Stabilization method and system for hybrid power supply of shelter nucleic acid laboratory

Abstract

The invention provides a stabilization method for hybrid power supply of a shelter nucleic acid laboratory, and the method comprises the steps: collecting environment parameters, power consumption and renewable energy power generation data in real time through sensors disposed inside and outside the shelter nucleic acid laboratory; a power demand peak value and renewable energy potential are predicted by using deep learning, a charge and discharge plan is optimized by using a genetic algorithm, and a dynamic energy management strategy is formed. When it is detected that the external power grid is unstable, an emergency response mechanism is started, the energy storage system and the standby generator are switched to jointly supply power, the power source proportion is adjusted through reinforcement learning, and an energy configuration scheme is generated. The fuzzy logic control system dynamically adjusts the equipment state, and intelligent energy saving of non-key equipment is achieved. And the block chain records the implementation process of the control strategy and generates an energy management log. And machine learning evaluation logs, and proposing power supply strategy optimization suggestions. According to the scheme, the stability and reliability of power supply are ensured, the energy utilization efficiency is optimized, and the operation cost is reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of power supply for nucleic acid laboratories, and in particular to a stabilizing method for hybrid power supply for modular nucleic acid laboratories. Background Art

[0002] As a temporary, rapidly deployed medical facility, Fangcang nucleic acid laboratory places extremely high demands on the stability and reliability of power supply. The laboratory must ensure stable power supply under any circumstances, efficiently manage power resources, reduce energy waste, and be able to quickly switch to backup power supply in the event of external power grid instability or emergencies to ensure the continuity of testing work.

[0003] At present, the hybrid power supply system of Fangcang nucleic acid laboratory mainly adopts multi-source power supply, fixed power supply strategy and manual switching. These schemes ensure the stability and reliability of power supply by combining external power grid, energy storage system and renewable energy, as well as pre-set charging and discharging plans. However, these schemes have obvious limitations in practical application.

[0004] Existing hybrid power supply solutions rely on static predictions and fixed models, which cannot effectively respond to emergencies and dynamically changing environments, resulting in insufficient power supply or excessive waste. The manual switching method has a long response time and complex operation, which may cause power outages at critical moments. In addition, the lack of intelligent management and comprehensive data recording and analysis makes energy utilization inefficient and difficult to detect and optimize power supply bottlenecks in a timely manner. Summary of the invention

[0005] The embodiment of the present invention provides a stabilization method and system for hybrid power supply of a modular nucleic acid laboratory, which is used to solve the problems in the prior art that rely on static predictions and fixed models, cannot effectively respond to emergencies and dynamically changing environments, and lead to insufficient or excessive waste of power supply. The manual switching method has a long response time and complex operation, which may cause power outages at critical moments. In addition, it lacks intelligent management and comprehensive data recording and analysis, resulting in low energy utilization efficiency and difficulty in timely discovery and optimization of power supply bottlenecks.

[0006] In a first aspect, an embodiment of the present invention provides a method for stabilizing hybrid power supply for a nucleic acid laboratory in a shelter, comprising:

[0007] Using a variety of sensors installed inside and outside the modular nucleic acid laboratory, environmental parameters, power consumption data, and renewable energy generation efficiency are collected in real time to obtain a multi-dimensional data set;

[0008] Analyzing the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy;

[0009] Using a genetic algorithm to optimize the charging and discharging plan of the power demand peak forecast and the power generation potential forecast of renewable energy, a dynamic energy management strategy is obtained;

[0010] When the external power grid is detected to be unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the joint power supply mode of the energy storage system and the backup generator, and adjust the proportion of each power supply in the joint power supply mode through the reinforcement learning algorithm to obtain the energy configuration plan;

[0011] Using a fuzzy logic control system to dynamically adjust the working state of the equipment in the energy configuration scheme, and obtain an intelligent energy-saving control strategy for non-critical equipment;

[0012] Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log;

[0013] The energy management log is evaluated using a machine learning model at a preset time node to obtain power supply strategy optimization suggestions.

[0014] Optionally, when it is detected that the external power grid is unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the joint power supply mode of the energy storage system and the backup generator, and adjust the proportion of each power supply in the joint power supply mode through the reinforcement learning algorithm to obtain an energy configuration plan, including:

[0015] The dynamic energy management strategy is used to perform emergency response mechanism processing on the detected unstable power supply of the external power grid, and a joint power supply mode of the energy storage system and the backup generator is obtained;

[0016] Using a reinforcement learning algorithm to adjust the proportion of each power source in the joint power supply mode to obtain an initial energy configuration plan;

[0017] The initial energy configuration scheme is optimized by using a simulated annealing algorithm and a particle swarm optimization algorithm in combination with the actual power demand of the laboratory and the instant output of renewable energy to obtain a standard energy configuration scheme;

[0018] Using an adaptive control algorithm and a sliding mode variable structure control technology, the output power of the energy storage system and the backup generator is adjusted for the standard energy configuration scheme to obtain control parameters;

[0019] Using an online learning algorithm to monitor the changes in power consumption inside the laboratory and the power supply status of the external power grid in real time during the execution of the control parameters and update the standard energy configuration plan;

[0020] The standard energy configuration plan and the adjustment process of the standard energy configuration plan are recorded using blockchain technology to obtain an energy management log.

[0021] Optionally, the output power of the energy storage system and the backup generator is adjusted for the standard energy configuration scheme using an adaptive control algorithm and a sliding mode variable structure control technology to obtain control parameters, including:

[0022] Dynamically adjusting the output power of the energy storage system in the standard energy configuration scheme by using an adaptive control algorithm to obtain a first control parameter;

[0023] Using sliding mode variable structure control technology to accurately control the output power of the standby generator under the first control parameter, and combining the adjustment result of the energy storage system to obtain the second control parameter;

[0024] Using a multi-objective optimization algorithm to comprehensively evaluate the second control parameter in combination with the real-time power demand and power availability of the laboratory, calculate cost and efficiency factors, and obtain a multi-objective optimized control parameter;

[0025] Using a predictive control algorithm to combine the control parameters of the multi-objective optimization with weather forecast data and historical electricity consumption patterns to perform power demand forecasting, adjust the output plan of the energy storage system and the backup generator, and obtain pre-adjusted control parameters;

[0026] The performance of the pre-adjustment control parameter in actual operation is monitored in real time by using a feedback control mechanism, and the pre-adjustment control parameter is corrected by an iterative learning algorithm to obtain a corrected pre-adjustment control parameter;

[0027] Using a Bayesian network to conduct a risk assessment on the adjustment process of the modified pre-adjustment control parameters, identify potential power supply bottlenecks and fault points, and obtain a risk assessment report;

[0028] Blockchain technology is used to securely store the generation process of the modified pre-adjusted control parameters, the adjustment records and the risk assessment report to generate a control parameter log.

