated cabin energy storage system.

[0039] Furthermore, probabilistic intervals of available energy, rather than single fixed values, are generated to provide a basis for risk-benefit trade-offs in grid dispatch. Based on these probabilistic intervals, combined with grid dispatch requirements and risk tolerance, an optimal confidence level is selected through optimization algorithms (such as utility theory and value-at-risk models). This balances grid dispatch requirements and risks, improving the economic efficiency and safety of energy storage systems.

[0040] This method selects the optimal confidence level based on the available energy probability interval, combined with grid dispatch requirements (such as peak and frequency regulation, and spare capacity) and risk tolerance. For example, a high confidence level is selected in risk-sensitive scenarios to ensure system reliability, while a low confidence level is selected in scenarios where economic efficiency is a priority to improve energy storage utilization.

[0041] The following will be combined with the Figure 2 The specific embodiments further describe in detail the method for estimating available energy of the prefabricated cabin energy storage system of the present invention.

[0042] like Figure 2 As shown, the whole process of environmental parameter probability modeling, equipment energy consumption confidence interval calculation, Monte Carlo simulation and scheduling optimization is demonstrated. The present invention uses the following technologies to evaluate available energy: Step 1: Data Collection and Probabilistic Modeling: Based on historical meteorological data and forecast error analysis results, construct a probability distribution of ambient temperature (such as a normal distribution or Bayesian posterior distribution). This includes the following steps: (1) Obtain real-time and historical ambient temperature data through sensors and meteorological platforms, and analyze the probability distribution of temperature prediction errors.

[0043] 1) Data source: Temperature sensors collect real-time temperature data from the energy storage system’s environment, while also accessing forecast data from the meteorological platform (such as the predicted temperature for the next 24 hours).

[0044] 2) Error analysis: Calculate temperature prediction error based on historical data ( ΔT=T 预测 －T 实际 ), the mean and standard deviation of the statistical error, assuming that the error follows a normal distribution Δ T ~N( μ , σ 2).

[0045] 3) Probability distribution generation: combining predicted values T 预测 and error distribution to generate the probability distribution of future temperature T Future~N( T Prediction+ μ , σ 2).

[0046] (2) Collect historical operating data of equipment (such as air conditioners), establish a probabilistic regression model of temperature-energy consumption (such as quantile regression), and output confidence intervals of equipment energy consumption at different confidence levels.

[0047] Specifically, a probabilistic mapping of equipment energy consumption is established: through regression analysis or machine learning models, a probabilistic relationship between ambient temperature and air conditioning energy consumption is established, and a confidence interval for energy consumption is generated. An example is shown below: 1) Quantile regression model: Quantile regression is used to establish a nonlinear relationship model between temperature and air conditioning energy consumption. The model expression is:

[0048] Among them, τ is the target quantile (such as 10%, 90%), Q τ is the predicted value of air conditioning energy consumption at the corresponding quantile.

[0049] 2) Confidence interval output: The quantile regression model is used to output energy consumption intervals at different confidence levels. For example, a 90% confidence interval corresponds to the predicted values of τ = 5% and τ = 95%: Step 2: Calculate the confidence interval of the battery health status: Among them, the confidence analysis of battery health status: combining battery aging experimental data with real-time monitoring errors to determine the confidence interval of SOH; (1) Based on the real-time monitoring data of the battery management system (BMS) and combined with the aging test data, a statistical inference model (such as the Bootstrap method or Bayesian estimation) is used to calculate the 95% confidence interval of the SOH. Taking the Bootstrap method as an example: 1) Data resampling: Randomly extract samples (repeatable sampling) from the battery historical monitoring data to generate multiple SOH data sets.

[0050] 2) Confidence interval calculation: Calculate the mean of the SOH for each resampled data set, repeat 1000 times to generate the sample distribution of the SOH, and take the 2.5% and 97.5% quantiles as the 95% confidence interval; Step 3: Calculate the probability of available energy: Input the above probabilities into a probability model (Monte Carlo simulation or Bayesian network) to generate the probability distribution and confidence interval of available energy.

[0051] (1) Input the temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval into a probability model (such as Monte Carlo simulation) to generate a probability distribution of available energy; 1) Input parameters: Temperature probability distribution T 未来 ~N(μ T ,σ 2 T ) (from step 1); Equipment energy consumption confidence interval E 空调 ∈[ E 空调,min , E 空调,max ] (from step 1); Battery health status confidence interval SOH∈[SOH min ,SOH max ] (from step 2).

[0052] 2) Random sampling: Randomly draw N temperature samples from the temperature probability distribution (e.g. N=10 4 ), for each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval, and randomly select the SOH value from the battery health status confidence interval.

