Shelter hospital power supply optimization method and system based on micro-grid technology

Abstract

The invention provides a shelter hospital power supply optimization method and system based on a micro-grid technology, and the method comprises the steps: monitoring the state information of each power utilization unit in a shelter hospital, analyzing the monitoring data through a deep reinforcement learning algorithm, and generating a dynamic adjustment strategy of a distributed power supply, a charging and discharging strategy of an energy storage system is evaluated and optimized in combination with a multi-objective optimization algorithm, a self-adaptive fuzzy logic control system is applied to adjust a power supply configuration scheme according to internal environment parameters of a shelter hospital, working characteristics of a power utilization unit and comfort requirements of a patient, an energy consumption control strategy is formed, and historical power utilization data and weather forecast information are combined to realize energy consumption control. The time sequence prediction model is used for predicting the power demand change trend and generating a scheduling plan, the block chain technology is used for recording and verifying the power transaction process and generating a power distribution scheme, and through comprehensive monitoring, intelligent analysis and self-adaptive control, operation and management of the shelter hospital power system are achieved, and reliable power supply is ensured.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of power supply for cabin hospitals, and in particular to a power supply optimization method for cabin hospitals based on microgrid technology. Background Art

[0002] In modern business operations, especially in e-commerce, finance, and marketing, data collection is a vital task. Enterprises need to monitor market dynamics, competitor conditions, customer needs, and other information in real time in order to make timely and effective decisions. Specific requirements include that enterprises need to adjust the frequency, type, and scope of data collection at any time according to business needs; data collection needs to be real-time to ensure the timeliness and accuracy of information; in order to reduce labor costs and improve efficiency, the data collection process should be automated as much as possible.

[0003] The existing scheme uses deep reinforcement learning algorithm to analyze monitoring data to generate dynamic adjustment strategies for distributed power sources, uses multi-objective optimization algorithm to comprehensively evaluate the charging and discharging optimization strategy of energy storage system, and uses fast switching control algorithm to make adaptive adjustments when external power grid fails. In addition, the adaptive fuzzy logic control system adjusts the power configuration scheme according to internal environmental parameters and patient comfort requirements, combines the time series prediction model to predict the trend of power demand changes in energy consumption control strategy, and finally uses blockchain technology to ensure transparency and security in the scheduling planning process. However, these solutions face a series of challenges: First, since they involve a large amount of real-time data collection and processing, they consume a lot of computing resources and have long delays; second, although deep reinforcement learning and multi-objective optimization methods can provide relatively accurate results, they have weak adaptability to new situations or outliers and may not be able to make optimal decisions in a timely manner; third, it is very difficult to integrate a variety of different functional modules into an efficient and collaborative whole, and there are challenges in ensuring seamless connection of each link while maintaining high reliability; finally, although blockchain technology has been introduced to enhance data security and integrity, protective measures still need to be further strengthened in the actual deployment process to resist potential attacks. At the same time, the existing technology is too professional and lacks an intuitive and easy-to-understand operating interface, making it difficult for non-professionals to understand and use it. Summary of the invention

[0004] The embodiment of the present invention provides a method and system for optimizing power supply for square cabin hospitals based on microgrid technology, so as to solve the problems in the prior art that the existing solutions may face large consumption of computing resources and long delays due to the involvement of a large amount of real-time data collection and processing; it is challenging to integrate multiple functional modules into an efficient and collaborative whole, especially in ensuring that each link can be seamlessly connected while maintaining high reliability; there are insufficient security considerations: although blockchain technology has been introduced to enhance data security and integrity, it is still necessary to further strengthen protection measures to resist potential attacks during actual deployment; many current technical implementations are too professional and lack an intuitive and easy-to-understand operating interface, making it difficult for non-professionals to understand and use them.

[0005] In a first aspect, an embodiment of the present invention provides a method for optimizing power supply of a shelter hospital based on microgrid technology, including:

[0006] Monitor the actual power demand of each power-consuming unit in the Fangcang Hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and use the deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources;

[0007] A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy;

[0008] When an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration solution in the island mode;

[0009] According to the internal environmental parameters of the Fangcang Hospital, the working characteristics of the power consumption units and the comfort requirements of the patients, the adaptive fuzzy logic control system is used to adjust the power configuration scheme to obtain the energy consumption control strategy;

[0010] Combining historical electricity consumption data with weather forecast information, the time series prediction model is applied to predict the trend of electricity demand changes for the energy consumption control strategy, and the scheduling plan of distributed power sources and energy storage systems is obtained. The blockchain technology is used to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

[0011] Optionally, according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power consumption unit and the patient comfort requirements, an adaptive fuzzy logic control system is used to adjust the power configuration scheme to obtain an energy consumption control strategy, including:

[0012] Use environmental perception sensors to monitor the internal environmental parameters of the shelter hospital, the working characteristics of the power units, and the comfort requirements of patients to obtain the environmental and demand data sets;

[0013] Analyzing the environment and demand data sets by using an adaptive fuzzy logic control system, and evaluating the applicability of energy consumption modes under different conditions in combination with the power configuration scheme to obtain a preliminary energy consumption evaluation report;

[0014] The preliminary energy consumption assessment report is precision-corrected by an integrated learning algorithm to improve the accuracy of energy consumption pattern matching and obtain a corrected energy consumption assessment report;

[0015] Applying a genetic algorithm, based on the corrected energy consumption assessment report, optimizes the energy consumption patterns of different areas in the shelter hospital and obtains optimization suggestions;

[0016] According to the optimization suggestions, combined with the flow of people and time distribution patterns in the Fangcang Hospital, the scenario-aware algorithm is used to dynamically adjust the energy consumption allocation ratio of each area and formulate an optimized energy consumption allocation plan;

[0017] The digital twin technology is used to simulate and test the optimized energy consumption allocation plan to generate an energy consumption control strategy.

[0018] Optionally, according to the optimization suggestion, combined with the flow of personnel and time distribution in the square cabin hospital, the energy consumption allocation ratio of each area is dynamically adjusted by using a scenario-aware algorithm, and an optimized energy consumption allocation plan is formulated, including:

[0019] Using the spatiotemporal prediction model, the trend of personnel flow in the preliminary energy consumption allocation plan is predicted to obtain the personnel flow prediction results;

[0020] Based on the personnel flow prediction results, the energy demand changes in each area in different time periods are analyzed by machine learning algorithms to generate dynamic energy demand predictions;

[0021] The dynamic energy demand forecast is combined with the preliminary energy consumption allocation plan, and the energy consumption allocation ratio of each area is evaluated again using a multi-objective optimization algorithm, so as to optimize energy use while meeting the needs of personnel flow, and generate a re-optimized energy consumption allocation plan;

[0022] By using augmented reality technology and combining it with the re-optimized energy consumption allocation plan, an energy consumption management interface is provided to the managers of the Fangcang Cabin Hospital, which supports real-time monitoring and manual intervention and generates an optimized energy consumption allocation plan.