[0029] Optionally, a Bayesian network is used to perform risk assessment on the adjustment process of the modified pre-adjustment control parameters, identify potential power supply bottlenecks and fault points, and obtain a risk assessment report, including:

[0030] Using a Bayesian network, a risk assessment is performed on the adjustment process of the modified pre-adjustment control parameters, potential power supply bottlenecks and fault points are identified, and a preliminary risk assessment report is obtained;

[0031] Decomposing the power supply bottlenecks and fault points in the preliminary risk assessment report by using the fault tree analysis method, determining the impact scope and possible chain reaction paths of each fault point, and obtaining a detailed risk impact analysis;

[0032] Using the Monte Carlo simulation method to perform probability simulation on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a risk probability distribution diagram;

[0033] An expert system is used to comprehensively evaluate the risk probability distribution diagram in combination with the historical data of laboratory operation, and targeted preventive measures and emergency plans are proposed to obtain an optimized risk management plan;

[0034] The optimized risk management plan is processed by natural language processing technology to automatically generate a target risk assessment report including preventive measures and emergency plans.

[0035] Optionally, a Monte Carlo simulation method is used to perform probability simulation on the refined risk impact analysis to evaluate the possibility of power supply system failure under different scenarios and obtain a risk probability distribution diagram, including:

[0036] Using the Monte Carlo simulation method to perform probability simulation processing on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a preliminary risk probability distribution map;

[0037] Performing time correlation analysis on the preliminary risk probability distribution diagram using a time series analysis method to identify the risk trend that changes over time and obtain a time series risk trend diagram;

[0038] The scenario analysis method is used to comprehensively analyze the time series risk trend chart in combination with external environmental factors to obtain a risk assessment matrix under different scenarios;

[0039] Using a deep learning model to perform pattern recognition on the risk assessment matrix, predict the failure mode of the power supply system under extreme conditions, and obtain a failure mode prediction result;

[0040] The Monte Carlo simulation method is used to perform probability simulation on the failure mode prediction results, evaluate the possibility of power supply system failure under different scenarios, and generate a risk probability distribution diagram.

[0041] Optionally, a fuzzy logic control system is used to dynamically adjust the working state of the equipment on the energy configuration scheme to obtain an intelligent energy-saving control strategy for non-critical equipment, including:

[0042] Using a fuzzy logic control system, the energy configuration scheme is dynamically adjusted to adjust the working state of the equipment to obtain an intelligent energy-saving control strategy for non-critical equipment;

[0043] Using adaptive control theory to modify the intelligent energy-saving control strategy in real time to obtain an adaptive intelligent energy-saving control strategy;

[0044] Using a multi-agent system architecture to collaboratively optimize multiple control units in the adaptive intelligent energy-saving control strategy to obtain a collaboratively optimized intelligent energy-saving control strategy;

[0045] Using a reinforcement learning algorithm, the collaborative optimization intelligent energy-saving control strategy is evaluated and iteratively updated to obtain an optimized intelligent energy-saving control strategy;

[0046] Edge computing technology is used to monitor and quickly respond to the execution process of the optimized intelligent energy-saving control strategy in real time to obtain the target intelligent energy-saving control strategy.

[0047] Optionally, blockchain technology is used to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log, including:

[0048] Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy in an unalterable manner, and obtain a preliminary energy management log;

[0049] Using data mining technology to conduct in-depth analysis on the preliminary energy management log, extract key energy usage patterns and abnormal events, and obtain log information;

[0050] Using natural language processing technology to perform text summarization on the log information and generate a summary report;

[0051] Using knowledge graph technology to perform correlation analysis on the data and information in the summary report, construct a knowledge graph of energy use behavior, and obtain a structured energy management knowledge graph;

[0052] The machine learning model is used to perform pattern recognition and trend prediction on the structured energy management knowledge graph, and energy management suggestions are put forward to obtain an energy management log.

[0053] In a second aspect, an embodiment of the present application provides a stabilization system for hybrid power supply of a square cabin nucleic acid laboratory, including:

[0054] The collection module uses a variety of sensors installed inside and outside the modular nucleic acid laboratory to collect environmental parameters, power consumption data, and renewable energy generation efficiency in real time to obtain a multi-dimensional data set;

[0055] An analysis module, used to analyze the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy;

[0056] A prediction module, for optimizing the charging and discharging plan based on the power demand peak prediction and the power generation potential prediction of renewable energy using a genetic algorithm to obtain a dynamic energy management strategy;

[0057] An adjustment module is used to, when detecting that the external power grid is unstable, use the dynamic energy management strategy to start the emergency response mechanism, switch to the joint power supply mode of the energy storage system and the backup generator, and adjust the proportion of each power supply in the joint power supply mode through a reinforcement learning algorithm to obtain an energy configuration plan;

[0058] An adjustment module, used to dynamically adjust the working state of the equipment by using a fuzzy logic control system to the energy configuration scheme, and obtain an intelligent energy-saving control strategy for non-critical equipment;

[0059] A recording module is used to record the implementation process and results of the intelligent energy-saving control strategy using blockchain technology to obtain a complete energy management log;

[0060] The evaluation module is used to evaluate the energy management log using a machine learning model at a preset time node to obtain power supply strategy optimization suggestions.

[0061] In a third aspect, an embodiment of the present invention provides a computing device, comprising 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 stabilization method for hybrid power supply in a modular nucleic acid laboratory as described in any one of the first aspects.

[0062] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, which, when executed by a processor, implement a stabilization method for hybrid power supply of a modular nucleic acid laboratory as described in any one of the first aspects.

[0063] In the embodiment of the present invention, a variety of sensors installed inside and outside the square cabin nucleic acid laboratory are used to collect environmental parameters, power consumption data and renewable energy generation efficiency in real time to obtain a multi-dimensional data set; the multi-dimensional data set is analyzed by a deep learning algorithm to obtain a power demand peak forecast and a renewable energy generation potential forecast; a genetic algorithm is used to optimize the charging and discharging plan of the power demand peak forecast and the renewable energy generation potential forecast to obtain a dynamic energy management strategy; when the external power grid is detected to be unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the energy storage system and the backup generator joint power supply mode, and adjust the proportion of each power supply in the joint power supply mode by the reinforcement learning algorithm to obtain an energy configuration scheme; the energy configuration scheme is dynamically adjusted by a fuzzy logic control system to obtain an intelligent energy-saving control strategy for non-critical equipment; the implementation process and implementation results of the intelligent energy-saving control strategy are recorded by blockchain technology to obtain a complete energy management log; the energy management log is evaluated by a machine learning model at a preset time node to obtain a power supply strategy optimization suggestion. The technical solution provided by the present invention improves energy utilization efficiency by real-time collection of multi-dimensional data and application of a deep learning algorithm to predict power demand peak and renewable energy generation potential. Genetic algorithms are used to optimize charging and discharging plans, and when the external power grid is unstable, the system quickly switches to a combined power supply mode of energy storage systems and backup generators. The power supply ratio is adjusted through a reinforcement learning algorithm, which significantly improves the flexibility and emergency response capabilities of the system. In addition, the fuzzy logic control system is used to achieve intelligent energy-saving control of non-critical equipment, further reducing energy waste and extending equipment life. The application of blockchain technology ensures the transparency and traceability of the energy management process, while the machine learning model continuously optimizes the power supply strategy and improves overall operating efficiency by evaluating the energy management log.

