A distributed energy optimization management method and system for rapidly deploying a mobile shelter hospital

Abstract

This invention provides a distributed energy optimization management method and system for rapidly deploying mobile makeshift hospitals. In this embodiment, the invention dynamically adjusts energy allocation by constructing a multi-layered virtual energy network model for the mobile makeshift hospital; it uses time series forecasting technology to predict energy consumption demand and power generation potential, generating an energy supply and demand balance plan; it introduces a multi-objective optimization algorithm to intelligently schedule the charging and discharging process of the energy storage system, obtaining the optimal charging and discharging plan; it collects and analyzes the operating data of the distributed energy system at preset time nodes, uses a machine learning model to predict fault risks from the operating data, and optimizes the optimal energy allocation strategy and multi-objective optimization algorithm based on the results, forming an adaptive and self-learning energy closed-loop management system. The technical solution provided by this invention enables dynamic optimization management of energy in mobile makeshift hospitals, ensuring efficient, flexible, and adaptive energy allocation and scheduling, and improving the overall performance and reliability of the system.

Description

Technical Field

[0001] This invention relates to the field of energy management technology for mobile makeshift hospitals, and in particular to a distributed energy optimization management method for rapidly deploying mobile makeshift hospitals. Background Technology

[0002] With the frequent occurrence of public health emergencies, the rapid deployment of mobile makeshift hospitals has become a crucial means of responding to large-scale epidemics. Mobile makeshift hospitals need to be constructed and put into use within a short period, placing extremely high demands on energy supply. Especially in remote areas or where resources are limited, ensuring both efficient and reliable energy supply for mobile makeshift hospitals has become a pressing issue. Furthermore, mobile makeshift hospitals are typically equipped with a large amount of medical equipment, whose power demands are highly uncertain and volatile. Therefore, a flexible and intelligent energy management system is needed to cope with this complex power environment.

[0003] While existing energy management solutions meet the basic power needs of mobile makeshift hospitals to some extent, they still suffer from insufficient flexibility, low levels of intelligence, and high maintenance costs. Traditional centralized energy supply methods cannot dynamically adjust energy allocation strategies based on the real-time power demands of medical equipment and the generation capacity of renewable energy sources, leading to frequent energy waste or supply shortages. Existing energy management systems lack intelligent dispatch capabilities and cannot fully utilize the advantages of renewable energy and energy storage systems, especially when facing complex and variable power environments, exhibiting poor adaptability and robustness. Furthermore, due to the lack of effective fault prediction and self-healing functions, existing energy management systems are prone to failure during operation, requiring frequent manual intervention and maintenance, increasing operation and maintenance costs and workload. Summary of the Invention

[0004] This invention provides a distributed energy optimization management method and system for rapidly deploying mobile makeshift hospitals, which solves the problem that the traditional centralized energy supply method in the prior art cannot dynamically adjust the energy allocation strategy according to the real-time power demand of medical equipment and the power generation of renewable energy, resulting in frequent energy waste or supply shortages.

[0005] In a first aspect, embodiments of the present invention provide a distributed energy optimization management method for rapidly deploying mobile makeshift hospitals, comprising:

[0006] Construct a multi-layered virtual energy network model for mobile makeshift hospitals;

[0007] Based on the multi-layer virtual energy network model, a deep reinforcement learning algorithm is applied to dynamically adjust energy allocation and generate the optimal energy allocation strategy.

[0008] By combining the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns, time series forecasting technology is used to predict energy consumption demand and power generation potential, and to generate an energy supply and demand balance plan.

[0009] Based on the energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system to obtain the optimal charging and discharging plan.

[0010] Based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is adopted. The operation data of the distributed energy system is collected and analyzed at preset time nodes. The failure risk is predicted by the operation data through a machine learning model, and an evaluation result is generated. Based on the evaluation result, the optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized to form an adaptive and self-learning energy closed-loop management system.

[0011] Optionally, based on the energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system to obtain the optimal charging and discharging plan, including:

[0012] By utilizing the current state information of the energy storage system and combining it with the energy supply and demand balance plan, a dynamic mathematical model of the energy storage system is constructed.

[0013] Using the aforementioned dynamic mathematical model, and combining the priority of electricity demand of medical equipment, the real-time power generation of renewable energy, and the fluctuation of electricity prices on the external power grid, a multi-objective optimization function is designed.

[0014] By applying evolutionary computation methods and combining them with a fuzzy logic controller, the multi-objective optimization function is solved to obtain a Pareto front composed of a set of non-dominated solutions.

[0015] By utilizing a multi-criteria decision support system that integrates expert knowledge and user preferences, the optimal charge-discharge plan is selected from the Pareto front.

[0016] Optionally, using the aforementioned dynamic mathematical model, and combining the priority of electricity demand from medical equipment, the real-time power generation of renewable energy sources, and fluctuations in external grid electricity prices, a multi-objective optimization function is designed, including:

[0017] Using the aforementioned dynamic mathematical model, and combining the priority of electricity demand from medical equipment, the real-time power generation of renewable energy, and the fluctuations in electricity prices from the external power grid, the objective variables of the multi-objective optimization function are defined.

[0018] Design a specific expression for a multi-objective optimization function based on the target variables, wherein the expression includes each target variable and the relative importance weight of each target variable;

[0019] By combining the specific expression with historical and real-time data, the parameters in the multi-objective optimization function are calibrated to obtain the calibrated multi-objective optimization function.

[0020] By using the calibrated multi-objective optimization function and considering changes in the external environment and internal requirements, the weight coefficients in the multi-objective optimization function are dynamically adjusted to generate a multi-objective optimization function that adapts to different operating conditions.

[0021] Optionally, the feature is that, using the calibrated multi-objective optimization function, and combining changes in the external environment and internal requirements, the weight coefficients in the multi-objective optimization function are dynamically adjusted to generate a multi-objective optimization function adapted to different operating conditions, including:

[0022] By using the calibrated multi-objective optimization function and combining changes in the external environment and internal needs, the trend of importance change of each objective variable is analyzed, and the results of the importance change trend analysis are obtained.

[0023] A weight adjustment rule is designed based on the results of the importance trend analysis, and the weight adjustment rule includes the differences in the importance of each target variable in different time periods;

[0024] The weight coefficients in the multi-objective optimization function are dynamically adjusted using the weight adjustment rule to obtain dynamic weight coefficients;

[0025] The dynamic weighting coefficients are applied to the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions.