[0023] Optionally, the optimized energy consumption allocation plan is simulated and tested by using digital twin technology to generate an energy consumption control strategy, including:

[0024] Using digital twin technology, a simulation test is performed on the optimized energy consumption allocation plan to obtain a simulation test result;

[0025] Through the virtual simulation platform, the application effects of the simulation test results under different environmental conditions are simulated to generate energy consumption performance data under various environmental conditions;

[0026] Apply big data analysis technology to process the energy consumption performance data, identify key factors affecting energy efficiency and their degree of influence, and form a key factor impact report;

[0027] In combination with the key factor impact report, the optimized energy consumption allocation plan is optimized using a deep learning algorithm to generate an optimized energy consumption control strategy draft;

[0028] Applying a real-time feedback mechanism, comparing and analyzing the actual operation data with the optimized draft energy consumption control strategy, dynamically adjusting the parameter settings in the draft energy consumption control strategy, and obtaining the optimal draft energy consumption control strategy;

[0029] By using visualization technology, the implementation effect of the optimal energy consumption control strategy is displayed to complete the formulation of the energy consumption control strategy.

[0030] Optionally, big data analysis technology is applied to process the energy consumption performance data, identify key factors affecting energy efficiency and their degree of influence, and form a key factor impact report, including:

[0031] Using big data analysis technology to process energy consumption performance data under various environmental conditions, a preliminary list of key factors is obtained, wherein the various environmental conditions include: climate conditions, time period, personnel density, equipment operation status, and hospital emergencies;

[0032] Using an association rule mining algorithm to deeply analyze the factors in the preliminary key factor list to obtain a key factor interaction matrix;

[0033] Based on the key factor interaction matrix, a multi-dimensional data analysis method is used to evaluate the impact of different key factor combinations to obtain a comprehensive impact assessment table;

[0034] In combination with the comprehensive impact assessment table, an energy consumption efficiency prediction model is established using a machine learning algorithm to obtain an energy consumption efficiency change trend graph;

[0035] The preliminary key factor list, key factor interaction matrix, comprehensive impact assessment table and energy efficiency change trend chart are integrated to form a key factor impact report.

[0036] Optionally, a multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy, including:

[0037] A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain a preliminary charging and discharging optimization plan;

[0038] Optimizing the preliminary charge and discharge optimization plan through a machine learning algorithm, calculating the battery health status, charge and discharge efficiency, and cost factors, and generating a detailed charge and discharge optimization plan;

[0039] Using the Internet of Things technology, the operating status of the energy storage system in the detailed charging and discharging optimization scheme is monitored in real time to generate real-time monitoring data;

[0040] Based on the real-time monitoring data, a predictive maintenance algorithm is used to predict potential failure points of the energy storage system and generate a preventive maintenance plan;

[0041] In combination with the preventive maintenance plan, a dynamic adjustment algorithm is used to adjust the detailed charge and discharge optimization plan in real time to generate a target charge and discharge optimization strategy.

[0042] Optionally, combining historical electricity consumption data with weather forecast information, applying a time series prediction model to the energy consumption control strategy to predict the trend of electricity demand changes, obtaining a dispatch plan for distributed power sources and energy storage systems, and using blockchain technology to record and verify the electricity trading process of the dispatch plan to generate a power distribution plan, including:

[0043] Combining historical electricity consumption data with weather forecast information, applying a time series forecasting model to predict the trend of electricity demand changes for the energy consumption control strategy, and obtaining preliminary electricity demand forecasting results;

[0044] Analyze the preliminary power demand forecast results using a deep learning algorithm, calculate the impact of holidays and special events, and generate a detailed power demand forecast report;

[0045] Based on the detailed power demand forecast report, the dispatch plan of the distributed power source and energy storage system is optimized by using a multi-objective optimization algorithm to generate an optimized dispatch plan;

[0046] Through the simulation test platform, the optimized scheduling plan is simulated and verified, the feasibility under different scenarios is evaluated, and a simulation test report is generated;

[0047] In combination with the simulation test report, the optimized scheduling plan is dynamically adjusted by using a real-time feedback mechanism to generate an optimal scheduling plan;

[0048] Blockchain technology is used to record and verify the power trading process of the optimal scheduling plan and generate a power distribution plan.

[0049] In a second aspect, the embodiment of the present application provides a power supply optimization for a square cabin hospital based on microgrid technology, including:

[0050] The monitoring module monitors the actual power demand of each power-consuming unit in the square cabin hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and uses a deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources;

[0051] An evaluation module, which uses a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy;

[0052] The adjustment module, when an external power grid fault is detected, uses a fast switching control algorithm to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration plan under the island mode;

[0053] The adjustment module uses an adaptive fuzzy logic control system to adjust the power configuration scheme according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power consumption unit and the patient comfort requirements, and obtains an energy consumption control strategy;

[0054] The recording module combines historical electricity consumption data with weather forecast information, applies a time series prediction model to predict the trend of electricity demand changes for the energy consumption control strategy, obtains the scheduling plan of distributed power sources and energy storage systems, and uses blockchain technology to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

[0055] In a third aspect, an embodiment of the present invention provides 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 method for optimizing power supply for a cabin hospital based on microgrid technology as described in any one of the first aspects.

[0056] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement a method for optimizing power supply for a cabin hospital based on microgrid technology as described in any one of the first aspects.

[0057] In the embodiment of the present invention, the actual power demand of each power-consuming unit in the square cabin hospital, the operating status of the current power supply system and the status information of the external power grid are monitored to obtain monitoring data, and the monitoring data is analyzed by using a deep reinforcement learning algorithm to obtain a dynamic adjustment strategy for the distributed power source;

[0058] A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy;

[0059] When an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration solution in the island mode;

[0060] According to the internal environmental parameters of the Fangcang Hospital, the working characteristics of the power consumption units and the comfort requirements of the patients, the adaptive fuzzy logic control system is used to adjust the power configuration scheme to obtain the energy consumption control strategy;

[0061] Combining historical electricity consumption data with weather forecast information, the time series prediction model is applied to predict the trend of electricity demand changes for the energy consumption control strategy, and the scheduling plan of distributed power sources and energy storage systems is obtained. The blockchain technology is used to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

[0062] The technical solution provided by the present invention realizes the intelligent management and optimization of the electric power supply system of the Cabin Hospital, improves the efficiency of electric power use, enhances the flexibility and reliability of the system, improves the patient experience, and ensures the security and transparency of the electric power trading process. Among them, enhance transparency and security: the application of blockchain technology not only ensures the transparency of the electric power trading process, but also enhances the security and integrity of the data, provides traceable and tamper-proof records for all participants, and promotes the establishment of a fair and just electric power trading mechanism; improves system robustness: when an external power grid fault is detected, the fast switching control algorithm can quickly adjust the operating mode of the energy storage system to the island operation state, ensuring the uninterrupted power supply of key medical facilities in the Cabin Hospital, and enhancing the reliability and stability of the entire power supply system.

[0063] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A flowchart of a method for optimizing power supply for a shelter hospital based on microgrid technology provided in an embodiment of the present invention;

[0066] Figure 2 A schematic diagram of the structure of a square cabin hospital power supply optimization system based on microgrid technology provided in an embodiment of the present invention;

[0067] Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0069] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0071] In the prior art, the data acquisition system relies on pre-set rules for data acquisition, and the pre-set rules remain fixed during the operation of the system. In practical applications, the characteristics of the data source, data requirements, and business logic will change over time, requiring the data acquisition system to be able to adapt to these changes. Based on this, the present invention provides a method for optimizing the power supply of a shelter hospital based on microgrid technology, such as Figure 1 ,include:

[0072] Step 101: monitor the actual power demand of each power consumption unit in the square cabin hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and use the deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for the distributed power source;

[0073] In this step, this stage includes real-time monitoring of the power consumption of all electrical equipment in the square cabin hospital, such as medical instruments, lighting systems, etc., and monitoring the operation of the entire power supply system, such as voltage, current, frequency, etc., as well as the health of the external power grid. Through these monitoring data, we can fully understand the current power supply and demand. Then, use a deep reinforcement learning algorithm to analyze this data. The algorithm can learn the power demand pattern from a large amount of historical data and generate a dynamic adjustment strategy based on this to optimize the working mode of distributed power sources, such as solar panels, wind turbines, etc., to ensure the balance of power supply and demand.