[0064] Furthermore, the emergency response mechanism has been refined. When the external power grid is detected to be unstable, the output power of the energy storage system and the backup generator is accurately adjusted through a variety of optimization algorithms (such as simulated annealing algorithm, particle swarm optimization algorithm) and control technologies (such as adaptive control algorithm, sliding mode variable structure control technology), which improves the accuracy and control precision of the configuration scheme. The online learning algorithm realizes real-time monitoring and dynamic updating of the standard energy configuration scheme, enhancing the response speed and adaptability of the system. Blockchain technology records the entire energy configuration scheme and its adjustment process, ensuring the transparency and traceability of the operation, thereby comprehensively improving the stability and reliability of the hybrid power supply system of the Fangcang nucleic acid laboratory.

[0065] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] 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.

[0067] Figure 1 A flow chart of a stabilization method for hybrid power supply of a modular nucleic acid laboratory provided by an embodiment of the present invention;

[0068] Figure 2 A schematic diagram of the structure of a stabilization system for hybrid power supply of a modular nucleic acid laboratory provided by an embodiment of the present invention;

[0069] Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] 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.

[0071] 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.

[0072] 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.

[0073] Relying on static predictions and fixed models, it is impossible to effectively respond to emergencies and dynamically changing environments, resulting in insufficient or excessive waste of power supply. The manual switching method has a long response time and complex operation, which may cause power outages at critical moments. In addition, the lack of intelligent management and comprehensive data recording and analysis makes energy utilization inefficient and difficult to timely discover and optimize power supply bottlenecks. Based on this, the present invention provides a stable method for hybrid power supply of a modular nucleic acid laboratory, such as Figure 1 ,include:

[0074] Step 101: Using a variety of sensors installed inside and outside the modular nucleic acid laboratory, environmental parameters, power consumption data, and renewable energy generation efficiency are collected in real time to obtain a multi-dimensional data set;

[0075] In this step, various sensors installed inside and outside the modular nucleic acid laboratory collect real-time environmental parameters (such as temperature and humidity), power consumption data (such as the power consumption of each device), and renewable energy generation efficiency (such as the power generation of solar panels). These sensors continuously collect data and integrate the data into a multi-dimensional data set to provide comprehensive basic information for subsequent analysis.

[0076] Step 102: Analyze the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy;

[0077] In this step, deep learning algorithms are used to process multi-dimensional data sets. By training neural network models, analyzing patterns and trends in historical data, and predicting future peak electricity demand and renewable energy generation potential, this prediction helps plan energy distribution strategies in advance and ensure efficient operation of the system.

[0078] Step 103: using a genetic algorithm to optimize the charging and discharging plan for the power demand peak forecast and the renewable energy generation potential forecast to obtain a dynamic energy management strategy;

[0079] In this step, the genetic algorithm is applied to optimize the charging and discharging plan. The genetic algorithm simulates the natural selection process to find the optimal solution and generate dynamic energy management strategies that can adapt to different working conditions. These strategies not only take into account the peak power demand and the power generation potential of renewable energy, but also balance the charging and discharging process of the energy storage system to achieve the best energy utilization efficiency.

[0080] Step 104: When it is detected that the external power grid is unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the energy storage system and the backup generator combined power supply mode, and adjust the proportion of each power supply in the combined power supply mode through the reinforcement learning algorithm to obtain an energy configuration plan;

[0081] In this step, when the external power grid is detected to be unstable, the emergency response mechanism is immediately activated and the energy storage system and backup generator are switched to a joint power supply mode. The power supply ratio between the energy storage system and the backup generator is dynamically adjusted using a reinforcement learning algorithm to ensure stable power supply in an emergency. Finally, an energy configuration plan that adapts to the current situation is generated to ensure the continuous operation of key equipment.

[0082] Step 105: using a fuzzy logic control system to dynamically adjust the working state of the equipment on the energy configuration scheme to obtain an intelligent energy-saving control strategy for non-critical equipment;

[0083] In this step, the fuzzy logic control system is used to dynamically adjust the energy configuration plan and process the working status of each device. The fuzzy logic control system intelligently adjusts the operating mode of non-critical equipment based on real-time data and preset rules to implement energy-saving control strategies. This method not only reduces unnecessary energy waste, but also extends the service life of the equipment.

[0084] Step 106: Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log;

[0085] In this step, blockchain technology is used to record the implementation process and results of the intelligent energy-saving control strategy. Blockchain technology ensures the transparency and immutability of the records and generates a complete energy management log, which not only enhances the credibility of the system, but also provides a detailed basis for subsequent audits and optimizations.

[0086] Step 107: Use a machine learning model to evaluate the energy management log at a preset time node to obtain power supply strategy optimization suggestions.

[0087] In this step, the energy management log is evaluated at a preset time point using a machine learning model. By analyzing the data in the log, potential problems and improvement points are identified, and power supply strategy optimization suggestions are generated. These suggestions are used to further optimize the energy management strategy to ensure that the system always maintains efficient and stable operation.

[0088] Based on this, the present invention provides a specific embodiment, in which step 104, when it is detected that the external power grid is unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the energy storage system and the backup generator joint power supply mode, and adjust the proportion of each power supply in the joint power supply mode by the reinforcement learning algorithm to obtain an energy configuration plan, which specifically includes the following steps:

[0089] Step 201: using the dynamic energy management strategy to perform emergency response mechanism processing on the detected unstable power supply of the external power grid, and obtaining a joint power supply mode of the energy storage system and the backup generator;

[0090] In this step, the dynamic energy management strategy is used to implement an emergency response mechanism to deal with the detected unstable power supply of the external power grid. When the system detects that the external power grid is unstable, the preset emergency response mechanism is immediately activated, and the current power demand and available resources are automatically evaluated according to the dynamic energy management strategy, and the power supply mode of the energy storage system and the backup generator is quickly switched to ensure that the laboratory can still obtain a stable and reliable power supply.

[0091] Step 202: using a reinforcement learning algorithm to adjust the proportion of each power source in the joint power supply mode to obtain an initial energy configuration plan;

[0092] In this step, the reinforcement learning algorithm is used to adjust the proportion of each power source in the joint power supply mode. The reinforcement learning algorithm dynamically adjusts the power supply ratio between the energy storage system and the backup generator according to the real-time power demand and the status of the energy storage system. Through continuous trial and error and optimization, the most suitable power distribution plan is found, and the initial energy configuration plan is formed to ensure that power distribution can quickly adapt to changing needs in an emergency.

[0093] Step 203: Optimizing the initial energy configuration scheme by using a simulated annealing algorithm and a particle swarm optimization algorithm in combination with the actual power demand of the laboratory and the instant output of renewable energy to obtain a standard energy configuration scheme;

[0094] In this step, the simulated annealing algorithm and particle swarm optimization algorithm are used to optimize the initial energy configuration plan in combination with the actual power demand in the laboratory and the immediate output of renewable energy. These algorithms perform multiple rounds of optimization on the initial energy configuration plan based on the actual power demand in the laboratory and the immediate output of renewable energy, taking into account various constraints such as power demand fluctuations and capacity limitations of the energy storage system to generate the optimal standard energy configuration plan.