[0026] Optionally, the feature is that, based on the multi-layer virtual energy network model, a deep reinforcement learning algorithm is applied to dynamically adjust energy allocation and generate an optimal energy allocation strategy, including:

[0027] Using the aforementioned multi-layer virtual energy network model, the energy consumption prediction information of mobile makeshift hospitals, the real-time power generation of renewable energy, the electricity price fluctuations of the external power grid, and the urgency level of mobile makeshift hospitals are integrated. At the same time, the uncertainty of weather changes is calculated, and the possible impact of weather changes is simulated through a probability distribution model to obtain the input state.

[0028] Based on the input state, the priority of power demand of mobile modular hospitals, the availability of renewable energy, the price signal of external power grid and the uncertainty of weather changes are set as multidimensional reward functions, with stable power supply and cost saving of emergency medical units as the main optimization objectives, thus obtaining the multidimensional reward function.

[0029] The input state and the multidimensional reward function are processed using a deep reinforcement learning model based on the Actor-Critic architecture to obtain an initial energy allocation strategy;

[0030] Based on the initial energy allocation strategy, during the training process, an experience replay mechanism is used to randomly extract historical data for replay learning, thereby improving the generalization ability and stability of the model and obtaining an enhanced energy allocation strategy.

[0031] Based on the enhanced energy allocation strategy, a specific emergency response strategy is designed for the preset abnormal situation to obtain an energy allocation strategy that adapts to the abnormal situation.

[0032] Based on the aforementioned energy allocation strategy adapted to abnormal situations, during actual operation, the latest energy consumption data of mobile makeshift hospitals, real-time power generation of renewable energy, and electricity price fluctuations of the external power grid are collected through online learning. The input state is dynamically adjusted, and a deep reinforcement learning model is used to generate an energy allocation strategy adapted to the current situation in real time. At the same time, the parameters of the deep reinforcement learning model are adjusted according to the actual situation to obtain the optimal energy allocation strategy.

[0033] Optionally, the method is characterized by combining the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns, using time series forecasting technology to predict energy consumption demand and power generation potential, and generating an energy supply and demand balance plan, including:

[0034] By combining the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns, multi-source data fusion is performed to obtain a multi-dimensional dataset.

[0035] Data preprocessing and feature engineering are performed on the multi-dimensional dataset to obtain a preprocessed multi-dimensional dataset;

[0036] Based on the preprocessed multi-dimensional dataset, a time series prediction model is constructed. A long short-term memory network deep learning model is used to capture the long-term dependencies and periodic patterns in the time series data, resulting in a trained time series prediction model.

[0037] The trained time series prediction model is used to make multi-step predictions of energy consumption demand and power generation potential within multiple preset time windows. The actual observations are added to the training dataset using a rolling update mechanism. The time series prediction model is then retrained and multi-step predictions are performed again to obtain updated prediction results.

[0038] Based on the updated forecast results, a detailed energy supply and demand balance plan is generated by comprehensively calculating the electricity demand of the medical unit, the power generation capacity of renewable energy sources, and the power supply price of the external power grid.

[0039] Optionally, based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is adopted. Operating data of the distributed energy system is collected and analyzed at preset time points. A machine learning model is used to predict fault risks from the operating data, generating evaluation results. Based on these evaluation results, the optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized to form an adaptive and self-learning energy closed-loop management system, including:

[0040] By utilizing the optimal charge and discharge plan, the operating parameter range of the distributed energy system is determined. The operating parameters include: the charge and discharge status of the energy storage system, the energy consumption of each medical unit, and the power generation of renewable energy.

[0041] At preset time points, collect and analyze the operation data of the distributed energy system within the range of the operating parameters. The operation data includes: energy efficiency ratio, carbon emissions, system reliability, and response speed.

[0042] Based on the operational data, a machine learning model is used to predict the failure risk of the distributed energy system and generate a failure risk prediction report.

[0043] Using the aforementioned fault risk prediction report, combined with key indicators of the operational data, a performance evaluation result is generated;

[0044] Using the performance evaluation results, the optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized to obtain the optimized optimal energy allocation strategy and multi-objective optimization algorithm.

[0045] The optimized energy allocation strategy and multi-objective optimization algorithm are then applied again to the distributed energy system to form an adaptive and self-learning energy closed-loop management system.

[0046] Secondly, embodiments of this application provide a distributed energy optimization management system for rapidly deploying mobile makeshift hospitals, comprising:

[0047] The building module is used to construct a multi-layered virtual energy network model for mobile modular hospitals;

[0048] The adjustment module is used to dynamically adjust energy allocation based on the multi-layer virtual energy network model by applying a deep reinforcement learning algorithm to generate the optimal energy allocation strategy.

[0049] The prediction module is used to combine the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data and medical activity patterns, and use time series prediction technology to predict energy consumption demand and power generation potential, and generate an energy supply and demand balance plan.

[0050] The scheduling module is used to intelligently schedule the charging and discharging process of the energy storage system based on the energy supply and demand balance plan and by introducing a multi-objective optimization algorithm to obtain the optimal charging and discharging plan.

[0051] The generation module, based on the optimal charging and discharging plan, adopts a performance evaluation mechanism based on big data analysis, collects and analyzes the operation data of the distributed energy system at preset time nodes, uses a machine learning model to predict the fault risk of the operation data, generates evaluation results, and iteratively optimizes the optimal energy allocation strategy and multi-objective optimization algorithm based on the evaluation results, forming an adaptive and self-learning energy closed-loop management system.

[0052] Thirdly, embodiments of the present invention provide a computing device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a distributed energy optimization management method for rapidly deploying mobile makeshift hospitals as described in any of the first aspects.

[0053] Fourthly, embodiments of the present invention provide a computer storage medium storing computer program instructions, wherein the computer program instructions, when executed by a processor, implement a distributed energy optimization management method for rapidly deploying mobile modular hospitals as described in any one of the first aspects.

[0054] In this embodiment of the invention, a multi-layered virtual energy network model for a mobile makeshift hospital is constructed. Based on this model, a deep reinforcement learning algorithm is applied to dynamically adjust energy allocation and generate an optimal energy allocation strategy. Combining the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns, time series forecasting technology is used to predict energy demand and power generation potential, generating an energy supply and demand balance plan. Based on this plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system, obtaining an optimal charging and discharging plan. Based on this plan, a performance evaluation mechanism based on big data analysis is adopted. Operating data of the distributed energy system is collected and analyzed at preset time nodes. A machine learning model is used to predict fault risks from the operating data, generating evaluation results. Based on these results, the optimal energy allocation strategy and the multi-objective optimization algorithm are iteratively optimized, forming an adaptive and self-learning energy closed-loop management system. The technical solution provided by this invention, by constructing a multi-layered virtual energy network model and combining deep reinforcement learning, time series forecasting, and multi-objective optimization algorithms, achieves efficient energy utilization, flexible scheduling, and stable energy supply. Specifically, this method can dynamically adjust energy allocation strategies, accurately predict future energy consumption demand and power generation potential, intelligently schedule the charging and discharging process of energy storage systems, and monitor system status in real time and predict potential faults through a performance evaluation mechanism based on big data analysis and machine learning models, thereby improving the overall energy efficiency, adaptability and reliability of the system and reducing maintenance costs and workload.

