Intelligent cabin multi-cabin cooperative intelligent management control system and method thereof

Abstract

The invention discloses an intelligent cabin multi-cabin collaborative intelligent management control system and method, and relates to the technical field of comprehensive energy management, and the intelligent cabin multi-cabin collaborative intelligent management control system comprises an information collection module, an information flow management module, an energy flow module, an energy prediction module and an energy sharing module. The subsequent data processing steps are simplified, the uniformity and consistency of the data are ensured, and the processing complexity is reduced. The genetic algorithm is adopted to optimize the energy flow path, the loss problem in the energy transmission process is clearly considered, and the loss in energy flow is reduced. Through dynamic selection of the paths, more efficient connection can be established between energy supply and demand, loss minimization in the energy transmission process is ensured, and thus the overall system efficiency is improved. The scheduling module is combined with an energy prediction result, energy distribution in the system can be scheduled in real time, and load demand changes are dynamically responded.

Description

Technical Field

[0001] The present invention relates to the field of integrated energy technology, and specifically to a smart cabin multi-compartment collaborative intelligent management control system and method thereof. Background Art

[0002] With the rapid development of energy management systems, smart cabins have gradually become critical infrastructure. However, the existing smart cabin management system has many technical problems in dealing with user satisfaction, system stability and emergency response. Specifically, the existing system lacks an effective mechanism for collecting and analyzing user satisfaction data, resulting in system optimization often being out of touch with actual user needs. In addition, the system's response speed and recovery capabilities are insufficient in the face of emergencies, and it lacks a comprehensive emergency plan and rapid response mechanism. These problems have seriously affected the system's reliability and user experience, and are in urgent need of improvement and optimization.

[0003] In the smart cabin, photovoltaic panels, battery packs and electrical equipment are key components of its energy management and use system. Photovoltaic panels are devices that convert solar energy into electrical energy, usually composed of multiple solar cell modules. They absorb sunlight and use the photoelectric effect to generate current, providing renewable clean energy for the smart cabin. This energy source not only reduces dependence on traditional energy, but also reduces carbon emissions, in line with the goal of sustainable development. Battery packs are devices used to store the electricity generated by photovoltaic panels. By storing the excess electricity generated by photovoltaic panels when there is sufficient sunlight, the battery pack can provide power for the smart cabin when there is no sunlight or during peak electricity consumption. The management and optimization of battery packs are the key to energy efficiency control in the smart cabin, which can ensure the effective use of energy and the efficient operation of the system. Electrical equipment is a general term for all electrical appliances inside the smart cabin, including lighting, air conditioning, monitoring equipment, information processing equipment, etc. The energy consumption characteristics and usage patterns of these devices will directly affect the overall energy efficiency and comfort of the smart cabin. The smart cabin adopts an intelligent management system, which can dynamically adjust the operation of electrical equipment according to real-time energy supply and demand, optimize energy use and reduce electricity costs. In general, photovoltaic panels, battery packs and electrical equipment work together in the smart cabin to achieve efficient and sustainable energy use through advanced energy management technology, thereby improving the user's living and working environment.

[0004] Publication number CN118036968A discloses a collaborative optimization scheduling method for a highway IE smart cabin, comprising the following steps: S1: constructing a computing task model based on the system architecture of the highway IE smart cabin; S2: collecting system operation data of the highway IES smart cabin; S3: optimizing and solving the computing task model using decision variables, objective functions and constraints to generate an operation optimization plan; S4: evaluating the operation optimization plan by calculating the operation cost savings rate.

[0005] The shortcomings of the above prior art are mainly reflected in:

[0006] First, the existing computing task model is relatively complex, requiring detailed definition of different types of computing tasks, deadlines, arrival times and other parameters, and load transfer according to different levels of tasks. This method may face the complexity of data processing in actual operation, especially when there are many types of tasks, the calculation of the transfer coefficient matrix of the load transfer model will become more complicated, making it difficult to schedule in real time.