[0053] (2) Output the available energy range under different confidence levels (such as 90%, 95%): 1) Available energy calculation: Calculate the available energy for each sample using the following formula: E 可用,i = E 额定 ·SOH i -( E空调,i + E 其他站用电 ) Among them, E other station electricity consumption refers to the energy consumption of other auxiliary equipment such as integrated power supply system, lighting system, security system, fire alarm system, environmental system, HVAC system, automation system, etc., which is relatively fixed and determined based on statistical analysis of electricity consumption within the station.

[0054] 2) Probability distribution generation: Statistics of all E 可用,i The distribution of , output quantile results. For example, the 90% confidence interval is: E 可用 ∈[E 5% ,E 95% ] Step 4: Dynamic scheduling optimization: (1) The optimal confidence level is selected based on the grid dispatching requirements and risk tolerance. Based on the optimal confidence level and the probability interval of available energy, the available energy of the prefabricated cabin energy storage system is obtained: 1) For the first scenario: high-risk scenarios (such as emergency frequency modulation): select the lower limit of the 90% confidence interval E5% to ensure the minimum available energy; 2) For the second scenario: conservative scenario (such as planned charging and discharging): select the median of the 95% confidence interval E50% to balance risks and benefits.

[0055] (2) Real-time update mechanism: 1) Dynamically update the new optimal confidence level of the input at set intervals. For example, for dynamic data input, update the ambient temperature forecast and SOH monitoring data every hour and re-execute the Monte Carlo simulation; 2) Adaptive adjustment: If the new optimal confidence level deviates from the historical value by more than a threshold (e.g., ±3%), an alarm is triggered and the scheduling strategy is adjusted to update the available energy of the prefabricated cabin energy storage system.

[0056] Example The method of the present invention was applied to estimate winter available energy in a coastal energy storage power station. Historical data analysis showed that the ambient temperature prediction error follows a normal distribution with a mean of 0°C and a standard deviation of 2°C. Quantile regression was used to establish a temperature-air conditioning energy consumption model, generating an energy consumption range with a 90% confidence interval. The battery health status was calculated using the Bootstrap method with a 95% confidence interval of [92%, 96%]. The Monte Carlo simulation output of the available energy with a 90% confidence interval of [850kWh, 920kWh] was used. The dispatch system selected the lower limit of the interval as a conservative strategy, successfully avoiding an output shortage caused by low temperatures and effectively improving system reliability.

[0057] Therefore, the energy storage power station credible energy assessment method based on the confidence probability analysis method provided by the present invention has the following advantages: 1) High-precision probability estimation: Quantifying the uncertainty of available energy through confidence intervals effectively improves the credibility of the estimation results; 2) Risk-controlled scheduling decisions: The scheduling system can select output strategies based on confidence intervals to reduce the risk of over-discharge or under-capacity. 3) Strong adaptability: The model can dynamically update probability distribution parameters to adapt to environmental changes in different seasons and regions; 4) Extend equipment life: Prevent battery overload at extreme SOH values through confidence interval warning.

[0058] In summary, this method integrates multi-source data through a probabilistic framework, quantifies uncertainty at each stage, and generates probability intervals for available energy, providing flexible decision support for grid dispatch. Multi-source information fusion improves estimation accuracy, and probability intervals quantify uncertainty. Confidence levels are selected based on risk tolerance to adapt to different dispatch scenarios. By combining real-time monitoring with experimental data, model parameters are dynamically updated to adapt to long-term system operation.

[0059] like Figure 3 As shown, the second object of the present invention is to provide a system for estimating available energy for a prefabricated pod-type energy storage system, comprising: an environmental parameter probability distribution construction module 100, an equipment energy consumption probability relationship construction module 200, a SOH confidence interval determination module 300, an available energy probability interval generation module 400, and an optimal confidence level selection module 500. The system for estimating available energy for a prefabricated pod-type energy storage system of the present invention is based on a method for estimating available energy for a prefabricated pod-type energy storage system.

[0060] The environmental parameter probability distribution construction module 100 is used to construct the probability distribution of environmental parameters based on historical meteorological data and prediction error analysis results; specifically, it is used to: The temperature sensor collects real-time temperature data of the energy storage system's environment and accesses the forecast data from the meteorological platform; Calculate the predicted value of temperature prediction error based on historical data, calculate the mean and standard deviation of the error, and obtain the error distribution; Combine the predicted values and the error distribution to generate a probability distribution of future temperatures.