[0055] These or other aspects of the invention will become more apparent from the following description of the embodiments. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 A flowchart illustrating a distributed energy optimization management method for rapidly deploying mobile modular hospitals, provided as an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the structure of a distributed energy optimization management system for rapidly deploying mobile modular hospitals provided in an embodiment of the present invention;

[0059] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present invention. Detailed Implementation

[0060] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0061] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0062] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] In existing technologies, traditional centralized energy supply methods cannot dynamically adjust energy allocation strategies based on the real-time power demand of medical equipment and the generation of renewable energy, leading to frequent energy waste or supply shortages. Existing energy management systems lack intelligent scheduling capabilities and cannot fully utilize the advantages of renewable energy and energy storage systems, especially when facing complex and changing power environments, exhibiting poor adaptability and robustness. Furthermore, due to the lack of effective fault prediction and self-healing functions, existing energy management systems are prone to failure during operation, requiring frequent manual intervention and maintenance, increasing operation and maintenance costs and workload. Therefore, this invention provides a distributed energy optimization management method for rapidly deploying mobile modular hospitals, such as... Figure 1 The specific steps are as follows:

[0064] Step 101: Construct a multi-layered virtual energy network model for the mobile modular hospital;

[0065] In this step, a multi-layered virtual energy network model is constructed. This model comprehensively considers the energy flow and interrelationships between various medical units, energy storage systems, renewable energy generation units, and external power grid connection points within the mobile modular hospital. By simulating the operating states and mutual influences of different devices and systems, it provides the infrastructure for subsequent energy optimization management. This model not only includes physical connections but also covers information such as energy demand forecasts and power generation capacity assessments for each node, ensuring a comprehensive reflection of actual operating conditions.

[0066] Step 102: Based on the multi-layer virtual energy network model, apply a deep reinforcement learning algorithm to dynamically adjust energy allocation and generate the optimal energy allocation strategy;

[0067] In this step, deep reinforcement learning algorithms (such as Qlearning or DQN) are used to dynamically adjust the energy allocation strategy based on real-time data provided by a multi-layered virtual energy network model. Through continuous trial and error learning, the algorithm selects the optimal action, i.e., the energy allocation scheme, under different system states to maximize long-term cumulative rewards. These rewards can be a comprehensive evaluation based on multiple objectives such as energy consumption cost, renewable energy utilization rate, and power supply reliability for critical medical facilities. Ultimately, this generates an optimal energy allocation strategy that can adapt to various operating conditions.

[0068] Step 103: Combining the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns, use time series forecasting technology to predict energy consumption demand and power generation potential, and generate an energy supply and demand balance plan.

[0069] In this step, time series forecasting techniques are used to predict future energy demand and power generation potential by combining optimal energy allocation strategies, real-time weather forecasts, historical energy consumption data, and medical activity patterns. Specifically, the time series model analyzes past data patterns and combines them with current external conditions (such as weather changes) and internal demands (such as changes in the power priority of medical equipment) to accurately predict energy demand and renewable energy generation over a future period. The result of this process is the generation of a detailed energy supply and demand balance plan to guide subsequent energy dispatch decisions.

[0070] Step 104: Based on the energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system to obtain the optimal charging and discharging plan;

[0071] In this step, based on the generated energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system. The multi-objective optimization algorithm aims to consider multiple optimization objectives simultaneously, such as minimizing the operating cost of the energy storage system, maximizing the utilization rate of renewable energy, and ensuring the reliability of power supply to critical medical facilities. By solving the multi-objective optimization problem, a Pareto front composed of a set of non-dominated solutions is found, and the best charging and discharging plan that is most suitable for the current operating conditions is selected from it to ensure that the energy storage system can achieve efficient and stable operation under different operating conditions.

[0072] Step 105: Based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is adopted. The operation data of the distributed energy system is collected and analyzed at preset time nodes. The failure risk is predicted by the operation data through a machine learning model, and an evaluation result is generated. The optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized according to the evaluation result to form an adaptive and self-learning energy closed-loop management system.

[0073] In this step, based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analytics is employed to collect and analyze the operational data of the distributed energy system at preset time points. Machine learning models are used to predict fault risks from this data, generating evaluation results. Based on these results, the optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized to ensure the system can continuously improve and adapt to new operating conditions. This adaptive and self-learning closed-loop energy management system makes the entire energy management system more intelligent and efficient.

[0074] Based on this, the present invention provides a specific embodiment. Step 104, based on the energy supply and demand balance plan, introduces a multi-objective optimization algorithm to intelligently schedule the charging and discharging process of the energy storage system to obtain the optimal charging and discharging plan, specifically including the following steps:

[0075] Step 201: Using the current state information of the energy storage system and in conjunction with the energy supply and demand balance plan, construct a dynamic mathematical model of the energy storage system;

[0076] In this step, based on the current state information of the energy storage system (such as remaining capacity, maximum charge and discharge power limit, charge and discharge efficiency, etc.), and combined with the future energy consumption demand and power generation potential predictions provided by the energy supply and demand balance plan, a dynamic mathematical model is constructed. This model can reflect the operating status of the energy storage system at different points in time in real time and provide the necessary input data for subsequent optimization algorithms, ensuring that the model can accurately simulate the actual behavior of the energy storage system.

[0077] Step 202: Using the aforementioned dynamic mathematical model, and considering the priority of electricity demand from medical equipment, the real-time power generation of renewable energy sources, and fluctuations in external grid electricity prices, design a multi-objective optimization function.

[0078] In this step, a multi-objective optimization function is designed using the established dynamic mathematical model, combined with factors such as the priority of electricity demand from medical equipment, real-time generation of renewable energy, and fluctuations in external grid electricity prices. This function comprehensively considers multiple optimization objectives, such as minimizing the operating cost of the energy storage system, maximizing the utilization rate of renewable energy, and ensuring the reliability of power supply to critical medical facilities. This approach ensures that the optimization process achieves efficient energy utilization and smooth supply while satisfying multiple constraints.