[0074] For example, in a makeshift shelter hospital, smart meters and sensor networks are installed to collect power consumption data in each ward and public area. At the same time, information about the external power grid is obtained through cooperation with the local power company. Then, a software platform based on deep reinforcement learning is used to analyze this data, predict the renewable energy generation in the next few hours based on weather changes, and automatically adjust the output power of distributed power sources to meet actual needs.

[0075] Step 102: using a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy;

[0076] In this step, after determining the dynamic adjustment strategy of distributed power sources, it is necessary to further consider how to effectively manage energy storage systems, such as battery packs. Multi-objective optimization algorithms play a key role in this process. They simultaneously consider multiple factors, such as cost-effectiveness, energy efficiency, environmental impact, etc., to find the best energy storage system charging and discharging solution. This helps ensure a stable power supply even when power demand peaks or troughs.

[0077] Step 103: When an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the energy storage system charging and discharging optimization strategy to obtain a power configuration solution in an island mode;

[0078] In this step, if a fault in the external power grid is detected, the fast switching control algorithm will be activated immediately, causing the Fangcang Cabin Hospital to enter "island" mode, that is, completely relying on the internal distributed power supply and energy storage system to operate independently. At this time, the previously formulated energy storage system charging and discharging strategy will be re-evaluated and adjusted to ensure that the normal operation of important equipment can be maintained without external power support.

[0079] Step 104: According to the internal environmental parameters of the square cabin hospital, the working characteristics of the power consumption unit and the patient comfort requirements, the power supply configuration scheme is adjusted by using an adaptive fuzzy logic control system to obtain an energy consumption control strategy;

[0080] In this step, in order to further refine the management of power resources, an adaptive fuzzy logic control system is introduced to fine-tune the power configuration plan. This system can handle uncertainty and nonlinear relationships, and flexibly adjust the energy consumption of facilities such as air conditioning and lighting according to changes in environmental parameters such as temperature and humidity and the working mode of power units in different time periods, while taking into account the comfort needs of patients to achieve more humane energy management.

[0081] For example, during high temperatures in summer, the adaptive fuzzy logic control system of the square cabin hospital will automatically adjust the air conditioning set points based on the data from the indoor temperature and humidity sensors, while reducing the lighting brightness in non-essential areas, saving electricity and ensuring a good treatment environment.

[0082] Step 105: Combine historical electricity consumption data with weather forecast information, apply a time series prediction model to predict the trend of electricity demand changes for the energy consumption control strategy, obtain a dispatch plan for distributed power sources and energy storage systems, use blockchain technology to record and verify the electricity trading process of the dispatch plan, and generate a power distribution plan;

[0083] In this step, the last step is to use historical electricity consumption records and the latest weather forecast information to make an accurate estimate of electricity demand in the future through a time series forecasting model. Based on this forecast result, a more reasonable scheduling plan for distributed power sources and energy storage systems can be formulated. In addition, blockchain technology is used to record and verify all scheduling decisions and their execution to ensure that the entire process is transparent and credible.

[0084] For example, combining the electricity consumption data of the past year and the weather forecast for the next week provided by the Meteorological Bureau, the time series model predicts that there will be continuous rainy weather next week, and the power generation of photovoltaic panels may drop significantly. Therefore, the dispatch plan recommends increasing the charging capacity of the energy storage system in advance and appropriately reducing the power supply to certain equipment in the cabin hospital in non-emergency situations. All these decisions will be publicly released through the blockchain platform for relevant stakeholders to review and supervise.

[0085] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0086] By monitoring the actual power demand of each power unit in the Fangcang Hospital, the status of the power supply system and the external power grid information, the deep reinforcement learning algorithm is used to analyze the data, generate a dynamic adjustment strategy, and combine the multi-objective optimization algorithm to evaluate the charging and discharging strategy of the energy storage system. When the external power grid fails, the fast switching control algorithm ensures stable power supply in the island mode. The adaptive fuzzy logic control system adjusts the power supply configuration according to environmental parameters and patient comfort requirements to optimize energy consumption. The time series prediction model combines historical data and weather forecasts to predict the trend of power demand changes and generate a scheduling plan. These steps significantly improve the stability and efficiency of power supply, reduce operating costs, enhance the flexibility and reliability of the system, and ensure the efficient operation of Fangcang Hospital under various conditions.

[0087] Based on this, the present invention provides a specific embodiment, wherein step 104 receives collection rule parameters input by a user, wherein the collection rule parameters include collection frequency, collection type, and collection scope, and specifically includes the following steps:

[0088] Step 401: Use environmental sensing sensors to monitor the internal environmental parameters of the shelter hospital, the working characteristics of the power units, and the comfort requirements of the patients to obtain an environmental and demand data set;

[0089] In this step, various environmental sensing sensors, such as temperature sensors, humidity sensors, and light intensity sensors, are deployed to collect real-time environmental parameters inside the shelter hospital. At the same time, the working status and performance indicators of different power consumption units are also monitored, such as the operating efficiency of the air-conditioning system and the energy consumption of lighting equipment. In addition, the patient's comfort feedback, such as preferences for temperature and light, is also considered. Together, this information constitutes a comprehensive data set for subsequent analysis.

[0090] For example, a variety of sensors are installed in a shelter hospital, including temperature and humidity sensors, carbon dioxide concentration detectors, and light sensors. These sensors can not only continuously record the physical environment conditions in the ward, but also collect patients' satisfaction evaluations of the current environmental conditions through an intelligent questionnaire system. All of these data are aggregated into a central database to form a detailed set of environmental and demand data.

[0091] Step 402: Analyze the environment and demand data set using an adaptive fuzzy logic control system, evaluate the applicability of energy consumption modes under different conditions in combination with the power configuration scheme, and obtain a preliminary energy consumption evaluation report;

[0092] In this step, the adaptive fuzzy logic control system is a control method based on fuzzy logic theory, which can handle uncertainty and nonlinear relationships and is suitable for complex and changing environments. By analyzing the environment and demand data sets, the system can combine the existing power configuration scheme to evaluate the effectiveness and applicability of various energy consumption modes under different environmental conditions and generate a preliminary energy consumption evaluation report.

[0093] For example, in the Fangcang shelter hospital, the adaptive fuzzy logic control system evaluated whether the current air conditioning system settings were reasonable based on the collected data, such as the changing trends of temperature and humidity in the ward and the patients' feedback on the environment. The system found that during certain time periods, the air conditioning set points were too high, resulting in energy waste and patient discomfort. Based on this, the system made recommendations to adjust the air conditioning set points and generated a preliminary energy consumption assessment report containing these findings.