[0007] Second, there is a great deal of uncertainty in factors such as driver charging demand, photovoltaic power generation, and DC load in the IE ES smart cabin system, which increases the difficulty of scheduling. Although the plan takes into account the matching of task scheduling with factors such as electricity prices and photovoltaic power generation, due to the high randomness of driver demand, photovoltaic power generation, and grid electricity prices, the assumptions in the plan (such as uninterruptible tasks, etc.) may be difficult to fully implement in actual operations.

[0008] Third, existing technologies focus on optimizing energy usage by transferring and allocating computing tasks, but task scheduling and load transfer need to be solved through complex optimization models, which will affect the system's real-time response capabilities, especially when facing sudden changes in load demand or fluctuations in energy supply.

[0009] Fourth, existing technologies assume multiple idealized conditions, such as the homogeneity of servers and the non-interruptibility of tasks, which may be difficult to fully meet in actual applications. Especially in heterogeneous environments, the performance and power of servers are different, which affects the actual applicability of these assumptions to the optimization results.

[0010] Fifth, the existing technology does not specifically mention the optimization of energy flow paths, and mainly focuses on the matching of task scheduling and power configuration, ignoring the optimization of energy loss during transmission. This may cause the system to generate large energy losses during energy transmission and distribution. Summary of the invention

[0011] The purpose of the present invention is to provide a smart cabin multi-warehouse collaborative intelligent management control system and method thereof to solve the problems raised in the above-mentioned background technology.

[0012] To achieve the above object, the present invention provides the following technical solutions:

[0013] Smart cabin multi-warehouse collaborative intelligent management and control system includes:

[0014] Information collection module: The information collection module is used to collect real-time energy data and information data of each warehouse, including the input current of the smart cabin, the input voltage, the current consumed by the load, the voltage consumed by the load and the energy stored;

[0015] Information flow management module: The information flow management module is used to generate a state monitoring matrix from the real-time energy data and information data of each warehouse, and perform data standardization processing on the matrix;

[0016] Energy flow module: The energy flow module is used to define the energy flow path, build an energy flow network by defining the energy flow path, establish an energy flow model, and optimize the energy flow path with the goal of minimizing the loss during energy transmission;

[0017] Energy prediction module: The energy prediction module is used to construct a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, and normalize the extracted historical data. The processed historical data is used as a training set, and the load demand of the smart cabin in the next hour is used as a label to train the long short-term memory network model.

[0018] Energy sharing module: The energy sharing module is used to establish a shared energy pool, update the status of the energy pool in real time through a status monitoring matrix, and set energy sharing rules and strategies.

[0019] Furthermore, a state monitoring matrix is ​​generated based on the real-time energy data and information data of each warehouse, and the state monitoring matrix is:

[0020]

[0021] Among them, V exi (t) represents the load voltage of the i-th smart cabin at time t, I exi (t) represents the load current of the i-th smart cabin at time t, I ini (t) represents the input current of the ith smart cabin at time t, B i (t) represents the energy stored in the i-th smart cabin at time t, V ini (t) represents the input voltage of the i-th smart cabin at time t.

[0022] Furthermore, the energy flow path is defined as the energy transmission route from the power source to the load and the energy storage device, the node is defined as each smart cabin and the photovoltaic panels, battery packs and power-consuming devices in each smart cabin, the edge is defined as the energy transmission channel between each node, and the energy flow network is constructed by nodes and edges. The load voltage, load current, input current and input voltage of each smart cabin are extracted, and the extracted data are integrated to form a comprehensive data set to calculate the input energy input and output. The formula is:

[0023] P in =V exi (t)·I exi (t)

[0024] p ex =V ini (t)·I ini (t)

[0025] Among them, P in is the input power, p ex is the output power;

[0026] The integrated data is used to analyze the energy input and output of each warehouse, generate energy flow reports, and evaluate the current balance of energy supply and demand.