[0079] Step 203: Apply evolutionary computation methods and combine them with a fuzzy logic controller to solve the multi-objective optimization function and obtain a Pareto front composed of a set of non-dominated solutions;

[0080] In this step, evolutionary computation methods (such as genetic algorithms or differential evolution algorithms) are combined with a fuzzy logic controller to solve the multi-objective optimization function. The evolutionary computation method explores the solution space, searching for a series of non-dominated solutions, i.e., the Pareto front. The fuzzy logic controller dynamically adjusts the parameters during the optimization process based on the current system state and environmental conditions, improving both the efficiency and quality of the solution. The final set of non-dominated solutions constitutes the Pareto front, with each solution representing a possible optimal charging and discharging plan.

[0081] Step 204: Using a multi-criteria decision support system, integrating expert knowledge and user preferences, select the optimal charge / discharge plan from the Pareto front.

[0082] In this step, a multi-criteria decision support system is used to integrate expert knowledge and user preferences to select the optimal charge-discharge plan from the Pareto front. The system employs methods such as the Analytic Hierarchy Process (AHP) or the Technology Selection and Prioritization Method (TOPS IS) to evaluate the performance of each non-dominated solution on different objectives. Combining expert experience with the actual needs of the user, the optimal charge-discharge plan is ultimately selected that meets both performance requirements and operator preferences, ensuring its feasibility and effectiveness in practical applications.

[0083] Based on this, the present invention provides a specific embodiment. Step 202, utilizing the dynamic mathematical model and combining the priority of electricity demand of medical equipment, the real-time power generation of renewable energy, and the fluctuation of electricity prices on the external power grid, designs a multi-objective optimization function, specifically including the following steps:

[0084] Step 301: Using the dynamic mathematical model, combined with the priority of electricity demand of medical equipment, the real-time power generation of renewable energy and the fluctuation of electricity prices of the external power grid, define the objective variable of the multi-objective optimization function;

[0085] In this step, based on the dynamic mathematical model of the energy storage system, and combined with the priority of electricity demand of medical equipment, the real-time power generation of renewable energy, and the fluctuation of electricity prices of the external power grid, the specific target variables of the multi-objective optimization function are determined. These target variables include, but are not limited to, the operating cost of the energy storage system, the utilization rate of renewable energy, the reliability of power supply to key medical facilities, and carbon emissions. By clarifying these target variables, the foundation is laid for the subsequent design of specific optimization functions.

[0086] Step 302: Design a specific expression for the multi-objective optimization function based on the target variables, wherein the expression includes each target variable and the relative importance weight of each target variable;

[0087] In this step, a specific mathematical expression for the multi-objective optimization function is designed based on the defined objective variables. This expression not only includes each objective variable but also introduces a relative importance weight for each objective variable. The weight coefficients reflect the priority and importance of different objectives in the overall optimization process, ensuring that the optimization result finds the optimal balance among multiple objectives. For example, the power supply reliability of critical medical facilities may be given a higher weight to ensure their stable operation.

[0088] Step 303: Using the specific expression combined with historical and real-time data, calibrate the parameters in the multi-objective optimization function to obtain the calibrated multi-objective optimization function;

[0089] In this step, specific expressions are used, combined with historical and real-time data, to calibrate the parameters in the multi-objective optimization function. Historical data provides the past operating patterns and trends of the system, while real-time data reflects the current state and environmental changes of the system. Through comprehensive analysis of these data, the parameters in the optimization function are adjusted to more accurately reflect the actual operating conditions. The calibrated multi-objective optimization function can better adapt to different operating conditions, improving the reliability and accuracy of the optimization results.

[0090] Step 304: Using the calibrated multi-objective optimization function, and combining changes in the external environment and internal requirements, dynamically adjust the weight coefficients in the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions;

[0091] In this step, the weight coefficients in the calibrated multi-objective optimization function are dynamically adjusted based on changes in the external environment (such as weather conditions and fluctuations in external power grid prices) and changes in internal demand (such as changes in the priority of electricity demand for medical equipment). This dynamic adjustment mechanism enables the optimization function to flexibly respond to different operating conditions, ensuring that the optimal energy management strategy can be found under any circumstances. The resulting multi-objective optimization function not only adapts to current operating conditions but also maintains high efficiency and stability in future environments.

[0092] Based on this, the present invention provides a specific embodiment. Step 304, using the calibrated multi-objective optimization function and combining changes in the external environment and internal requirements, dynamically adjusts the weight coefficients in the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions. Specifically, this includes the following steps:

[0093] Step 401: Using the calibrated multi-objective optimization function, combined with changes in the external environment and internal needs, analyze the trend of importance changes of each objective variable to obtain the results of the importance change trend analysis.

[0094] In this step, a calibrated multi-objective optimization function is used to analyze the changing trends of the importance of each objective variable by combining changes in the external environment (such as weather conditions and fluctuations in external power grid prices) and changes in internal demand (such as changes in the priority of electricity demand for medical equipment). Through comparative analysis of historical and real-time data, the changing patterns of each objective variable in different time periods are identified, and the results of the importance trend analysis are finally obtained.

[0095] Step 402: Design weight adjustment rules for the importance change trend analysis results, wherein the weight adjustment rules include the differences in the importance of each target variable in different time periods;

[0096] In this step, weight adjustment rules are designed based on the analysis of importance trends. These rules consider the differences in the importance of each objective variable over different time periods, ensuring that the optimization function can flexibly adapt to various operating conditions. For example, when renewable energy generation is higher during the day, the weight of renewable energy utilization may be increased; while at night, the importance of energy storage systems may be higher. In this way, a set of rules for dynamically adjusting weight coefficients is established.

[0097] Step 403: Dynamically adjust the weight coefficients in the multi-objective optimization function using the weight adjustment rule to obtain dynamic weight coefficients;

[0098] In this step, pre-designed weight adjustment rules are applied to dynamically adjust the weight coefficients in the multi-objective optimization function. Based on the current time period and actual operating conditions, the weight coefficients of each objective variable are automatically updated to reflect the latest trends in importance. This process ensures that the optimization function can adapt to changes in the external environment and internal needs in real time, generating more accurate and effective energy management strategies, ultimately resulting in dynamic weight coefficients.