[0095] Step 204: using an adaptive control algorithm and a sliding mode variable structure control technology, adjusting the output power of the energy storage system and the backup generator for the standard energy configuration scheme to obtain control parameters;

[0096] In this step, the adaptive control algorithm and sliding mode variable structure control technology are used to adjust the output power of the energy storage system and the backup generator for the standard energy configuration scheme. The adaptive control algorithm dynamically adjusts the output power of the energy storage system and the backup generator according to real-time data to ensure that it meets the requirements of the standard energy configuration scheme. The sliding mode variable structure control technology further enhances the robustness and response speed of the system, ensures accurate control of the output power, and realizes refined control of the output power of the energy storage system and the backup generator.

[0097] Step 205: Use an online learning algorithm to monitor the changes in the internal power consumption of the laboratory and the power supply status of the external power grid during the execution of the control parameters in real time, and update the standard energy configuration plan;

[0098] In this step, an online learning algorithm is used to monitor the changes in the internal power consumption of the laboratory and the power supply status of the external power grid during the execution of the control parameters in real time, and update the standard energy configuration plan. The online learning algorithm continuously monitors the changes in the internal power consumption of the laboratory and the power supply status of the external power grid, analyzes the data in real time, and dynamically adjusts the standard energy configuration plan to ensure that the energy configuration plan is always in the best state and can flexibly respond to various changes.

[0099] Step 206: Use blockchain technology to record the standard energy configuration plan and the adjustment process of the standard energy configuration plan to obtain an energy management log;

[0100] In this step, blockchain technology is used to record the standard energy configuration plan and the adjustment process of the standard energy configuration plan. Blockchain technology ensures the security, transparency, and immutability of all energy management activities. Each adjustment and execution result of the standard energy configuration plan is securely stored on the blockchain, forming a complete energy management log, providing reliable data support for subsequent auditing and optimization.

[0101] Based on this, the present invention provides a specific embodiment. In step 205, an adaptive control algorithm and a sliding mode variable structure control technology are used to adjust the output powers of the energy storage system and the standby generator in the standard energy configuration plan to obtain control parameters, which specifically include the following steps:

[0102] Step 301: Use an adaptive control algorithm to dynamically adjust the output power of the energy storage system in the standard energy configuration plan to obtain a first control parameter;

[0103] In this step, an adaptive control algorithm is used to dynamically adjust the output power of the energy storage system in the standard energy configuration plan. The adaptive control algorithm dynamically adjusts the output power of the energy storage system according to the real-time power demand and the state of the energy storage system to ensure that it can provide the most appropriate power output under different working conditions, and finally obtains a first control parameter.

[0104] The expression of the first control parameter is as follows:

[0105]

[0106] C1(t): The first control parameter at time t.

[0107] α, β: Weight coefficients to ensure the output power P of the energy storage system ESA balance is achieved between the change in laboratory power consumption ΔP.

[0108] P ES (t): Output power of the energy storage system at time t.

[0109] P ES,max : Maximum output power of the energy storage system.

[0110] ΔP(t): Change in electricity consumption within the laboratory.

[0111] P lab (t): Total power demand of the laboratory at time t.

[0112] Step 302: using a sliding mode variable structure control technique to accurately control the output power of the backup generator under the first control parameter, and combining the adjustment result of the energy storage system to obtain a second control parameter;

[0113] In this step, the sliding mode variable structure control technology is used to accurately control the output power of the backup generator under the first control parameter. This technology enhances the robustness and response speed of the system, ensures that the backup generator and the energy storage system work together to achieve the best power distribution effect, and finally combines the adjustment results of the energy storage system to obtain the second control parameter.

[0114] The expression of the second control parameter is as follows:

[0115]

[0116] C2(t): The second control parameter at time t.

[0117] γ,δ: weight coefficients to ensure the output power P of the standby generator G A balance is achieved between the first control parameter C1.

[0118] P G (t): Output power of the standby generator at time t.

[0119] P G,max : Maximum output power of the standby generator.

[0120] C1 opt : The optimal value of the first control parameter.

[0121] Step 303: using a multi-objective optimization algorithm to comprehensively evaluate the second control parameter in combination with the real-time power demand and power availability of the laboratory, calculate the cost and efficiency factors, and obtain a multi-objective optimized control parameter;

[0122] In this step, a multi-objective optimization algorithm is used to comprehensively evaluate the second control parameter in combination with the laboratory's real-time power demand and power availability. The algorithm takes into account cost and efficiency factors, and finds the optimal control parameter combination through multiple rounds of iterations to achieve the best energy utilization effect, and finally obtains the multi-objective optimized control parameters.

[0123] The expressions of the control parameters for multi-objective optimization are as follows:

[0124]

[0125] C multi (t): Multi-objective optimization control parameters at time t.

[0126] η,θ: weight coefficients, corresponding to cost E cost and efficiency E eff The weight of .

[0127] E cost (t): Energy cost at time t.

[0128] E cost,max : Maximum possible energy cost.

[0129] E eff (t): Energy efficiency at time t.

[0130] E eff,max : Maximum energy efficiency.

[0131] Step 304: using a predictive control algorithm to perform power demand forecasting on the control parameters of the multi-objective optimization in combination with weather forecast data and historical power consumption patterns, adjusting the output plans of the energy storage system and the backup generator, and obtaining pre-adjusted control parameters;

[0132] In this step, a predictive control algorithm is used to forecast power demand by combining the multi-objective optimized control parameters with weather forecast data and historical power consumption patterns. The algorithm plans the output plan of the energy storage system and backup generators in advance to ensure a stable power supply under different weather conditions. Finally, the output plan of the energy storage system and backup generators is adjusted to obtain pre-adjusted control parameters.

[0133] The expression of the preset control parameter is as follows:

[0134] C pre (t) = λ·F pred (t)+μ·H use (t)

[0135] C pre (t): Pre-adjustment control parameter at time t.

[0136] λ,μ: weight coefficients to ensure weather forecast F pred Compared with the historical electricity consumption pattern H use strike a balance between.

[0137] F pred (t): Weather forecast data at time t, used to predict future electricity demand.

[0138] H use (t): Historical electricity consumption pattern data at time t.

[0139] Step 305: using a feedback control mechanism to monitor the performance of the pre-adjustment control parameter in actual operation in real time, and correcting the pre-adjustment control parameter through an iterative learning algorithm to obtain a corrected pre-adjustment control parameter;

[0140] In this step, a feedback control mechanism is used to monitor the performance of the pre-adjusted control parameters in actual operation in real time. These parameters are continuously corrected through an iterative learning algorithm to quickly respond to deviations in actual operation, ensure that the control parameters are always in the optimal state, and finally obtain the corrected pre-adjusted control parameters.