[0094] Step 403: performing precision correction on the preliminary energy consumption assessment report through an integrated learning algorithm to improve the accuracy of energy consumption pattern matching and obtain a corrected energy consumption assessment report;

[0095] In this step, the ensemble learning algorithm is a machine learning method that improves the accuracy and robustness of the overall prediction by combining the prediction results of multiple models. Here, the ensemble learning algorithm is used to further analyze and correct the data in the preliminary energy consumption assessment report, thereby improving the match between the energy consumption pattern and the actual demand, and finally generating a more accurate energy consumption assessment report.

[0096] For example, the preliminary energy consumption assessment report of the shelter hospital was reanalyzed using a variety of ensemble learning algorithms such as random forests and gradient boosting machines. By comparing the results of different algorithms, it was found that there were deviations in the estimated energy consumption patterns in some areas. After correction, the new energy consumption assessment report provided more accurate energy consumption pattern recommendations, especially in terms of energy consumption management at night and in the early morning.

[0097] Step 404: Apply a genetic algorithm to optimize the energy consumption patterns of different areas in the shelter hospital based on the corrected energy consumption assessment report to obtain optimization suggestions;

[0098] In this step, the genetic algorithm is an optimization algorithm that simulates the natural selection process and iteratively searches for the optimal solution to the problem. In this step, the genetic algorithm will optimize the energy consumption pattern of each area in the shelter hospital based on the corrected energy consumption assessment report to find the best energy consumption allocation strategy, thereby reducing unnecessary energy consumption.

[0099] For example, genetic algorithms are applied to optimize the energy consumption patterns of different functional areas of square cabin hospitals, such as wards, operating rooms, and public rest areas. For example, through the optimization algorithm, it is determined that solar power should be used first during peak hours during the day, and more reliance should be placed on energy storage system discharge during off-peak hours. These recommendations are aimed at maximizing the use of renewable energy while ensuring a stable power supply for critical medical facilities.

[0100] Step 405: According to the optimization suggestions, combined with the flow of personnel and time distribution in the square cabin hospital, the energy consumption allocation ratio of each area is dynamically adjusted by using the situation-awareness algorithm, and an optimized energy consumption allocation plan is formulated;

[0101] In this step, the situational awareness algorithm can automatically adjust decisions based on changes in conditions in specific scenarios. In this step, the situational awareness algorithm will take into account the flow of people and time distribution patterns in the shelter hospital, and dynamically adjust the energy consumption allocation ratio of each area to meet the actual needs of different time periods, thereby formulating a more flexible and efficient energy consumption allocation plan.

[0102] For example, based on the optimization suggestions, combined with the entry and exit records of people in the shelter hospital and the schedule of daily activities, the situational awareness algorithm dynamically adjusted the energy consumption distribution of each area. For example, during the period when there are more patients, the ventilation and lighting intensity of the public areas are increased; at night or when there are fewer people, the energy consumption of these areas is appropriately reduced to save electricity.

[0103] Step 406: Using digital twin technology, simulate and test the optimized energy consumption allocation plan to generate an energy consumption control strategy;

[0104] In this step, digital twin technology is a technology that simulates and analyzes by creating virtual copies of physical entities. In this stage, digital twin technology is used to build a virtual model of the shelter hospital and test the optimized energy allocation plan in it. Through simulation testing, the effectiveness of the plan can be verified and necessary adjustments can be made, ultimately generating a complete set of energy consumption control strategies.

[0105] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0106] Environmental sensing sensors are used to monitor the internal environmental parameters of the Fangcang Hospital, the working characteristics of the power units, and the comfort requirements of patients to obtain a comprehensive data set. The adaptive fuzzy logic control system analyzes these data, evaluates the applicability of energy consumption patterns under different conditions, and generates a preliminary energy consumption assessment report. The integrated learning algorithm further corrects the report accuracy and improves the accuracy of energy consumption pattern matching. The genetic algorithm optimizes the energy consumption pattern design in different areas and provides specific optimization suggestions. The scenario perception algorithm combines the flow of personnel and the time distribution rules to dynamically adjust the energy consumption allocation ratio and formulate an optimized energy consumption allocation plan. Digital twin technology performs simulation tests to generate the final energy consumption control strategy. These steps significantly improve the accuracy and flexibility of energy consumption management, ensure patient comfort, reduce energy waste, and improve overall operational efficiency.

[0107] Based on this, the present invention provides a specific embodiment, in which step 405, according to the optimization suggestion, combined with the flow of personnel and time distribution in the square cabin hospital, uses a situation-aware algorithm to dynamically adjust the energy consumption allocation ratio of each area and formulate an optimized energy consumption allocation plan, which specifically includes the following steps:

[0108] Step 411: using the spatiotemporal prediction model, performing trend prediction on the personnel flow in the preliminary energy consumption allocation plan to obtain a personnel flow prediction result;

[0109] In this step, the spatiotemporal prediction model is a prediction method that combines time series analysis and spatial distribution characteristics. It not only considers the trend of data changes over time, but also considers the mutual influence between different locations. In this step, the spatiotemporal prediction model is used to predict the flow of people in different time periods and different areas in the Fangcang Hospital, thereby helping to understand future activity patterns.

[0110] For example, in a square cabin hospital, historical traffic data is collected by crowd counters and cameras installed at the entrance, and a spatiotemporal prediction model is constructed by combining information from the patient reservation system. The model can predict the number of patients arriving at different times of the day in the next week and their stay time in various areas, such as ward areas and treatment areas. For example, the model may predict that 9:00 a.m. to 11:00 a.m. is the peak time for patients to visit, while the flow of people gradually decreases after 3:00 p.m.

[0111] Step 412: Based on the personnel flow prediction result, the energy consumption demand changes of each area in different time periods are analyzed by a machine learning algorithm to generate a dynamic energy consumption demand prediction;

[0112] In this step, machine learning algorithms can learn patterns from large amounts of data and make predictions. Based on the results of the personnel flow prediction, machine learning algorithms can further analyze the changes in energy demand in various areas over different time periods to generate a dynamic energy demand forecast. This helps to more accurately estimate energy consumption in the future.

[0113] For example, machine learning algorithms such as support vector machines or random forests can be used to train the historical energy consumption data and predicted personnel flow data of shelter hospitals. For example, if the model finds that the energy consumption of the air conditioning system increases whenever the number of patients increases, the air conditioning settings can be adjusted in advance to adapt to higher energy consumption requirements when a large number of patients are expected to arrive. Ultimately, the generated dynamic energy demand forecast can help managers better plan power supply.

[0114] Step 413: combining the dynamic energy demand forecast with the preliminary energy consumption allocation plan, and using a multi-objective optimization algorithm to re-evaluate the energy consumption allocation ratio of each area, so as to optimize energy use while meeting the needs of personnel flow, and generate a re-optimized energy consumption allocation plan;

[0115] In this step, the multi-objective optimization algorithm aims to optimize multiple objective functions simultaneously, such as minimizing cost, maximizing efficiency, etc. In this step, the multi-objective optimization algorithm combines the dynamic energy demand forecast with the preliminary energy consumption allocation plan, and re-evaluates the energy consumption allocation ratio of each area to ensure that the needs of personnel flow are met while maximizing energy conservation.

[0116] For example, suppose that the preliminary energy allocation plan has determined the basic energy configuration for each area. Combined with the dynamic energy demand forecast, the multi-objective optimization algorithm recalculates the optimal energy ratio for each area. For example, during the time period when the number of patients is expected to be high, the lighting and ventilation intensity of the public areas may be increased; while when there are fewer patients, the energy consumption of these areas is reduced. In this way, the optimized solution can achieve the optimization of energy use while ensuring the quality of service.