[0027] Furthermore, the input voltage, input current, output voltage and output current of each path in the energy flow network are collected, the energy input and energy output of each path are calculated, and the energy loss in the transmission process is calculated according to the input power and output power of each path. The formula for the energy loss is:

[0028] loss(E tra , i) = E input，i ―E output，i

[0029] Among them, loss(E tra , i) represents the energy loss of the i-th path during the energy transmission process, E input，i represents the energy input of the ith path, E output，i represents the energy output of the i-th path;

[0030] Construct the objective function, the objective function is:

[0031]

[0032] Where N is the number of all paths in the system;

[0033] Genetic algorithm is used to optimize the energy flow path.

[0034] Furthermore, the steps of optimizing the energy flow path by using the genetic algorithm are as follows:

[0035] The initial population is randomly generated. Each individual in the population represents a possible energy flow path. Each individual consists of a node and an edge.

[0036] Calculate the fitness of each individual, and the fitness function is defined as:

[0037]

[0038] Among them, Fitness(x) represents the fitness of the i-th individual;

[0039] Randomly select a number of individuals from the population to compete, and select the individual with the highest fitness;

[0040] Generate new individuals through crossover operation, select two parent individuals, randomly exchange some of their genes (nodes or edges of the path), generate two new individuals, randomly select some genes in the individuals for mutation, the mutation is to randomly change a node, change the direction of the path or change the connection of the edge, and control the frequency of mutation to between 1% and 5%;

[0041] Repeat crossover and mutation, evaluate its fitness after each crossover and mutation, eliminate individuals with low fitness, retain individuals with high fitness, and set the fitness threshold to 0.95

[0042] The individual with the highest fitness is selected from the final population as the optimal energy flow path.

[0043] Furthermore, the historical data of the previous 24 hours is extracted from the state monitoring matrix, and the data is scaled to the [0,1] interval using normalization, and the formula is:

[0044]

[0045] Among them, X norm represents the standardized data, X represents the historical data that needs to be standardized, and X max Indicates the maximum value of the same type of historical data extracted in the previous 24 hours, X max Indicates the minimum value of the same type of historical data extracted in the previous 24 hours.

[0046] Furthermore, the energy input and energy output of each smart cabin are calculated according to the data in the state monitoring matrix. The available residual energy of each smart cabin is calculated through the energy input and energy output of each smart cabin. The available residual energy of each smart cabin is managed in a unified manner to establish a virtual energy pool. The state of the energy pool is updated in real time through the state monitoring matrix. The formula is:

[0047] E excess (t) = E generated (t)―E consumed (t)―B(t)

[0048] Among them, E excess (t) represents the excess energy of each bin at time t, E generated (t) represents the input energy of each bin at time t, E consumed (t) is the output energy of each bin at time t, and B(t) is the storage energy of each bin at time t;

[0049] Each smart cabin decides whether to participate in energy sharing based on the real-time energy status:

[0050] If E excess (t)>0, the smart cabin injects energy into the shared pool;

[0051] If E excess (t)<0, the smart cabin obtains energy from the shared pool;

[0052] If E excess (t) = 0, the smart cabin is in an energy balance state, neither obtaining energy from the shared pool nor injecting energy into the shared pool.

[0053] Furthermore, according to the state monitoring matrix and the energy flow path model, the energy state of each warehouse is judged in real time. According to the prediction results of the long short-term memory network model, the system adjusts the energy sharing strategy in advance and sets the sharing priority rules:

[0054] High-demand warehouses are prioritized: warehouses with high load demand, low input power, and energy storage that is close to exhaustion are given priority to obtain energy from the shared pool;

[0055] Low-demand bins come second: Bins with lower load demands come second;

[0056] Priority in supplying excess energy warehouses: Excess energy warehouses are given priority in being injected into the shared pool.