[0141] Step 306: using a Bayesian network to perform risk assessment on the adjustment process of the modified pre-adjustment control parameters, identifying potential power supply bottlenecks and fault points, and obtaining a risk assessment report;

[0142] In this step, the Bayesian network is used to conduct risk assessment on the adjustment process of the modified pre-adjustment control parameters. The Bayesian network analyzes the risks of each link, identifies potential power supply bottlenecks and fault points, and generates a detailed risk assessment report based on historical data and expert experience.

[0143] Step 307: Using blockchain technology to securely store the generation process of the modified pre-adjusted control parameters, the adjustment records and the risk assessment report, and generate a control parameter log;

[0144] In this step, blockchain technology is used to securely store the generation process, adjustment records, and risk assessment reports of the corrected pre-adjusted control parameters. Each adjustment and assessment result is recorded in an unalterable manner on the blockchain, forming a complete control parameter log to ensure data security and transparency, and provide reliable support for subsequent audits and optimizations.

[0145] Based on this, the present invention provides a specific embodiment, wherein the step 306 uses a Bayesian network to perform risk assessment on the adjustment process of the modified pre-adjustment control parameter, identifies potential power supply bottlenecks and fault points, and obtains a risk assessment report, which specifically includes the following steps:

[0146] Step 401: using a Bayesian network to conduct a risk assessment on the adjustment process of the modified pre-adjustment control parameters, identify potential power supply bottlenecks and fault points, and obtain a preliminary risk assessment report;

[0147] In this step, the Bayesian network is used to conduct risk assessment on the adjustment process of the modified pre-adjustment control parameters. The Bayesian network analyzes the risks of each link, identifies potential power supply bottlenecks and fault points, and generates a detailed risk assessment report based on historical data and expert experience, and finally obtains a preliminary risk assessment report;

[0148] Among them, the calculation formula for risk assessment by Bayesian network is as follows:

[0149]

[0150] Among them, P(F i |E) means that under the given evidence E, the i-th fault point F i The posterior probability of occurrence; P(E|F i ) indicates that at the i-th fault point F i The likelihood of observing evidence E if it occurs; P(F i ) represents the i-th fault point F i The prior probability of occurrence; K is the number of all possible failure points; P(E|F k ) indicates that at the kth fault point F k The likelihood of observing evidence E if it occurs; P(F k ) represents the kth fault point F k Prior probability of occurrence; w k is the importance weight of the kth fault point, which can be estimated based on historical data and expert experience.

[0151] Step 402: Decompose the power supply bottlenecks and fault points in the preliminary risk assessment report using a fault tree analysis method, determine the impact range of each fault point and possible chain reaction paths, and obtain a detailed risk impact analysis;

[0152] In this step, the fault tree analysis method is used to decompose the power supply bottlenecks and fault points in the preliminary risk assessment report. The fault tree analysis method determines in detail the impact range and possible chain reaction paths of each fault point, deeply analyzes the potential risks of the system, and finally obtains a detailed risk impact analysis.

[0153] Step 403: using a Monte Carlo simulation method to perform probability simulation on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a risk probability distribution diagram;

[0154] In this step, the Monte Carlo simulation method is used to perform probability simulation on the detailed risk impact analysis. This method evaluates the possibility of power supply system failure under different scenarios through random sampling, generates an intuitive risk probability distribution map, provides a scientific basis for subsequent risk management, and finally obtains a risk probability distribution map;

[0155] The formula for calculating the probability of power supply system failure is as follows:

[0156]

[0157] Among them, P fail represents the probability of power supply system failure; N is the number of Monte Carlo simulations, that is, the total number of random sampling; I (Scenario i ) is an indicator function, which takes the value of 1 when the i-th simulated scenario causes the power supply system to fail, otherwise it takes the value of 0; i is the failure rate parameter under the i-th simulation scenario, which can be estimated based on historical data and expert experience; D i is the power demand in the ith simulation scenario, obtained from the peak power demand forecast; R i is the renewable energy output under the i-th simulation scenario, obtained from the prediction of renewable energy generation potential; S i is the state of the energy storage system under the i-th simulation scenario, obtained from the optimization of the energy storage system charging and discharging plan; G i is the state of the backup generator in the i-th simulation scenario, obtained from the proportion adjustment of each power source in the joint power supply mode; E i is the stability of the external power grid under the i-th simulation scenario, which is detected based on the unstable power supply of the external power grid.

[0158] Step 404: using an expert system to comprehensively evaluate the risk probability distribution diagram in combination with the historical data of laboratory operation, propose targeted preventive measures and emergency plans, and obtain an optimized risk management plan;

[0159] In this step, an expert system is used to conduct a comprehensive evaluation of the risk probability distribution map combined with the historical data of laboratory operations. Based on historical data and expert experience, the expert system proposes targeted preventive measures and emergency plans to ensure the scientificity and effectiveness of the response strategy, and ultimately obtain an optimized risk management plan.

[0160] Step 405: Using natural language processing technology to perform text generation processing on the optimized risk management plan, and automatically generate a target risk assessment report including preventive measures and emergency plans;

[0161] In this step, natural language processing technology is used to generate text for the optimized risk management plan. This technology converts the optimized risk management plan into an easy-to-understand text form and automatically generates a target risk assessment report that includes preventive measures and emergency plans, ensuring that the report content is clear, accurate and easy to implement.

[0162] Based on this, the present invention provides a specific embodiment, wherein the step 403 uses a Monte Carlo simulation method to perform probability simulation on the refined risk impact analysis, evaluates the possibility of power supply system failure under different scenarios, and obtains a risk probability distribution diagram, which specifically includes the following steps:

[0163] Step 501: using a Monte Carlo simulation method to perform probability simulation processing on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a preliminary risk probability distribution map;

[0164] In this step, the Monte Carlo simulation method is used to perform probabilistic simulation on the refined risk impact analysis. By defining a series of possible scenarios and corresponding variable probability distributions, this method can randomly sample these variables multiple times to simulate the operation of the power supply system under various conditions. Each simulation represents a possible situation and records whether the system fails. After a large number of iterations, the probability of failure of the power supply system under different scenarios can be statistically calculated, and then a preliminary risk probability distribution map can be drawn to provide an intuitive view of the possibility of failure.

[0165] Step 502: using a time series analysis method to perform time correlation analysis on the preliminary risk probability distribution graph, identifying the risk trend that changes over time, and obtaining a time series risk trend graph;

[0166] In this step, time series analysis methods are used to study the time-varying patterns of the data in the preliminary risk probability distribution map. Time series analysis focuses on identifying and quantifying time dependencies in the data, including trends, seasonality, and cyclical components. By modeling the time series of historical risk probability data, trends and patterns in the evolution of risk levels over time can be detected, which helps predict future risk development paths and generate time series risk trend maps to show how risks change over time.