[0117] Step 414: using augmented reality technology and combining the re-optimized energy consumption allocation plan, an energy consumption management interface is provided for the managers of the Fangcang hospital, supporting real-time monitoring and manual intervention, and generating an optimized energy consumption allocation plan;

[0118] In this step, augmented reality (AR) technology can overlay virtual information onto the real world, allowing users to intuitively see and interact. In this step, AR technology is used to create an energy consumption management interface that allows managers to view energy consumption in real time and make manual adjustments as needed. This visualization tool improves management efficiency and promotes more flexible energy management strategies.

[0119] For example, an AR-based mobile application was developed that can display the real-time energy consumption status of various areas of the Fangcang Hospital. Managers can scan a specific area through the camera on a smartphone or tablet, and the screen will display the current energy consumption level, temperature, humidity and other information of the area, as well as recommended energy consumption adjustment suggestions. In addition, managers can also operate directly on the interface, such as adjusting the air conditioning temperature or changing the lighting brightness, to achieve instant manual intervention. Such an interface not only provides real-time data feedback, but also enhances the transparency and controllability of the decision-making process.

[0120] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0121] The spatiotemporal prediction model is used to predict the trend of personnel flow in the shelter hospital, and the machine learning algorithm is used to analyze the changes in energy demand in each area in different time periods to generate a dynamic energy demand forecast. The multi-objective optimization algorithm comprehensively evaluates and adjusts the energy allocation ratio of each area to ensure that energy use is optimized while meeting the needs of personnel flow, and generates a re-optimized energy allocation plan. Augmented reality technology provides managers with an intuitive energy management interface, supports real-time monitoring and manual intervention, and ultimately generates an optimized energy allocation plan. These steps significantly improve the accuracy and flexibility of energy management, enhance the response speed and efficiency of the system, reduce energy waste, and improve patient comfort and operational management.

[0122] Based on this, the present invention provides a specific embodiment, in which step 406, according to the optimization suggestion, combined with the flow of personnel and time distribution in the square cabin hospital, uses a situation-aware algorithm to dynamically adjust the energy consumption allocation ratio of each area and formulate an optimized energy consumption allocation plan, which specifically includes the following steps:

[0123] Step 421: using digital twin technology to perform simulation testing on the optimized energy consumption allocation plan to obtain simulation test results;

[0124] In this step, digital twin technology is a technology that simulates the behavior of physical entities by creating virtual copies of them. In this step, digital twins are used to build an accurate virtual model of the shelter hospital and its internal systems in order to test the optimized energy consumption allocation plan without actual operation. Through simulation testing, the performance of the plan under different conditions can be evaluated and data can be collected for further analysis.

[0125] Step 422: simulating the application effect of the simulation test result under different environmental conditions through a virtual simulation platform to generate energy consumption performance data under various environmental conditions;

[0126] In this step, the virtual simulation platform is a software tool used to simulate real-world conditions, which allows users to change input parameters and observe the changes in output results. Here, the virtual simulation platform is used to simulate the application effect of the optimized energy consumption allocation plan under different environmental conditions, such as different weather conditions, seasonal changes, etc., thereby generating a series of energy consumption performance data.

[0127] For example, based on the digital twin model established above, a virtual simulation platform was used to simulate the impact of different seasons and weather conditions on the energy consumption of shelter hospitals. For example, in hot summer weather, the air conditioning system requires more electricity to maintain a comfortable indoor temperature; in winter, heating needs may need to be considered. Through these simulations, energy consumption performance data under different environmental conditions were generated, including key indicators such as hourly energy consumption and peak load.

[0128] Step 423: Apply big data analysis technology to process the energy consumption performance data, identify key factors affecting energy consumption efficiency and their degree of influence, and form a key factor impact report;

[0129] In this step, big data analysis technology refers to the process of extracting valuable information from large and complex data sets. In this step, big data analysis technology is used to process the energy consumption performance data generated by virtual simulation, with the aim of finding out which factors have a significant impact on energy efficiency and quantifying the impact of these factors. Finally, a detailed report on the impact of key factors will be formed.

[0130] Step 424: In combination with the key factor impact report, the optimized energy consumption allocation plan is optimized using a deep learning algorithm to generate an optimized energy consumption control strategy draft;

[0131] In this step, the deep learning algorithm is a machine learning method that can automatically learn features and make predictions from large amounts of data. At this stage, the deep learning algorithm combines the information in the key factor impact report to further optimize the existing energy consumption allocation plan to generate a more efficient and more adaptable draft energy consumption control strategy for actual environmental changes.

[0132] For example, based on the findings in the key factor impact report, the energy consumption allocation plan was re-optimized using a deep neural network. For example, in response to changes in outdoor temperature, the algorithm automatically generated a strategy for dynamically adjusting the air conditioning set point; for personnel flow patterns, the algorithm designed an intelligent lighting control system to reduce unnecessary energy waste. Ultimately, an optimized energy consumption control strategy draft was formed, ready to enter the next stage of verification.

[0133] Step 425: applying a real-time feedback mechanism, comparing and analyzing the actual operation data with the optimized energy consumption control strategy draft, dynamically adjusting the parameter settings in the energy consumption control strategy draft, and obtaining the optimal energy consumption control strategy draft;

[0134] In this step, the real-time feedback mechanism refers to the process of continuously collecting data during system operation and adjusting system parameters in real time based on this data. In this step, by comparing the actual operation data with the optimized energy consumption control strategy draft, the parameter settings in the draft are continuously adjusted until the best energy consumption control solution is found.

[0135] For example, in the actual operation of the Fangcang Hospital, various sensors are installed to collect real-time energy consumption data. These data are transmitted to the central control system and compared with the optimized draft energy consumption control strategy. If it is found that the actual energy consumption in some areas is higher than expected, the system will automatically adjust the relevant parameters, such as lowering the air conditioning temperature or reducing the lighting brightness. After a period of operation and adjustment, a more accurate and efficient draft energy consumption control strategy was finally obtained.

[0136] More specifically, the present invention also provides a formula, which is optimized using the following formula:

[0137] P opt =α·E pred +β·C env +γ·F sys +δ·T real +η·H hist +θ·W weather

[0138] +λ·M maint

[0139] Among them, P opt Indicates the optimized parameter setting value, which is used to adjust the specific parameters in the energy consumption control strategy draft; E pred represents the energy demand forecast value, which is the preliminary power demand forecast result generated by the time series forecasting model; C env Indicates the environmental condition impact value, based on the degree of environmental factor impact identified in the key factor impact report; F sys represents the system performance factor, based on the system performance indicators evaluated in the simulation test report; T real Indicates actual operation data, which is obtained through the real-time feedback mechanism and is used to dynamically adjust parameter settings; H hist Represents historical electricity consumption data, which is used to predict electricity consumption patterns based on historical electricity consumption records; W weather Represents weather forecast information, which is used to adjust energy consumption control strategies based on weather forecast data; M maintIt represents the impact value of the maintenance plan, which is based on the preventive maintenance plan and is used to consider the impact of maintenance on energy consumption; α represents the weight coefficient of the energy demand forecast value, which reflects the importance of energy demand forecast in parameter optimization; β represents the weight coefficient of the environmental condition impact value, which reflects the importance of environmental factors in parameter optimization; γ represents the weight coefficient of the system performance factor, which reflects the importance of system performance in parameter optimization; δ represents the weight coefficient of the actual operation data, which reflects the importance of the actual operation data in parameter optimization; η represents the weight coefficient of the historical electricity consumption data, which reflects the importance of the historical electricity consumption data in parameter optimization; θ represents the weight coefficient of the weather forecast information, which reflects the importance of the weather forecast in parameter optimization; λ represents the weight coefficient of the maintenance plan impact value, which reflects the importance of the maintenance plan in parameter optimization.