[0061] The device energy consumption probability relationship building module 200 is used to collect historical device operation data, establish a probability relationship between ambient temperature and device energy consumption, and generate a device energy consumption confidence interval based on the probability relationship; specifically, it is used to: The historical operation data of the equipment is collected, and a temperature-energy consumption probability regression model is established through the probability mapping of the equipment energy consumption. The energy consumption ranges under different confidence levels are output according to the temperature-energy consumption probability regression model.

[0062] The SOH confidence interval determination module 300 is used to determine the SOH confidence interval by combining battery aging test data with real-time monitoring errors. Specifically, it is used to: Based on the real-time monitoring data of the battery management system and combined with the aging test data, the confidence interval of SOH is calculated using a statistical inference model.

[0063] The available energy probability interval generation module 400 is used to input the probability distribution of environmental parameters, the device energy consumption confidence interval, and the battery health status confidence interval into the probability model to generate the available energy probability interval; specifically, it is used to: Temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval input probability model; Randomly extract N temperature samples from the temperature probability distribution. For each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval and randomly select the SOH value from the battery health status confidence interval. Calculate the available energy based on the SOH value of each sample, count the distribution of all available energy, output the quantile results, and output the probability interval of available energy at different confidence levels. The method of calculating the available energy according to the SOH value of each sample includes: The available energy is calculated for each sample using the following formula: E 可用,i = E 额定 ·SOH i -( E 空调,i + E 其他站用电 ) in, E 其他站用电 It is the energy consumption of auxiliary equipment, including integrated power supply system, lighting system, security system, fire alarm system, environmental system, HVAC system and automation system.

[0064] The optimal confidence level selection module 500 is used to select the optimal confidence level based on the grid dispatch requirements and risk tolerance. Based on the optimal confidence level and the probability interval of the available energy, the module obtains the available energy of the prefabricated cabin energy storage system. Specifically, the module is used to: For the first scenario: select the lower limit of the 90% confidence interval E 5% ; For the second scenario: select the 95% confidence interval median E 50% ; As a preferred solution, when selecting the optimal confidence level, a real-time update mechanism is also adopted, specifically including: Dynamically update the input optimal confidence level at set intervals; If the optimal confidence level deviates from the historical value by more than a threshold, an alarm is triggered and the scheduling strategy is adjusted.

[0065] like Figure 4 As shown, a third object of an embodiment of the present invention is to provide an electronic device, comprising a memory 701, a processor 702, and a computer program stored in the memory 701 and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for estimating available energy of a prefabricated cabin-type energy storage system. The electronic device also includes a communication interface 703 and a bus 704.

[0066] A fourth object of an embodiment of the present invention is to provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned method for estimating available energy of a prefabricated cabin energy storage system.

[0067] A fifth object of an embodiment of the present invention is to provide a computer program product, wherein the computer program product includes computer instructions, and the computer instructions instruct a computer to execute the above-mentioned method for estimating available energy of a prefabricated cabin energy storage system.

[0068] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0070] The present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to magnetic disk storage, readable storage media, optical storage, etc.) containing computer-usable program code.

[0071] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for estimating available energy of a prefabricated cabin energy storage system, characterized in that: include: Construct the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results; Collect historical equipment operation data, establish a probabilistic relationship between ambient temperature and equipment energy consumption, and generate a confidence interval for equipment energy consumption based on the probabilistic relationship; Combine battery aging experimental data with real-time monitoring errors to determine the confidence interval of the battery health status; The probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status are input into the probability model to generate the probability interval of available energy; The optimal confidence level is selected in combination with the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy.

2. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The method of constructing the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results includes: The temperature sensor collects real-time temperature data of the energy storage system's environment and accesses the forecast data from the meteorological platform; Calculate the predicted value of temperature prediction error based on historical data, calculate the mean and standard deviation of the error, and obtain the error distribution; Combine the predicted values and the error distribution to generate a probability distribution of future temperatures.

3. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The collecting of historical operation data of the equipment, establishing a probabilistic relationship between ambient temperature and equipment energy consumption, and generating a confidence interval for equipment energy consumption based on the probabilistic relationship include: The historical operation data of the equipment is collected, and a temperature-energy consumption probability regression model is established through the probability mapping of the equipment energy consumption. The energy consumption ranges under different confidence levels are output according to the temperature-energy consumption probability regression model.

4. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The combination of battery aging experimental data and real-time monitoring error to determine the confidence interval of SOH includes: Based on the real-time monitoring data of the battery management system and combined with the aging test data, the confidence interval of SOH is calculated using a statistical inference model.

5. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status are input into the probability model to generate the probability interval of available energy, including: Input the temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval into the probability model; Randomly extract N temperature samples from the temperature probability distribution. For each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval and randomly select the SOH value from the battery health status confidence interval. The available energy is calculated based on the SOH value of each sample, the distribution of all available energy is statistically analyzed, the quantile results are output, and the probability intervals of available energy under different confidence levels are output.

6. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The method of calculating the available energy according to the SOH value of each sample includes: The available energy is calculated for each sample using the following formula: E 可用,i = E 额定 ·SOH i -( E 空调,i + E 其他站用电 ) in, E 其他站用电 It is the energy consumption of auxiliary equipment, including integrated power supply system, lighting system, security system, fire alarm system, environmental system, HVAC system and automation system.

7. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: The selecting of the optimal confidence level comprises: For the first scenario: select the lower limit of the 90% confidence interval E 5% ; For the second scenario: select the 95% confidence interval median E 50% .

8. The method for estimating available energy of a prefabricated cabin energy storage system according to claim 1, characterized in that: When obtaining the available energy of the prefabricated cabin-type energy storage system, the method further includes using a real-time update mechanism for dynamic adjustment. The real-time update mechanism for dynamic adjustment specifically includes: Dynamically update the input optimal confidence level at set intervals; If the optimal confidence level deviates from the historical value by more than a threshold, an alarm is triggered and the scheduling strategy is adjusted.

9. A system for estimating available energy of a prefabricated cabin energy storage system, characterized in that: include: Environmental parameter probability distribution construction module, used to construct the probability distribution of environmental parameters based on historical meteorological data and forecast error analysis results; The equipment energy consumption probability relationship construction module is used to collect historical equipment operation data, establish a probabilistic relationship between ambient temperature and equipment energy consumption, and generate equipment energy consumption confidence intervals based on the probabilistic relationship; The SOH confidence interval determination module is used to combine battery aging test data with real-time monitoring errors to determine the SOH confidence interval; The available energy probability interval generation module is used to input the probability distribution of environmental parameters, the confidence interval of device energy consumption, and the confidence interval of battery health status into the probability model to generate the probability interval of available energy; The optimal confidence level selection module is used to select the optimal confidence level based on the grid dispatching requirements and risk tolerance. On the basis of the optimal confidence level, the available energy of the prefabricated cabin energy storage system is obtained according to the probability interval of the available energy.

10. The available energy estimation system of the prefabricated cabin type energy storage system according to claim 9, characterized in that: The environmental parameter probability distribution building module is specifically used to: The temperature sensor collects real-time temperature data of the energy storage system's environment and accesses the forecast data from the meteorological platform; Calculate the predicted value of temperature prediction error based on historical data, calculate the mean and standard deviation of the error, and obtain the error distribution; Combine the predicted values and the error distribution to generate a probability distribution of future temperatures.

11. The available energy estimation system of the prefabricated cabin type energy storage system according to claim 9, characterized in that: The device energy consumption probability relationship building module is specifically used to: The historical operation data of the equipment is collected, and a temperature-energy consumption probability regression model is established through the probability mapping of the equipment energy consumption. The energy consumption ranges under different confidence levels are output according to the temperature-energy consumption probability regression model.

12. The available energy estimation system of the prefabricated cabin type energy storage system according to claim 9, characterized in that: The SOH confidence interval determination module is specifically used to: Based on the real-time monitoring data of the battery management system and combined with the aging test data, a statistical inference model is used to calculate the confidence interval of SOH.

13. The available energy estimation system of the prefabricated cabin type energy storage system according to claim 9, characterized in that: The available energy probability interval generation module is specifically used to: Input the temperature probability distribution, device energy consumption confidence interval, and battery health status confidence interval into the probability model; Randomly extract N temperature samples from the temperature probability distribution. For each temperature sample, randomly select the energy consumption value from the device energy consumption confidence interval and randomly select the SOH value from the battery health status confidence interval. The available energy is calculated based on the SOH value of each sample, the distribution of all available energy is statistically analyzed, the quantile results are output, and the probability intervals of available energy under different confidence levels are output.

14. The available energy estimation system of the prefabricated cabin type energy storage system according to claim 10, characterized in that: Also includes: Real-time update module, used to dynamically update the input optimal confidence level at set intervals; If the latest SOH confidence interval deviates from the historical value by more than a threshold, an alarm is triggered and the scheduling strategy is adjusted.

15. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for estimating available energy of the prefabricated cabin-type energy storage system according to any one of claims 1 to 8 is implemented.

16. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for estimating available energy of a prefabricated cabin-type energy storage system according to any one of claims 1 to 8 is implemented.

17. A computer program product comprising computer instructions, characterized in that: The computer instructions instruct the computer to execute the method for estimating available energy of the prefabricated cabin-type energy storage system according to any one of claims 1 to 8.

Images