[0167] Step 503: using the scenario analysis method to comprehensively analyze the time series risk trend graph in combination with external environmental factors to obtain a risk assessment matrix under different scenarios;

[0168] In this step, scenario analysis is applied to the time series risk trend chart, taking into account the impact of external environmental factors such as policy changes, market dynamics or technological advances. Scenario analysis involves constructing multiple possible future scenarios, each of which represents a specific set of assumptions. By combining the results of time series analysis with different scenarios, the development of risks under various external conditions can be evaluated. What is ultimately formed is a set of risk assessment matrices, in which each cell reflects the risk level of the power supply system under a specific scenario, providing a comprehensive reference framework for decision-making.

[0169] Step 504: using a deep learning model to perform pattern recognition on the risk assessment matrix, predicting the failure mode of the power supply system under extreme conditions, and obtaining a failure mode prediction result;

[0170] In this step, the deep learning model is trained to identify complex patterns in the risk assessment matrix. Deep learning is a form of machine learning that can automatically learn features from large amounts of data and make predictions. For the risk assessment of the power supply system, the model can identify which patterns may cause the system to fail under extreme conditions. By inputting different risk assessment matrices, the model can predict a variety of potential failure modes. The output result is the behavior pattern that the power supply system may exhibit under future extreme conditions, that is, the failure mode prediction result.

[0171] Step 505: using a Monte Carlo simulation method to perform probability simulation on the failure mode prediction result, evaluate the possibility of power supply system failure under different scenarios, and generate a risk probability distribution diagram;

[0172] In this step, the Monte Carlo simulation method is used again to perform probabilistic simulation based on the failure mode prediction results obtained in the previous step. The purpose of this simulation is to more accurately evaluate the specific possibility of power supply system failure under different scenarios and extreme conditions. By setting various parameters and conditions, the simulation process can reflect the performance of the system when facing different types of risks. Finally, based on the results of all simulation tests, a new risk probability distribution map is generated to provide accurate data support and visual representation for risk management.

[0173] Based on this, the present invention provides a specific embodiment, wherein step 106 specifically includes the following steps:

[0174] Step 601: using a fuzzy logic control system to dynamically adjust the working state of the equipment on the energy configuration scheme to obtain an intelligent energy-saving control strategy for non-critical equipment;

[0175] In this step, the fuzzy logic control system is a computational model that mimics the human decision-making process and can handle imprecise or uncertain information. The system is applied to the energy configuration plan, which simulates expert decision-making by setting a series of rules to achieve dynamic adjustment of the working status of non-critical equipment. According to real-time environmental conditions and demand changes, the fuzzy logic controller automatically adjusts the operating parameters of these devices, such as temperature, speed, etc., to achieve energy-saving effects. The final result is a set of intelligent energy-saving control strategies designed to ensure that non-critical equipment reduces energy consumption as much as possible without affecting overall operations.

[0176] Step 602: using adaptive control theory to modify the intelligent energy-saving control strategy in real time to obtain an adaptive intelligent energy-saving control strategy;

[0177] In this step, adaptive control theory involves developing a control system that can self-adjust to cope with unknown or changing environmental conditions. Based on the initially formed intelligent energy-saving control strategy, an adaptive algorithm is applied to continuously monitor the deviation between the actual operating conditions and the expected goals. Once the performance deviates from the ideal state, the system will automatically adjust the control parameters and optimize the operating mode to ensure that the energy-saving measures are always effective. This process is dynamic and continuous, thus forming an adaptive intelligent energy-saving control strategy that can self-improve over time.

[0178] Step 603: using a multi-agent system architecture to collaboratively optimize multiple control units in the adaptive intelligent energy-saving control strategy to obtain a collaboratively optimized intelligent energy-saving control strategy;

[0179] In this step, the multi-agent system (MAS) is a network composed of multiple intelligent agents, each of which is responsible for a specific task and can communicate and cooperate with other intelligent agents. MAS is used to coordinate the interaction between different control units to achieve more efficient energy management. Each agent represents one or a group of devices, and through local information exchange and collaboration, they jointly find the optimal energy-saving path. This approach not only improves the flexibility and response speed of the system, but also promotes the effective allocation of resources, and ultimately forms a set of collaboratively optimized intelligent energy-saving control strategies.

[0180] Step 604: using a reinforcement learning algorithm to perform performance evaluation and iterative update on the collaborative optimization intelligent energy-saving control strategy to obtain an optimized intelligent energy-saving control strategy;

[0181] Reinforcement learning is a machine learning method in which the agent learns the best behavior strategy by interacting with the environment. The reinforcement learning algorithm is used to evaluate the effectiveness of the collaboratively optimized intelligent energy-saving control strategy, and continuously adjust the strategy based on feedback to improve efficiency. The agent learns by trying different actions and observing the results, gradually accumulating knowledge to make better decisions. After many iterations, the system can identify which actions are most helpful in saving energy, and then formulate a more optimized intelligent energy-saving control strategy.

[0182] Step 605: Use edge computing technology to monitor and quickly respond to the execution process of the optimized intelligent energy-saving control strategy in real time to obtain a target intelligent energy-saving control strategy;

[0183] In this step, edge computing refers to the technology of processing data at the edge of the network, that is, performing calculations close to the data source to reduce latency and improve efficiency. Edge computing is used to monitor the application of optimized intelligent energy-saving control strategies in real time. This technology allows instant analysis of data collected on-site and rapid adoption of necessary adjustment measures to ensure the effective implementation of the strategy. By shortening response time and increasing processing power, edge computing helps maintain efficient operation of the system and ultimately achieves the construction of the target intelligent energy-saving control strategy.

[0184] Based on this, the present invention provides a specific embodiment, in which step 106 uses blockchain technology to record the implementation process and implementation results of the intelligent energy-saving control strategy to obtain a complete energy management log, which specifically includes the following steps:

[0185] Step 701: Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy in an unalterable manner, and obtain a preliminary energy management log;

[0186] In this step, blockchain technology is applied to the implementation process and result recording of intelligent energy-saving control strategies. As a distributed ledger technology, blockchain ensures that all recorded data is highly secure and cannot be tampered with. Every adjustment of the control strategy, change in equipment status, and energy consumption are recorded in detail on the blockchain. These records are not only transparent and traceable, but also provide reliable basic data for subsequent analysis, ultimately forming a preliminary energy management log.

[0187] Step 702: using data mining technology to perform in-depth analysis on the preliminary energy management log, extract key energy usage patterns and abnormal events, and obtain log information;

[0188] In this step, data mining technology is used to conduct in-depth analysis of large amounts of data in the preliminary energy management log. By applying statistical analysis, cluster analysis, and association rules, key energy usage patterns and potential abnormal events are identified. Data mining can reveal the rules and trends hidden behind massive amounts of data, and help discover peak hours of energy usage, inefficient operations, and other issues that require attention. The log information ultimately generated provides an important basis for optimizing energy management and fault prevention.

[0189] Step 703: Perform text summarization on the log information using natural language processing technology to generate a summary report;

[0190] In this step, natural language processing (NLP) technology is used to process and analyze log information and automatically generate concise and clear summary reports. The NLP algorithm can automatically extract key content from the log, identify important terms and phrases, and convert complex technical information into easy-to-understand natural language descriptions. Through text summarization technology, the system can quickly generate a summary report covering major findings and recommendations, making it easier for managers and technicians to quickly understand the current energy management status.