[0140] Step 426: using visualization technology to display the implementation effect of the optimal energy consumption control strategy, and completing the formulation of the energy consumption control strategy;

[0141] In this step, visualization technology is a technology that converts data into graphical or image representations, which can help users understand and analyze complex information more easily. In this final step, visualization technology is used to show the implementation effect of the optimal energy consumption control strategy, allowing managers to intuitively see the benefits of the strategy, thus completing the entire energy consumption control strategy formulation process.

[0142] For example, a web-based visualization platform has been developed that can display the real-time energy consumption of each area of ​​the Fangcang Hospital, historical energy consumption trends, and the energy-saving effects brought about by the optimized energy consumption control strategy. Managers can view the energy consumption distribution of each area in the form of charts, heat maps, etc., and can also view the specific values ​​of energy savings in a specific time period. In addition, the platform also provides an interactive interface that allows users to select different time periods and areas for in-depth analysis. In this way, not only management efficiency is improved, but also the transparency and support of decision-making are enhanced.

[0143] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0144] Through digital twin technology and virtual simulation platform, the optimized energy consumption allocation plan of the shelter hospital is simulated and tested, and the application effect under multiple environmental conditions is simulated to generate detailed energy consumption performance data. Big data analysis technology identifies the key factors affecting energy efficiency and their degree of influence, and forms a key factor impact report. Combined with the report, the energy consumption allocation plan is further optimized using deep learning algorithms to generate a draft energy consumption control strategy. The real-time feedback mechanism compares the actual operating data with the draft, dynamically adjusts the parameter settings, and ensures the formulation of the best energy consumption control strategy. These steps significantly improve the accuracy and adaptability of energy consumption management, reduce energy waste, and improve the stability and reliability of the system. At the same time, visualization technology is used to enhance management transparency and decision support.

[0145] Based on this, the present invention provides a specific embodiment, wherein the step 102 uses a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy, and specifically includes the following steps:

[0146] Step 201: using a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain a preliminary charging and discharging optimization plan;

[0147] In this step, the multi-objective optimization algorithm is a mathematical optimization method that aims to optimize multiple objective functions simultaneously, such as minimizing cost, maximizing efficiency, etc. In this step, the multi-objective optimization algorithm is used to evaluate the current state of the energy storage system and dynamically adjust the strategy to find a charging and discharging plan that can meet the power demand while optimizing the battery life and economy.

[0148] Step 202: Optimize the preliminary charge and discharge optimization plan through a machine learning algorithm, calculate the battery health status, charge and discharge efficiency and cost factors, and generate a detailed charge and discharge optimization plan;

[0149] In this step, the machine learning algorithm can learn patterns from a large amount of historical data and make predictions and decisions based on these patterns. In this step, the machine learning algorithm further optimizes the preliminary charge and discharge plan and generates a more detailed and efficient charge and discharge optimization plan by analyzing the battery health status, charge and discharge efficiency, and cost factors.

[0150] Step 203: Using the Internet of Things technology, real-time monitoring is performed on the operating status of the energy storage system in the detailed charge-discharge optimization scheme to generate real-time monitoring data;

[0151] In this step, IoT technology connects various devices and sensors to achieve real-time data collection and transmission. In this step, IoT technology is used to continuously monitor the operating status of the energy storage system, including key parameters such as battery voltage, current, and temperature, to ensure that the system works as expected and provide real-time data to support subsequent analysis and adjustments.

[0152] Step 204: Based on the real-time monitoring data, a predictive maintenance algorithm is used to predict potential failure points of the energy storage system and generate a preventive maintenance plan;

[0153] In this step, the predictive maintenance algorithm is a data analysis-based method that can identify possible equipment failures in advance and take measures to prevent them. In this step, the predictive maintenance algorithm uses real-time monitoring data to analyze the operating trends of the energy storage system, predict possible failures, and formulate preventive maintenance plans based on this to reduce downtime and repair costs.

[0154] Step 205: In combination with the preventive maintenance plan, the detailed charge-discharge optimization plan is adjusted in real time using a dynamic adjustment algorithm to generate a target charge-discharge optimization strategy;

[0155] In this step, the dynamic adjustment algorithm is an algorithm that can automatically adjust the strategy according to the actual situation during operation. In this step, the dynamic adjustment algorithm combines the preventive maintenance plan to make real-time adjustments to the existing detailed charging and discharging optimization plan to ensure that the energy storage system can maintain efficient operation while also coping with possible failure risks, thereby generating the final target charging and discharging optimization strategy.

[0156] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0157] The energy consumption performance data under various environmental conditions are processed through big data analysis technology to generate a preliminary list of key factors. The association rule mining algorithm is used to deeply analyze these factors and form a key factor interaction matrix. The multi-dimensional data analysis method evaluates the impact of different key factor combinations and generates a comprehensive impact assessment table. Combining these results, the machine learning algorithm establishes an energy efficiency prediction model and draws a trend chart of energy efficiency changes. Finally, it is integrated into a key factor impact report. These steps significantly improve the understanding and management of energy consumption influencing factors, enhance the accuracy of energy consumption forecasts, optimize energy use efficiency, reduce operating costs, and provide scientific data support and decision-making basis for the energy consumption management of Fangcang Hospital.

[0158] Based on this, the present invention provides a specific embodiment, wherein the step 105 combines historical electricity consumption data with weather forecast information, applies a time series prediction model to the energy consumption control strategy to predict the trend of electricity demand changes, obtains a scheduling plan for distributed power sources and energy storage systems, uses blockchain technology to record and verify the electricity trading process of the scheduling plan, and generates an electricity distribution plan, specifically including the following steps:

[0159] Step 501: combining historical electricity consumption data with weather forecast information, applying a time series prediction model to predict the trend of electricity demand changes for the energy consumption control strategy, and obtaining a preliminary electricity demand prediction result;

[0160] In this step, the time series forecasting model is a method to predict the data change trend in a certain period of time in the future based on historical data. In this step, by combining the historical electricity consumption data of the Fangcang Hospital and future weather forecast information, the trend of electricity demand change in the future period of time can be predicted. These forecast results will serve as the basis for formulating energy consumption control strategies.

[0161] Step 502: Analyze the preliminary power demand forecast results using a deep learning algorithm, calculate the impact of holidays and special events, and generate a detailed power demand forecast report;

[0162] In this step, the deep learning algorithm is a complex machine learning method that can automatically extract features from large amounts of data and make predictions. In this step, the deep learning algorithm is used to further analyze the preliminary power demand forecast results, especially considering the impact of holidays and special events on power demand, so as to generate a more detailed and accurate power demand forecast report.