[0099] Step 404: Apply the dynamic weight coefficients to the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions;

[0100] In this step, dynamic weighting coefficients are applied to the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions. By introducing dynamic weighting coefficients, the optimization function can find the optimal solution under different operating conditions, ensuring that the charging and discharging process of the energy storage system and the overall energy management strategy are always in the best state. This adaptive optimization mechanism improves the flexibility and reliability of the system, ensuring that the energy supply of the mobile modular hospital is both efficient and stable.

[0101] Existing methods typically employ static weighting coefficients, failing to dynamically adjust the importance of each target variable based on changes in the external environment, internal demand, and time period. This results in inflexible energy management strategies under different operating conditions, hindering the effective response to fluctuations in electricity demand from medical equipment and uncertainties in renewable energy generation, thus impacting the overall system performance and stability. Therefore, this invention introduces a weighting adjustment rule for dynamically adjusting the weighting coefficients. The expression for this dynamic adjustment rule is as follows:

[0102]

[0103] Among them, w i (t) represents the weight coefficient of the i-th objective variable at time t; The initial weight coefficients of the i-th objective variable are determined by the calibrated multi-objective optimization function; α i Δt represents the weight adjustment coefficient of the i-th target variable as it changes over time, reflecting the difference in importance of each target variable within different time periods; Δt represents the time interval, used to represent the time difference from the last adjustment to the current time; β i ΔE represents the weight adjustment coefficient of the i-th target variable as the external environment changes, reflecting the impact of changes in the external environment on the importance of the target variable; i (t) represents the change in the external environment of the i-th target variable at time t, which can be obtained by analyzing external environmental data such as real-time weather forecasts and fluctuations in external power grid prices; γ iΔD represents the weight adjustment coefficient of the i-th target variable as internal demand changes, reflecting the impact of changes in internal demand on the importance of the target variable; i (t) represents the change in internal demand of the i-th target variable at time t, which can be obtained by analyzing internal demand data such as changes in the priority of electricity demand for medical equipment; δ i F represents the weight adjustment coefficient of the i-th objective variable as the system performance changes, reflecting the impact of system performance changes on the importance of the objective variable; i (t) represents the change in system performance of the i-th objective variable at time t, obtained by analyzing the operational data of the distributed energy system; η i θ represents the weight adjustment coefficient of the i-th target variable as it changes over time, reflecting the importance of different time periods (e.g., day and night) to the target variable; T(t) represents the time period factor, such as the number of hours in a day or the number of days in a week, used to reflect the weight changes over different time periods; i The weight adjustment coefficient represents the trend of the i-th target variable as its importance changes, reflecting the degree to which the weights are adjusted based on the analysis results of the trend of importance changes; φ i (t) represents the trend value of the importance of the i-th target variable at time t, which is obtained through the analysis of historical and real-time data;

[0104] Through the aforementioned complex formula, this invention enables more precise dynamic adjustment of the weight coefficients in the multi-objective optimization function, allowing the system to better adapt to changes in the external environment, internal demand, and time cycles. This not only improves energy efficiency and ensures a stable power supply for critical medical facilities but also enhances the system's flexibility and reliability, reduces maintenance costs and workload, thereby significantly improving the overall performance of the mobile modular hospital energy management system.

[0105] Based on this, the present invention provides a specific embodiment. Step 102, based on the multi-layer virtual energy network model, applies a deep reinforcement learning algorithm to dynamically adjust energy allocation and generate an optimal energy allocation strategy, specifically including the following steps:

[0106] Step 501: Using the multi-layer virtual energy network model, integrate the energy consumption prediction information of the mobile makeshift hospital, the real-time power generation of renewable energy, the electricity price fluctuation of the external power grid, and the urgency of the mobile makeshift hospital. At the same time, calculate the uncertainty of weather changes, simulate the possible impact of weather changes through a probability distribution model, and obtain the input state.

[0107] In this step, based on a multi-layer virtual energy network model, the energy consumption prediction information of the mobile makeshift hospital, the real-time power generation of renewable energy, the electricity price fluctuations of the external power grid, and the urgency of the mobile makeshift hospital are integrated. At the same time, the uncertainty of weather changes is calculated, and the possible impact of weather changes is simulated through a probability distribution model. These data and simulation results together constitute the input state for subsequent optimization.

[0108] Step 502: Based on the input state, set the priority of power demand of mobile modular hospital, availability of renewable energy, price signal of external power grid and uncertainty of weather change as multidimensional reward function, with stable power supply and cost saving of emergency medical unit as the main optimization objectives, and obtain multidimensional reward function;

[0109] In this step, based on the input state, the priority of the mobile modular hospital's power demand, the availability of renewable energy, the price signal of the external power grid, and the uncertainty of weather changes are set as multidimensional reward functions. Stable power supply and cost savings of the emergency medical unit are set as the main optimization objectives. In this way, a multidimensional reward function that comprehensively considers multiple factors is constructed.

[0110] Step 503: Process the input state and the multidimensional reward function using a deep reinforcement learning model based on the Actor-Critic architecture to obtain an initial energy allocation strategy;

[0111] In this step, a deep reinforcement learning model based on the Actor-Critic architecture is used to process the input state and multidimensional reward function. The Actor is responsible for selecting actions (i.e., energy allocation strategies), while the Critic evaluates the value of the selected actions. Through continuous trial and error learning, an initial energy allocation strategy that can adapt to the current input state is finally obtained.

[0112] Step 504: Based on the initial energy allocation strategy, during the training process, historical data is randomly sampled for replay learning using the experience replay mechanism to improve the generalization ability and stability of the model, thereby obtaining an enhanced energy allocation strategy.

[0113] In this step, based on the initial energy allocation strategy, an experience replay mechanism is introduced during the training process. By randomly sampling historical data for replay learning, the model can be trained in more diverse scenarios, thereby improving its generalization ability and stability, and finally obtaining an enhanced energy allocation strategy after reinforcement learning.

[0114] Step 505: Based on the enhanced energy allocation strategy, design specific emergency response strategies for preset abnormal situations to obtain an energy allocation strategy that adapts to abnormal situations;

[0115] In this step, based on the enhanced energy distribution strategy, specific emergency response strategies are designed for pre-set abnormal situations (such as equipment failure or extreme weather). These strategies ensure that the system can still maintain stable operation under abnormal situations, ultimately forming an energy distribution strategy that adapts to abnormal situations.

[0116] Step 506: Based on the energy allocation strategy adapted to abnormal situations, during actual operation, the latest energy consumption data of mobile makeshift hospitals, real-time power generation of renewable energy, and electricity price fluctuations of the external power grid are collected using online learning. The input state is dynamically adjusted, and a deep reinforcement learning model is used to generate an energy allocation strategy adapted to the current situation in real time. At the same time, the parameters of the deep reinforcement learning model are adjusted according to the actual situation to obtain the optimal energy allocation strategy.