[0191] Step 704: Use knowledge graph technology to perform association analysis on the data and information in the summary report, construct a knowledge graph of energy usage behavior, and obtain a structured energy management knowledge graph;

[0192] In this step, knowledge graph technology is used to perform correlation analysis on the data and information in the summary report. By constructing an entity relationship network, the knowledge graph can show the intrinsic connection between different energy use behaviors, revealing the causal relationship and impact path. This structured representation method not only helps to intuitively understand complex energy management issues, but also provides a solid foundation for subsequent decision support. The resulting structured energy management knowledge graph is a visualization tool that contains rich information and logical associations.

[0193] Step 705: Use a machine learning model to perform pattern recognition and trend prediction on the structured energy management knowledge graph, propose energy management suggestions, and obtain an energy management log;

[0194] In this step, machine learning models are applied to structured energy management knowledge graphs for pattern recognition and trend prediction. By training the model to identify patterns in historical data and predict future energy demand changes and potential risks, the system can make specific energy management recommendations based on these analysis results, such as optimizing equipment operating time, adjusting energy configuration plans, or taking preventive maintenance measures. The energy management log generated in the end not only records all the analysis and recommendations, but also provides a scientific basis for the continuous improvement of energy management strategies.

[0195] Figure 2 A structural schematic diagram of a stabilization system for hybrid power supply of a square cabin nucleic acid laboratory is provided for the embodiment of the present application, such as Figure 2 As shown, the system includes:

[0196] The acquisition module 21 uses a variety of sensors installed inside and outside the modular nucleic acid laboratory to collect environmental parameters, power consumption data, and power generation efficiency of renewable energy in real time to obtain a multi-dimensional data set;

[0197] An analysis module 22 is used to analyze the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy;

[0198] A prediction module 23, for optimizing the charging and discharging plan based on the power demand peak prediction and the power generation potential prediction of renewable energy using a genetic algorithm to obtain a dynamic energy management strategy;

[0199] The adjustment module 24 is used to use the dynamic energy management strategy to start the emergency response mechanism when detecting that the external power grid is unstable, switch to the energy storage system and the backup generator joint power supply mode, and adjust the proportion of each power supply in the joint power supply mode through the reinforcement learning algorithm to obtain an energy configuration plan;

[0200] The adjustment module 25 is used to dynamically adjust the working state of the equipment by using the fuzzy logic control system to the energy configuration scheme, so as to obtain the intelligent energy-saving control strategy of the non-critical equipment;

[0201] The recording module 26 is used to record the implementation process and results of the intelligent energy-saving control strategy using blockchain technology to obtain a complete energy management log;

[0202] The evaluation module 27 is used to evaluate the energy management log using a machine learning model at a preset time node to obtain power supply strategy optimization suggestions.

[0203] Figure 2 The hybrid power supply stabilization system for the square cabin nucleic acid laboratory can be implemented Figure 1 The implementation principle and technical effect of the xx method described in the embodiment shown will not be repeated. For the above embodiment, the specific way in which each module and unit performs the operation of a hybrid power supply stabilization system for a square cabin nucleic acid laboratory has been described in detail in the embodiment of the method, and will not be elaborated here.

[0204] Figure 2 The embodiment shown in the figure. A hybrid power supply stabilization system for a square cabin nucleic acid laboratory 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;

[0205] 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 .

[0206] The processing component 32 is used to use a variety of sensors installed inside and outside the modular nucleic acid laboratory to collect environmental parameters, power consumption data and renewable energy power generation efficiency in real time to obtain a multi-dimensional data set; use a deep learning algorithm to analyze the multi-dimensional data set to obtain a power demand peak forecast and a renewable energy power generation potential forecast; use a genetic algorithm to optimize the charging and discharging plan of the power demand peak forecast and the renewable energy power generation potential forecast to obtain a dynamic energy management strategy; when it is detected that the external power grid is unstable, use the dynamic energy management strategy to start the emergency response mechanism, switch to the energy storage system and the backup generator combined power supply mode, adjust the proportion of each power supply in the combined power supply mode through the reinforcement learning algorithm, and obtain an energy configuration plan; use a fuzzy logic control system to dynamically adjust the working state of the equipment to the energy configuration plan to obtain an intelligent energy-saving control strategy for non-critical equipment; use blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log; use a machine learning model to evaluate the energy management log at a preset time node to obtain power supply strategy optimization suggestions.

[0207] 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.

[0208] 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.

[0209] Computing devices also include other components, such as input / output interfaces, display components, and communication components.

[0210] 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.

[0211] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0212] 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.

[0213] 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 illustrated embodiment provides a stabilizing method and system for hybrid power supply in a modular nucleic acid laboratory.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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 stabilizing hybrid power supply for a modular nucleic acid laboratory, characterized in that: include: Using a variety of sensors installed inside and outside the modular nucleic acid laboratory, environmental parameters, power consumption data, and renewable energy generation efficiency are collected in real time to obtain a multi-dimensional data set; Analyzing the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy; Using a genetic algorithm to optimize the charging and discharging plan of the power demand peak forecast and the power generation potential forecast of renewable energy, a dynamic energy management strategy is obtained; When the external power grid is detected to be unstable, the dynamic energy management strategy is used to start the emergency response mechanism, switch to the joint power supply mode of the energy storage system and the backup generator, and adjust the proportion of each power supply in the joint power supply mode through the reinforcement learning algorithm to obtain the energy configuration plan; Using a fuzzy logic control system to dynamically adjust the working state of the equipment in the energy configuration scheme, and obtain an intelligent energy-saving control strategy for non-critical equipment; Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log; The energy management log is evaluated using a machine learning model at a preset time node to obtain power supply strategy optimization suggestions.

2. The method according to claim 1, characterized in that When the external power grid is detected to be unstable, the dynamic energy management strategy is used to start the emergency response mechanism and switch to the joint power supply mode of the energy storage system and the backup generator. The proportion of each power source in the joint power supply mode is adjusted through the reinforcement learning algorithm to obtain an energy configuration plan, including: The dynamic energy management strategy is used to perform emergency response mechanism processing on the detected unstable power supply of the external power grid, and a joint power supply mode of the energy storage system and the backup generator is obtained; Using a reinforcement learning algorithm to adjust the proportion of each power source in the joint power supply mode to obtain an initial energy configuration plan; The initial energy configuration scheme is optimized by using a simulated annealing algorithm and a particle swarm optimization algorithm in combination with the actual power demand of the laboratory and the instant output of renewable energy to obtain a standard energy configuration scheme; Using an adaptive control algorithm and a sliding mode variable structure control technology, the output power of the energy storage system and the backup generator is adjusted for the standard energy configuration scheme to obtain control parameters; Using an online learning algorithm to monitor the changes in power consumption inside the laboratory and the power supply status of the external power grid in real time during the execution of the control parameters and update the standard energy configuration plan; The standard energy configuration plan and the adjustment process of the standard energy configuration plan are recorded using blockchain technology to obtain an energy management log.