[0057] A smart cabin multi-warehouse collaborative intelligent management and control method, the smart cabin multi-warehouse collaborative intelligent management and control method is executed by the above-mentioned smart cabin multi-warehouse collaborative intelligent management and control system, including:

[0058] Step 1: Collecting real-time energy data and information data of each warehouse, including the input current of the smart cabin, the input voltage, the current consumed by the load, the voltage consumed by the load, and the energy stored;

[0059] Step 2: Generate a status monitoring matrix using the real-time energy data and information data of each warehouse, and perform data standardization on the matrix;

[0060] Step 3: Define the energy flow path, build an energy flow network by defining the energy flow path, establish an energy flow model, and optimize the energy flow path with the goal of minimizing the loss in the energy transmission process;

[0061] Step 4: Build a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, and normalize the extracted historical data. Use the processed historical data as the training set, and use the load demand of the smart cabin in the next hour as the label to train the long short-term memory network model.

[0062] Step 5: Establish a shared energy pool, update the status of the energy pool in real time through the status monitoring matrix, and set the rules and strategies for energy sharing.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The present invention simplifies the energy supply and demand balance assessment and dynamically adjusts energy allocation, thereby reducing reliance on complex computing models and achieving faster and more efficient real-time scheduling, especially with greater flexibility when processing a large number of computing tasks. By real-time monitoring and adjusting the energy supply and demand balance, the present invention flexibly responds to changes in energy supply and demand, reduces reliance on strict assumptions, and can better handle uncertainty.

[0065] The present invention greatly improves the response speed of the system through the clear design of energy flow path, and can quickly adjust when facing sudden load demand or energy fluctuations to ensure the flexibility and stability of the system. The scheduling module combines the energy prediction results, can schedule the energy distribution in the system in real time, and dynamically respond to changes in load demand.

[0066] The present invention can more flexibly adapt to the uncertainty in the actual environment. Through energy prediction and genetic algorithm optimization, it can dynamically respond to fluctuations in energy supply, clearly optimize the energy flow path, reduce energy loss during transmission, and ensure efficient energy transmission and use, thereby significantly improving the overall energy utilization efficiency of the system. The genetic algorithm is used to optimize the energy flow path, clearly consider the loss problem during energy transmission, and reduce the loss in energy flow. Through the dynamic selection of the path, a more efficient connection can be established between energy supply and demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0068] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0070] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0071] Example:

[0072] See also Figure 1 , the present invention provides a technical solution:

[0073] Smart cabin multi-warehouse collaborative intelligent management and control system includes:

[0074] Information collection module: The information collection module is used to collect real-time energy data and information data of each warehouse. The real-time energy data and information data of each warehouse include the input current of the smart cabin, the input voltage, the current consumed by the load, the voltage consumed by the load and the energy stored;

[0075] Hall effect current sensors are selected for monitoring current, suitable for different current ranges (such as 20A, 50A, 100A, etc.).

[0076] Select voltage sensors to measure the DC voltage of photovoltaic power generation and the AC voltage of energy storage equipment. Use energy storage monitoring sensors to obtain battery power, charging and discharging status, and voltage changes. Install them at the output end of photovoltaic power generation, the input and output ends of energy storage equipment, and the load port to ensure the real-time acquisition of current and voltage. The energy storage status sensor is installed on the energy storage equipment (such as battery pack) in the smart cabin to monitor its power and charging and discharging process. Ensure that the sensor is connected to the data collector or data gateway via the CAN bus to provide a unified interface. Collect data from various sensors in real time through a data gateway (such as Ardu ino, Raspberry Pi, or industrial-grade gateway device). Set the acquisition frequency to once per second or once per minute, and adjust the specific frequency according to the dynamic changes in energy flow. Transmit data from the sensor to a local server or cloud database via Wi-Fi. Perform real-time verification of the collected data to prevent data packet loss or transmission errors, and ensure the integrity and accuracy of the data. Regularly check whether the collected data has abnormal values ​​or exceeds the reasonable range (such as sudden and large fluctuations in voltage or current values), and filter the data.