[0163] Step 503: Based on the detailed power demand forecast report, a multi-objective optimization algorithm is used to optimize the scheduling plan of the distributed power source and the energy storage system to generate an optimized scheduling plan;

[0164] In this step, the multi-objective optimization algorithm aims to optimize multiple objective functions simultaneously, such as minimizing cost, maximizing efficiency, etc. In this step, the multi-objective optimization algorithm optimizes the scheduling planning of distributed power generation and energy storage systems based on the refined power demand forecast report to ensure that economic benefits are maximized and environmental impact is minimized while meeting power demand.

[0165] Step 504: Through the simulation test platform, simulate and verify the optimized scheduling plan, evaluate the feasibility under different scenarios, and generate a simulation test report;

[0166] In this step, the simulation test platform is a tool used to simulate real-world situations, which allows users to change input parameters and observe changes in output results. In this step, the simulation test platform is used to verify the feasibility and effectiveness of the optimized scheduling plan in different scenarios, thereby generating a detailed simulation test report.

[0167] Step 505: In combination with the simulation test report, the optimized scheduling plan is dynamically adjusted by using a real-time feedback mechanism to generate an optimal scheduling plan;

[0168] In this step, the real-time feedback mechanism refers to the process of continuously collecting data during system operation and adjusting system parameters in real time based on this data. In this step, by comparing the simulation test report with the actual operation data, the optimized scheduling plan is continuously adjusted until the best solution is found.

[0169] Step 506: Using blockchain technology, record and verify the power transaction process of the optimal scheduling plan to generate a power distribution plan;

[0170] The embodiments of the present invention can achieve the following beneficial effects through the above steps:

[0171] By combining multi-objective optimization algorithms with machine learning technology, the charging and discharging strategies of energy storage systems are carefully designed and optimized, taking into account factors such as battery health, efficiency, and cost, and using IoT technology to achieve real-time monitoring of the operating status of energy storage systems. Based on the collected data, predictive maintenance algorithms are used to effectively predict potential failure points and develop preventive maintenance plans, further ensuring the stability and reliability of the system. This comprehensive approach significantly improves the management efficiency of energy storage systems, extends equipment life, reduces operation and maintenance costs, and enhances the flexibility and sustainability of energy use, laying a solid foundation for building a more intelligent and efficient energy management system.

[0172] By combining historical electricity consumption data with weather forecast information, applying time series prediction models and deep learning algorithms, the accuracy of power demand forecasting has been significantly improved, providing a solid data foundation for energy consumption control in Fangcang Hospital. Multi-objective optimization algorithms and real-time feedback mechanisms ensure the optimal scheduling of distributed power sources and energy storage systems, reduce energy waste, reduce operating costs, and enhance the stability and reliability of the system. Detailed power demand forecast reports and simulation test reports provide managers with detailed information support, improving the scientificity and quality of decision-making. In addition, the dynamic adjustment mechanism enables the system to flexibly respond to changes in actual operation and further optimize resource allocation. Overall, these steps not only improve the efficiency and economy of power supply, but also enhance the adaptability and stability of the system, ensuring the efficient operation of Fangcang Hospital under various conditions.

[0173] Figure 2 A structural diagram of a square cabin hospital power supply optimization system based on microgrid technology is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0174] The monitoring module 21 monitors the actual power demand of each power consumption unit in the square cabin hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and uses a deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources;

[0175] An evaluation module 22 uses a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy;

[0176] The adjustment module 23, when an external power grid fault is detected, adopts a fast switching control algorithm to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration solution in the island mode;

[0177] The adjustment module 24 uses an adaptive fuzzy logic control system to adjust the power configuration scheme according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power consumption unit and the patient comfort requirements to obtain an energy consumption control strategy;

[0178] The recording module 25 combines historical electricity consumption data with weather forecast information, applies a time series prediction model to predict the trend of electricity demand changes for the energy consumption control strategy, obtains a scheduling plan for distributed power sources and energy storage systems, and uses blockchain technology to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

[0179] Figure 2 The power supply optimization system for square cabin hospitals based on microgrid technology can be implemented Figure 1 The implementation principle and technical effect of the square cabin hospital power supply optimization method based on microgrid technology described in the embodiment shown will not be repeated. The specific way in which each module and unit performs operations in the square cabin hospital power supply optimization system based on microgrid technology in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0180] Figure 2 The illustrated embodiment of a modular hospital power supply optimization system based on microgrid technology 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;

[0181] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0182] The processing component 32 is used to monitor the actual power demand of each power unit in the square cabin hospital, the operating status of the current power supply system and the status information of the external power grid to obtain monitoring data, and use the deep reinforcement learning algorithm to analyze the monitoring data to obtain the dynamic adjustment strategy of the distributed power source; use the multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current status of the energy storage system to obtain the charging and discharging optimization strategy of the energy storage system; when an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain the power configuration plan under the island mode; according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power unit and the patient comfort requirements, the adaptive fuzzy logic control system is used to adjust the power configuration plan to obtain the energy consumption control strategy; combined with historical power consumption data and weather forecast information, the time series prediction model is used to predict the power demand change trend of the energy consumption control strategy to obtain the scheduling plan of the distributed power source and the energy storage system, and the blockchain technology is used to record and verify the power trading process of the scheduling plan to generate a power distribution plan.

[0183] The processing component 32 includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (AICs), 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 method.

[0184] The 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 memory, flash memory, magnetic disk or optical disk.

[0185] Computing devices also include other components, such as input / output interfaces, display components, and communication components.

[0186] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device or an input device.

[0187] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0188] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0189] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The embodiment shown monitors the actual power demand of each power unit in the square cabin hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and uses a deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources; uses a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current status of the energy storage system to obtain an energy storage system charging and discharging optimization strategy; when an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the energy storage system charging and discharging optimization strategy to obtain a power supply configuration plan under island mode; according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power unit, and the patient comfort requirements, an adaptive fuzzy logic control system is used to adjust the power supply configuration plan to obtain an energy consumption control strategy; combined with historical power consumption data and weather forecast information, a time series prediction model is used to predict the power demand change trend of the energy consumption control strategy to obtain a scheduling plan for distributed power sources and energy storage systems, and blockchain technology is used to record and verify the power trading process of the scheduling plan to generate a power distribution plan method and system.

[0190] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0191] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0192] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing power supply for shelter hospitals based on microgrid technology, characterized in that: include: Monitor the actual power demand of each power-consuming unit in the Fangcang Hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and use the deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources; A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy; When an external power grid fault is detected, a fast switching control algorithm is used to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration solution in the island mode; According to the internal environmental parameters of the Fangcang Hospital, the working characteristics of the power consumption units and the comfort requirements of the patients, the adaptive fuzzy logic control system is used to adjust the power configuration scheme to obtain the energy consumption control strategy; Combining historical electricity consumption data with weather forecast information, the time series prediction model is applied to predict the trend of electricity demand changes for the energy consumption control strategy, and the scheduling plan of distributed power sources and energy storage systems is obtained. The blockchain technology is used to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

2. The method according to claim 1, characterized in that According to the internal environmental parameters of the Fangcang Hospital, the working characteristics of the power consumption units and the comfort requirements of the patients, the adaptive fuzzy logic control system is used to adjust the power configuration scheme to obtain the energy consumption control strategy, including: Use environmental perception sensors to monitor the internal environmental parameters of the shelter hospital, the working characteristics of the power units, and the comfort requirements of patients to obtain the environmental and demand data sets; Analyzing the environment and demand data sets by using an adaptive fuzzy logic control system, and evaluating the applicability of energy consumption modes under different conditions in combination with the power configuration scheme to obtain a preliminary energy consumption evaluation report; The preliminary energy consumption assessment report is precision-corrected by an integrated learning algorithm to improve the accuracy of energy consumption pattern matching and obtain a corrected energy consumption assessment report; Applying a genetic algorithm, based on the corrected energy consumption assessment report, optimizes the energy consumption patterns of different areas in the shelter hospital and obtains optimization suggestions; According to the optimization suggestions, combined with the flow of people and time distribution patterns in the Fangcang Hospital, the scenario-aware algorithm is used to dynamically adjust the energy consumption allocation ratio of each area and formulate an optimized energy consumption allocation plan; The digital twin technology is used to simulate and test the optimized energy consumption allocation plan to generate an energy consumption control strategy.