3. The method according to claim 2, characterized in that By using adaptive control algorithm and sliding mode variable structure control technology, the output power of energy storage system and backup generator is adjusted for the standard energy configuration scheme to obtain control parameters, including: Dynamically adjusting the output power of the energy storage system in the standard energy configuration scheme by using an adaptive control algorithm to obtain a first control parameter; Using sliding mode variable structure control technology to accurately control the output power of the standby generator under the first control parameter, and combining the adjustment result of the energy storage system to obtain the second control parameter; Using a multi-objective optimization algorithm to comprehensively evaluate the second control parameter in combination with the real-time power demand and power availability of the laboratory, calculate cost and efficiency factors, and obtain a multi-objective optimized control parameter; Using a predictive control algorithm to combine the control parameters of the multi-objective optimization with weather forecast data and historical electricity consumption patterns to perform power demand forecasting, adjust the output plan of the energy storage system and the backup generator, and obtain pre-adjusted control parameters; The performance of the pre-adjustment control parameter in actual operation is monitored in real time by using a feedback control mechanism, and the pre-adjustment control parameter is corrected by an iterative learning algorithm to obtain a corrected pre-adjustment control parameter; Using a Bayesian network to conduct a risk assessment on the adjustment process of the modified pre-adjustment control parameters, identify potential power supply bottlenecks and fault points, and obtain a risk assessment report; Blockchain technology is used to securely store the generation process of the modified pre-adjusted control parameters, the adjustment records and the risk assessment report to generate a control parameter log.

4. The method according to claim 3, characterized in that The Bayesian network is used to conduct risk assessment on the adjustment process of the modified pre-adjustment control parameters, identify potential power supply bottlenecks and fault points, and obtain a risk assessment report, including: Using a Bayesian network, a risk assessment is performed on the adjustment process of the modified pre-adjustment control parameters, potential power supply bottlenecks and fault points are identified, and a preliminary risk assessment report is obtained; Decomposing the power supply bottlenecks and fault points in the preliminary risk assessment report by using the fault tree analysis method, determining the impact scope and possible chain reaction paths of each fault point, and obtaining a detailed risk impact analysis; Using the Monte Carlo simulation method to perform probability simulation on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a risk probability distribution diagram; An expert system is used to comprehensively evaluate the risk probability distribution diagram in combination with the historical data of laboratory operation, and targeted preventive measures and emergency plans are proposed to obtain an optimized risk management plan; The optimized risk management plan is processed by natural language processing technology to automatically generate a target risk assessment report including preventive measures and emergency plans.

5. The method according to claim 4, characterized in that The Monte Carlo simulation method is used to perform probability simulation on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a risk probability distribution diagram, including: Using the Monte Carlo simulation method to perform probability simulation processing on the detailed risk impact analysis, evaluate the possibility of power supply system failure under different scenarios, and obtain a preliminary risk probability distribution map; Performing time correlation analysis on the preliminary risk probability distribution diagram using a time series analysis method to identify the risk trend that changes over time and obtain a time series risk trend diagram; The scenario analysis method is used to comprehensively analyze the time series risk trend chart in combination with external environmental factors to obtain a risk assessment matrix under different scenarios; Using a deep learning model to perform pattern recognition on the risk assessment matrix, predict the failure mode of the power supply system under extreme conditions, and obtain a failure mode prediction result; The Monte Carlo simulation method is used to perform probability simulation on the failure mode prediction results, evaluate the possibility of power supply system failure under different scenarios, and generate a risk probability distribution diagram.

6. The method according to claim 1, characterized in that The energy configuration scheme is dynamically adjusted by using a fuzzy logic control system to obtain an intelligent energy-saving control strategy for non-critical equipment, including: Using a fuzzy logic control system, the energy configuration scheme is dynamically adjusted to adjust the working state of the equipment to obtain an intelligent energy-saving control strategy for non-critical equipment; Using adaptive control theory to modify the intelligent energy-saving control strategy in real time to obtain an adaptive intelligent energy-saving control strategy; Using a multi-agent system architecture to collaboratively optimize multiple control units in the adaptive intelligent energy-saving control strategy to obtain a collaboratively optimized intelligent energy-saving control strategy; Using a reinforcement learning algorithm, the collaborative optimization intelligent energy-saving control strategy is evaluated and iteratively updated to obtain an optimized intelligent energy-saving control strategy; Edge computing technology is used to monitor and quickly respond to the execution process of the optimized intelligent energy-saving control strategy in real time to obtain the target intelligent energy-saving control strategy.

7. The method according to claim 1, characterized in that Blockchain technology is used to record the implementation process and results of the intelligent energy-saving control strategy to obtain a complete energy management log, including: Using blockchain technology to record the implementation process and results of the intelligent energy-saving control strategy in an unalterable manner, and obtain a preliminary energy management log; Using data mining technology to conduct in-depth analysis on the preliminary energy management log, extract key energy usage patterns and abnormal events, and obtain log information; Using natural language processing technology to perform text summarization on the log information and generate a summary report; Using knowledge graph technology to perform correlation analysis on the data and information in the summary report, construct a knowledge graph of energy use behavior, and obtain a structured energy management knowledge graph; The machine learning model is used to perform pattern recognition and trend prediction on the structured energy management knowledge graph, and energy management suggestions are put forward to obtain an energy management log.

8. A stabilizing system for hybrid power supply of a modular nucleic acid laboratory, characterized in that: include: The collection module uses a variety of sensors installed inside and outside the modular nucleic acid laboratory to collect environmental parameters, power consumption data, and renewable energy generation efficiency in real time to obtain a multi-dimensional data set; An analysis module, used to analyze the multi-dimensional data set using a deep learning algorithm to obtain a peak power demand forecast and a power generation potential forecast of renewable energy; A prediction module, for optimizing the charging and discharging plan based on the power demand peak prediction and the power generation potential prediction of renewable energy using a genetic algorithm to obtain a dynamic energy management strategy; An adjustment module is used to, when detecting that the external power grid is unstable, use the dynamic energy management strategy to start the emergency response mechanism, switch to the joint power supply mode of the energy storage system and the backup generator, and adjust the proportion of each power supply in the joint power supply mode through a reinforcement learning algorithm to obtain an energy configuration plan; An adjustment module, used to dynamically adjust the working state of the equipment by using a fuzzy logic control system to the energy configuration scheme, and obtain an intelligent energy-saving control strategy for non-critical equipment; A recording module is used to record the implementation process and results of the intelligent energy-saving control strategy using blockchain technology to obtain a complete energy management log; The evaluation module is used to evaluate the energy management log using a machine learning model at a preset time node to obtain power supply strategy optimization suggestions.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a stabilization method for hybrid power supply of a modular nucleic acid laboratory 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 stabilization method for hybrid power supply of a modular nucleic acid laboratory as described in any one of claims 1 to 7 is implemented.

Images