[0117] In this step, based on the energy allocation strategy adapted to abnormal situations, an online learning approach is adopted during actual operation. By continuously collecting the latest energy consumption data, renewable energy generation status, and external grid electricity price fluctuations, the input state is dynamically adjusted. A deep reinforcement learning model is used to generate an energy allocation strategy adapted to the current situation in real time, and the model parameters are adjusted according to the actual situation to finally obtain the optimal energy allocation strategy.

[0118] Based on this, the present invention provides a specific embodiment, wherein step 103 specifically includes the following steps:

[0119] Step 601: Combine the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data, and medical activity patterns to perform multi-source data fusion and obtain a multi-dimensional dataset;

[0120] In this step, multi-source data fusion is performed, combining optimal energy allocation strategies, real-time weather forecasts, historical energy consumption data, and medical activity patterns. These data sources include, but are not limited to, the charging and discharging status of energy storage systems, the energy consumption of each medical unit, and the power generation of renewable energy sources. By integrating this data from different sources, a comprehensive dataset encompassing multiple dimensions such as time, location, and equipment status is formed, providing a comprehensive foundation for subsequent analysis.

[0121] Step 602: Perform data preprocessing and feature engineering on the multi-dimensional dataset to obtain a preprocessed multi-dimensional dataset;

[0122] In this step, data preprocessing and feature engineering are performed on the multi-dimensional dataset. Data preprocessing includes operations such as removing outliers, imputing missing values, and standardization or normalization to ensure data quality. Feature engineering involves extracting useful features from the raw data, such as calculating moving averages, generating lagged features, and extracting periodic components. After these processes, a structured and easily modelable preprocessed multi-dimensional dataset is obtained.

[0123] Step 603: Based on the preprocessed multi-dimensional dataset, construct a time series prediction model, and use a long short-term memory network deep learning model to capture long-term dependencies and periodic patterns in the time series data to obtain the trained time series prediction model.

[0124] In this step, a time series prediction model is constructed based on the preprocessed multi-dimensional dataset. Long Short-Term Memory (LSTM) networks are chosen as the deep learning model because they excel at capturing long-term dependencies and periodic patterns in time series data. By training this model, it can accurately predict future energy consumption demand and power generation potential, ultimately resulting in the trained time series prediction model.

[0125] Step 604: Use the trained time series prediction model to make multi-step predictions of energy consumption demand and power generation potential within multiple preset time windows, and use a rolling update mechanism to add the actual observations to the training dataset, retrain the time series prediction model and make multi-step predictions again to obtain the updated prediction results.

[0126] In this step, the trained time series prediction model is used to make multi-step predictions of energy consumption demand and power generation potential within multiple preset time windows. In order to improve the accuracy of the prediction, a rolling update mechanism is adopted, in which actual observations are added to the training dataset, the time series prediction model is retrained, and multi-step predictions are made again. This process ensures that the model always makes predictions based on the latest data, thereby obtaining more accurate and reliable updated prediction results.

[0127] Step 605: Based on the updated prediction results, comprehensively calculate the electricity demand of the medical unit, the power generation capacity of renewable energy and the power supply price of the external power grid, and generate a detailed energy supply and demand balance plan;

[0128] In this step, based on the updated forecast results, a detailed energy supply and demand balance plan is generated by comprehensively considering the electricity demand of the medical unit, the power generation capacity of renewable energy and the power supply price of the external grid, and by calculating the balance between these factors in detail. This plan not only guides the charging and discharging strategy of the energy storage system, but also optimizes the energy management of the entire mobile hospital, ensuring a stable power supply for critical medical facilities and effective cost control.

[0129] Based on this, the present invention provides a specific embodiment. Step 105, based on the optimal charging and discharging plan, employs a performance evaluation mechanism based on big data analysis, collects and analyzes the operating data of the distributed energy system at preset time nodes, uses a machine learning model to predict fault risks from the operating data, generates evaluation results, and iteratively optimizes the optimal energy allocation strategy and multi-objective optimization algorithm based on the evaluation results to form an adaptive and self-learning energy closed-loop management system. Specifically, it includes the following steps:

[0130] Step 701: Using the optimal charging and discharging plan, determine the operating parameter range of the distributed energy system. The operating parameters include: the charging and discharging status of the energy storage system, the energy consumption of each medical unit, and the power generation of renewable energy.

[0131] In this step, the range of operating parameters for the distributed energy system is determined based on the optimal charging and discharging schedule. These parameters include the charging and discharging status of the energy storage system, the energy consumption of each medical unit, and the power generation of renewable energy. By clarifying the range of these operating parameters, specific guidance is provided for subsequent data collection and analysis, ensuring the accuracy and representativeness of the data.

[0132] Step 702: At preset time points, collect and analyze the operation data of the distributed energy system within the range of the operating parameters. The operation data includes: energy efficiency ratio, carbon emissions, system reliability, and response speed.

[0133] In this step, operational data of the distributed energy system within the specified operating parameter range is collected and analyzed at predetermined time points. This operational data includes key indicators such as energy efficiency ratio, carbon emissions, system reliability, and response speed. By regularly collecting and analyzing this data, a comprehensive understanding of the system's actual operating status can be obtained, providing a basis for subsequent performance evaluation and optimization.

[0134] Step 703: Based on the operational data, predict the failure risk of the distributed energy system using a machine learning model and generate a failure risk prediction report;

[0135] In this step, based on the collected operational data, machine learning models are used to predict the failure risks of the distributed energy system. These models can identify various factors that may lead to system failure and predict potential future risks, ultimately generating a failure risk prediction report to help managers take preventative measures in advance and reduce the potential failure rate.

[0136] Step 704: Using the aforementioned fault risk prediction report and combining it with the key indicators of the operational data, generate performance evaluation results;

[0137] In this step, the failure risk prediction report is used in conjunction with key indicators in the operating data, such as energy efficiency ratio, carbon emissions, system reliability and response speed, to generate performance evaluation results. The performance evaluation results not only reflect the current operating status of the system, but also point out existing problems and directions for improvement, providing clear goals and basis for subsequent optimization.