3. The method according to claim 2, characterized in that According to the optimization suggestions, combined with the flow of people and time distribution in the Fangcang Hospital, the scenario-aware algorithm is used to dynamically adjust the energy consumption allocation ratio of each area and formulate an optimized energy consumption allocation plan, including: Using the spatiotemporal prediction model, the trend of personnel flow in the preliminary energy consumption allocation plan is predicted to obtain the personnel flow prediction results; Based on the personnel flow prediction results, the energy demand changes in each area in different time periods are analyzed by machine learning algorithms to generate dynamic energy demand predictions; The dynamic energy demand forecast is combined with the preliminary energy consumption allocation plan, and the energy consumption allocation ratio of each area is evaluated again using a multi-objective optimization algorithm, so as to optimize energy use while meeting the needs of personnel flow, and generate a re-optimized energy consumption allocation plan; By using augmented reality technology and combining it with the re-optimized energy consumption allocation plan, an energy consumption management interface is provided to the managers of the Fangcang Cabin Hospital, which supports real-time monitoring and manual intervention and generates an optimized energy consumption allocation plan.

4. The method according to claim 2, characterized in that: Using digital twin technology, the optimized energy consumption allocation plan is simulated and tested to generate an energy consumption control strategy, including: Using digital twin technology, a simulation test is performed on the optimized energy consumption allocation plan to obtain a simulation test result; Through the virtual simulation platform, the application effects of the simulation test results under different environmental conditions are simulated to generate energy consumption performance data under various environmental conditions; Apply big data analysis technology to process the energy consumption performance data, identify key factors affecting energy efficiency and their degree of influence, and form a key factor impact report; In combination with the key factor impact report, the optimized energy consumption allocation plan is optimized using a deep learning algorithm to generate an optimized energy consumption control strategy draft; Applying a real-time feedback mechanism, comparing and analyzing the actual operation data with the optimized draft energy consumption control strategy, dynamically adjusting the parameter settings in the draft energy consumption control strategy, and obtaining the optimal draft energy consumption control strategy; By using visualization technology, the implementation effect of the optimal energy consumption control strategy is displayed to complete the formulation of the energy consumption control strategy.

5. The method according to claim 4, characterized in that Apply big data analysis technology to process the energy consumption performance data, identify the key factors affecting energy efficiency and their degree of influence, and form a key factor impact report, including: Using big data analysis technology to process energy consumption performance data under various environmental conditions, a preliminary list of key factors is obtained, wherein the various environmental conditions include: climate conditions, time period, personnel density, equipment operation status, and hospital emergencies; Using an association rule mining algorithm to deeply analyze the factors in the preliminary key factor list to obtain a key factor interaction matrix; Based on the key factor interaction matrix, a multi-dimensional data analysis method is used to evaluate the impact of different key factor combinations to obtain a comprehensive impact assessment table; In combination with the comprehensive impact assessment table, an energy consumption efficiency prediction model is established using a machine learning algorithm to obtain an energy consumption efficiency change trend graph; The preliminary key factor list, key factor interaction matrix, comprehensive impact assessment table and energy efficiency change trend chart are integrated to form a key factor impact report.

6. The method according to claim 1, characterized in that A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy, including: A multi-objective optimization algorithm is used to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain a preliminary charging and discharging optimization plan; Optimizing the preliminary charge and discharge optimization plan through a machine learning algorithm, calculating the battery health status, charge and discharge efficiency, and cost factors, and generating a detailed charge and discharge optimization plan; Using the Internet of Things technology, the operating status of the energy storage system in the detailed charging and discharging optimization scheme is monitored in real time to generate real-time monitoring data; Based on the real-time monitoring data, a predictive maintenance algorithm is used to predict potential failure points of the energy storage system and generate a preventive maintenance plan; In combination with the preventive maintenance plan, a dynamic adjustment algorithm is used to adjust the detailed charge and discharge optimization plan in real time to generate a target charge and discharge optimization strategy.

7. The method according to claim 1, characterized in that Combining historical electricity consumption data with weather forecast information, the time series prediction model is applied to the energy consumption control strategy to predict the trend of electricity demand changes, and the scheduling plan of distributed power supply and energy storage system is obtained. The scheduling plan is recorded and verified by blockchain technology to generate a power distribution plan, including: Combining historical electricity consumption data with weather forecast information, applying a time series forecasting model to predict the trend of electricity demand changes for the energy consumption control strategy, and obtaining preliminary electricity demand forecasting results; Analyze the preliminary power demand forecast results using a deep learning algorithm, calculate the impact of holidays and special events, and generate a detailed power demand forecast report; Based on the detailed power demand forecast report, the dispatch plan of the distributed power source and energy storage system is optimized by using a multi-objective optimization algorithm to generate an optimized dispatch plan; Through the simulation test platform, the optimized scheduling plan is simulated and verified, the feasibility under different scenarios is evaluated, and a simulation test report is generated; In combination with the simulation test report, the optimized scheduling plan is dynamically adjusted by using a real-time feedback mechanism to generate an optimal scheduling plan; Blockchain technology is used to record and verify the power trading process of the optimal scheduling plan and generate a power distribution plan.

8. A power supply optimization system for square cabin hospitals based on microgrid technology, characterized in that: include: The monitoring module monitors the actual power demand of each power-consuming unit in the square cabin hospital, the operating status of the current power supply system, and the status information of the external power grid to obtain monitoring data, and uses a deep reinforcement learning algorithm to analyze the monitoring data to obtain a dynamic adjustment strategy for distributed power sources; An evaluation module, which uses a multi-objective optimization algorithm to comprehensively evaluate the dynamic adjustment strategy and the current state of the energy storage system to obtain an energy storage system charging and discharging optimization strategy; The adjustment module, when an external power grid fault is detected, uses a fast switching control algorithm to adaptively adjust the charging and discharging optimization strategy of the energy storage system to obtain a power configuration plan under the island mode; The adjustment module uses an adaptive fuzzy logic control system to adjust the power configuration scheme according to the internal environmental parameters of the square cabin hospital, the working characteristics of the power consumption unit and the patient comfort requirements, and obtains an energy consumption control strategy; The recording module combines historical electricity consumption data with weather forecast information, applies a time series prediction model to predict the trend of electricity demand changes for the energy consumption control strategy, obtains the scheduling plan of distributed power sources and energy storage systems, and uses blockchain technology to record and verify the electricity trading process of the scheduling plan to generate a power distribution plan.

9. A computing device, characterized in that It includes 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 to implement a power supply optimization method for a cabin hospital based on microgrid technology as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a power supply optimization method for a square cabin hospital based on microgrid technology as described in any one of claims 1 to 7 is implemented.

Images