[0138] Step 705: Using the performance evaluation results, iteratively optimize the optimal energy allocation strategy and multi-objective optimization algorithm to obtain the optimized optimal energy allocation strategy and multi-objective optimization algorithm;

[0139] In this step, the optimal energy allocation strategy and multi-objective optimization algorithm are iteratively optimized using the performance evaluation results. By adjusting the parameters and weights in the optimization algorithm, the new strategy and algorithm can further improve the overall efficiency and stability of the system while meeting performance requirements. Finally, the optimized optimal energy allocation strategy and multi-objective optimization algorithm are obtained, ensuring that the system can continuously improve and adapt to new operating conditions.

[0140] Step 706: The optimized energy allocation strategy and multi-objective optimization algorithm are applied again to the distributed energy system to form an adaptive and self-learning energy closed-loop management system.

[0141] In this step, the optimized energy allocation strategy and multi-objective optimization algorithm are applied again to the distributed energy system. By continuously cycling through this process, the system can automatically adjust and optimize its own operation mode based on the latest operating data and performance evaluation results, forming an adaptive and self-learning energy closed-loop management system. This mechanism ensures that the system can always maintain a high-efficiency and stable operating state under different operating conditions.

[0142] Figure 2 This application provides a schematic diagram of the structure of a distributed energy optimization management system for rapidly deploying mobile modular hospitals, as shown in the embodiments of this application. Figure 2 As shown, the system includes:

[0143] Module 21 is used to build a multi-layered virtual energy network model for mobile modular hospitals;

[0144] Adjustment module 22 is used to dynamically adjust energy allocation based on the multi-layer virtual energy network model by applying a deep reinforcement learning algorithm to generate the optimal energy allocation strategy.

[0145] The prediction module 23 is used to combine the optimal energy allocation strategy, real-time weather forecast information, historical energy consumption data and medical activity patterns, and use time series prediction technology to predict energy consumption demand and power generation potential, and generate an energy supply and demand balance plan.

[0146] The scheduling module 24 is used to intelligently schedule the charging and discharging process of the energy storage system based on the energy supply and demand balance plan and by introducing a multi-objective optimization algorithm to obtain the optimal charging and discharging plan.

[0147] The generation module 25, based on the optimal charging and discharging plan, adopts a performance evaluation mechanism based on big data analysis, collects and analyzes the operation data of the distributed energy system at preset time nodes, performs fault risk prediction on the operation data through a machine learning model, generates evaluation results, and iteratively optimizes the optimal energy allocation strategy and multi-objective optimization algorithm based on the evaluation results to form an adaptive and self-learning energy closed-loop management system.

[0148] Figure 2 The aforementioned distributed energy optimization management system for rapidly deploying mobile modular hospitals can execute... Figure 1 The implementation principle and technical effects of the xx method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs operations in the distributed energy optimization management system for rapidly deploying mobile makeshift hospitals described in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0149] Figure 2 The distributed energy optimization management system for a rapidly deployable mobile modular hospital, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0150] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0151] The processing component 32 is used to construct a multi-layer virtual energy network model for mobile modular hospitals;

[0152] Based on the aforementioned multi-layered virtual energy network model, a deep reinforcement learning algorithm is applied to dynamically adjust energy allocation and generate an optimal energy allocation strategy. Combining this optimal energy allocation strategy with real-time weather forecasts, historical energy consumption data, and medical activity patterns, time series forecasting technology is used to predict energy demand and power generation potential, generating an energy supply and demand balance plan. Based on this energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system, obtaining an optimal charging and discharging plan. Based on this optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is adopted. Operating data of the distributed energy system is collected and analyzed at preset time nodes. A machine learning model is used to predict fault risks from the operating data, generating evaluation results. Based on these evaluation results, the optimal energy allocation strategy and the multi-objective optimization algorithm are iteratively optimized, forming an adaptive and self-learning energy closed-loop management system.

[0153] The processing component 32 includes one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component can be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DPs), digital signal processing devices (DPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0154] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0155] Computing devices also include other components such as input / output interfaces, display components, and communication components.

[0156] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices or input devices.

[0157] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0158] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0159] This invention also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The illustrated embodiment presents a distributed energy optimization management method and system for rapidly deploying mobile modular hospitals.

[0160] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0161] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0163] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed energy optimization management method for rapid deployment of a mobile shelter hospital, characterized in that, The application relates to a multi-layer virtual energy network model for constructing a mobile shelter hospital. Based on the multi-layer virtual energy network model, a deep reinforcement learning algorithm is applied to dynamically adjust energy distribution and generate an optimal energy distribution strategy. In combination with the optimal energy distribution strategy, real-time weather forecast information, historical energy consumption data and medical activity patterns, a time series prediction technology is used to predict energy consumption demand and power generation potential, and an energy supply and demand balance plan is generated. Based on the energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system, and an optimal charging and discharging plan is obtained. Based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is adopted to collect and analyze the operation data of the distributed energy system at preset time nodes, a machine learning model is used to predict the fault risk of the operation data, an evaluation result is generated, and the optimal energy distribution strategy and the multi-objective optimization algorithm are iteratively optimized based on the evaluation result, forming an adaptive and self-learning energy closed-loop management system. Based on the energy supply and demand balance plan, a multi-objective optimization algorithm is introduced to intelligently schedule the charging and discharging process of the energy storage system, and an optimal charging and discharging plan is obtained. The current state information of the energy storage system is utilized to construct a dynamic mathematical model of the energy storage system in combination with the energy supply and demand balance plan. A multi-objective optimization function is designed by utilizing the dynamic mathematical model, combining the power demand priority of medical equipment, the real-time power generation of renewable energy and the price fluctuation of the external power grid. An evolutionary calculation method is applied to solve the multi-objective optimization function in combination with a fuzzy logic controller, and a Pareto front surface composed of a group of non-inferior solutions is obtained. An multi-criteria decision support system is utilized to select the optimal charging and discharging plan from the Pareto front surface by integrating expert knowledge and user preferences. The dynamic mathematical model is utilized to define the objective variables of the multi-objective optimization function by combining the power demand priority of medical equipment, the real-time power generation of renewable energy and the price fluctuation of the external power grid. A specific expression of the multi-objective optimization function is designed according to the objective variables, and the expression contains each objective variable and the relative importance weight of each objective variable. The parameters in the multi-objective optimization function are calibrated by utilizing the specific expression in combination with historical data and real-time data, and a calibrated multi-objective optimization function is obtained. The weight coefficients in the multi-objective optimization function are dynamically adjusted by utilizing the calibrated multi-objective optimization function in combination with external environmental changes and internal demand changes, and a multi-objective optimization function suitable for different operating conditions is generated. The weight coefficients in the multi-objective optimization function are dynamically adjusted by utilizing the calibrated multi-objective optimization function in combination with external environmental changes and internal demand changes, and a multi-objective optimization function suitable for different operating conditions is generated. ​ ​ The importance trend analysis result is obtained by analyzing the importance trend of each target variable by using the calibrated multi-objective optimization function in combination with external environment changes and internal demand changes. A weight adjustment rule is designed for the importance trend analysis result, and the weight adjustment rule includes the importance difference of each target variable in different time periods. The weight coefficients in the multi-objective optimization function are dynamically adjusted by using the weight adjustment rule to obtain dynamic weight coefficients. The dynamic weight coefficients are applied to the multi-objective optimization function to generate a multi-objective optimization function that adapts to different operating conditions.

2. The method of claim 1, wherein, Based on the multi-layer virtual energy network model, a deep reinforcement learning algorithm is applied to dynamically adjust energy distribution to generate an optimal energy distribution strategy, including: The input state is obtained by integrating the mobile field hospital energy consumption prediction information, real-time renewable energy generation, external grid price fluctuations, and the urgency of the mobile field hospital, while calculating the uncertainty of weather changes, simulating the possible influence of weather changes through a probability distribution model, and using the multi-layer virtual energy network model. Based on the input state, the mobile field hospital power demand priority, renewable energy availability, external grid price signal, and weather change uncertainty are set as a multi-dimensional reward function, where stable power supply and cost savings of the emergency medical unit are the main optimization objectives, and the multi-dimensional reward function is obtained. Utilizing a deep reinforcement learning model based on processing the input state and the multi-dimensional reward function to obtain an initial energy allocation strategy; Based on the initial energy distribution strategy, the experience replay mechanism is used to randomly extract historical data for replay learning during the training process to improve the generalization ability and stability of the model, and an enhanced energy distribution strategy is obtained. Based on the enhanced energy distribution strategy, a specific emergency response strategy is designed for the preset abnormal situation to obtain an energy distribution strategy that adapts to abnormal situations. Based on the energy distribution strategy that adapts to abnormal situations, in actual operation, the latest mobile field hospital energy consumption data, real-time renewable energy generation, and external grid price fluctuations are collected using online learning to dynamically adjust the input state, and a deep reinforcement learning model is used to generate an energy distribution strategy that adapts to the current situation in real time. At the same time, the parameters of the deep reinforcement learning model are adjusted according to the actual situation to obtain the best energy distribution strategy.

3. The method of claim 1, wherein, In combination with the best energy distribution strategy, real-time weather forecast information, and historical energy consumption data and medical activity patterns, time series prediction technology is used to predict energy consumption demand and power generation potential to generate an energy supply and demand balance plan, including: In combination with the best energy distribution strategy, real-time weather forecast information, and historical energy consumption data and medical activity patterns, multi-source data fusion is performed to obtain a multi-dimensional data set. Data preprocessing and feature engineering are performed on the multi-dimensional data set to obtain a preprocessed multi-dimensional data set. Based on the preprocessed multi-dimensional data set, a time series prediction model is constructed, and a long short-term memory network deep learning model is used to capture long-term dependencies and periodic patterns in time series data to obtain a trained time series prediction model. The trained time series prediction model is used to perform multi-step prediction on energy demand and power generation potential within multiple preset time windows, and a rolling update mechanism is used to add actual observation values to the training data set, retrain the time series prediction model, and perform multi-step prediction again to obtain updated prediction results. Based on the updated prediction results, the electricity demand of the medical unit, the power generation capacity of the renewable energy source, and the power supply price of the external power grid are comprehensively calculated to generate a detailed energy supply and demand balance plan.

4. The method of claim 1, wherein, Based on the optimal charging and discharging plan, a performance evaluation mechanism based on big data analysis is used to collect and analyze the operation data of the distributed energy system at preset time nodes, and a machine learning model is used to predict the fault risk of the distributed energy system based on the operation data to generate an evaluation result. The optimal energy distribution strategy and multi-objective optimization algorithm are iteratively optimized based on the evaluation result to form a self-adaptive and self-learning energy closed-loop management system, including: Using the optimal charging and discharging plan, the operating parameter range of the distributed energy system is determined, including the charging and discharging state of the energy storage system, the energy consumption of each medical unit, and the renewable energy generation capacity; At the preset time nodes, the operation data of the distributed energy system within the operating parameter range is collected and analyzed, including the energy efficiency ratio, carbon emissions, and system reliability and response speed; Based on the operation data, a machine learning model is used to predict the fault risk of the distributed energy system to generate a fault risk prediction report; Using the fault risk prediction report, the key indicators of the operation data are combined to generate a performance evaluation result; Using the performance evaluation result, the optimal energy distribution strategy and multi-objective optimization algorithm are iteratively optimized to obtain an optimized optimal energy distribution strategy and multi-objective optimization algorithm; The optimized optimal energy distribution strategy and multi-objective optimization algorithm are applied to the distributed energy system again to form a self-adaptive and self-learning energy closed-loop management system.

5. A distributed energy optimization management system for a rapidly deployable mobile shelter hospital for performing a method of distributed energy optimization management for a rapidly deployable mobile shelter hospital according to any one of claims 1 to 4, characterized in that, Including: A construction module is configured to construct a multi-layer virtual energy network model of the mobile shelter hospital; An adjustment module is configured to apply a deep reinforcement learning algorithm to dynamically adjust energy distribution based on the multi-layer virtual energy network model to generate an optimal energy distribution strategy; A prediction module is configured to use time series prediction technology to predict energy demand and power generation potential based on the optimal energy distribution strategy, real-time weather forecast information, and historical energy consumption data and medical activity patterns to generate an energy supply and demand balance plan; A scheduling module is configured to introduce a multi-objective optimization algorithm to intelligently schedule the charging and discharging process of the energy storage system based on the energy supply and demand balance plan to obtain an optimal charging and discharging plan; A generation module is configured to use a performance evaluation mechanism based on big data analysis to collect and analyze operation data of the distributed energy system at preset time nodes, use a machine learning model to predict the fault risk of the distributed energy system based on the operation data to generate an evaluation result, and iteratively optimize the optimal energy distribution strategy and multi-objective optimization algorithm based on the evaluation result to form a self-adaptive and self-learning energy closed-loop management system.

6. A computing device, comprising: The application relates to a computer device for implementing the method, which comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component, so as to realize the distributed energy optimization management method of the fast-deployed mobile shelter hospital.

7. A computer storage medium, characterized in that The application further relates to a computer program, which is stored in a computer and used to realize the distributed energy optimization management method of the fast-deployed mobile shelter hospital.

Images