[0077] Information flow management module: The information flow management module is used to generate a status monitoring matrix with the real-time energy data and information data of each warehouse, and standardize the data of the matrix; the data of the real-time monitoring matrix will change in real time. The role of the real-time monitoring matrix data change is to identify abnormalities in a timely manner, optimize energy distribution, and respond quickly by continuously tracking and analyzing the operating status of each node or component in the system. This monitoring helps to improve the stability and reliability of the system, ensure the effectiveness of energy flow and task scheduling in a dynamic environment, avoid potential failures or performance degradation, and provide data support for the continuous optimization of the system.

[0078] Energy flow module: The energy flow module is used to define the energy flow path. By defining the energy flow path, an energy flow network is constructed, and an energy flow model is established. The energy flow path is optimized with the optimization goal of minimizing the loss during energy transmission. By setting the goal of optimizing the energy flow path to minimize the loss during energy transmission, this module can effectively improve the efficiency and stability of energy flow.

[0079] Energy prediction module: The energy prediction module is used to build a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, and normalize the extracted historical data. The processed historical data is used as the training set, and the load demand of the smart cabin in the next hour is used as the label to train the long short-term memory network model. By constructing a long short-term memory network model, this module can accurately predict the load demand of the smart cabin in the next hour, providing support for subsequent energy sharing.

[0080] In this embodiment, the long short-term memory network is referred to as (LSTM). LSTM is a special recursive neural network whose main advantage is that it can effectively capture long-term dependencies in sequence data. Compared with traditional recursive neural networks, LSTM can solve the problem of gradient disappearance or explosion by introducing a gating mechanism (including input gate, forget gate and output gate) to control the flow of information, which makes it perform well when processing long sequence data. LSTM is widely used in fields such as time series prediction, natural language processing and speech recognition because it improves the prediction accuracy and robustness of the model by filtering unnecessary interference while maintaining information.

[0081] Energy sharing module: The energy sharing module is used to establish a shared energy pool, update the status of the energy pool in real time through the status monitoring matrix, and set the rules and strategies for energy sharing. The energy sharing mechanism based on information flow realizes energy sharing and dynamic scheduling between warehouses through real-time monitoring and prediction of the energy status of each warehouse. This module ensures that energy flows efficiently between warehouses to meet their respective load requirements and maximize the overall energy efficiency of the system. Under the guidance of sharing priorities and rules, the system can flexibly respond to changes in energy demand in each warehouse to ensure the stability and sustainable operation of the system.

[0082] Furthermore, a state monitoring matrix is ​​generated based on the real-time energy data and information data of each warehouse. The state monitoring matrix is:

[0083]

[0084] Among them, V exi (t) represents the load voltage of the i-th smart cabin at time t, I exi (t) represents the load current of the i-th smart cabin at time t, I ini (t) represents the input current of the ith smart cabin at time t, B i (t) represents the energy stored in the i-th smart cabin at time t, V ini (t) represents the input voltage of the i-th smart cabin at time t.

[0085] In this embodiment, the state monitoring matrix is ​​a two-dimensional matrix used to represent the energy state of each warehouse in real time. Each row of the matrix corresponds to a warehouse, and the column represents the different state data of the warehouse. The state monitoring matrix is ​​an efficient tool for real-time monitoring and analysis of the state and performance of each component in the system. Its main advantage is that it can centrally integrate data from different sources, so that system managers can quickly identify potential problems and respond in a timely manner. In a visual way, the state monitoring matrix provides intuitive indicators and trend analysis to help optimize resource allocation, improve system efficiency, and enhance fault warning capabilities. In addition, the state monitoring matrix also supports the comparison and analysis of historical data, promotes continuous improvement and decision support of the system, thereby improving the reliability and stability of the overall operation. Compared with the existing technology, the use of the state monitoring matrix has a significant advantage in that it can monitor the operating status of photovoltaic panels, battery packs and electrical equipment in the smart cabin in real time, so as to promptly identify faults, abnormalities or inefficient energy utilization. This real-time monitoring mechanism can quickly respond to changes in the system, dynamically adjust the energy scheduling strategy, and avoid unnecessary energy waste and system crashes. Compared with the comparison scheme, the state monitoring matrix provides higher system stability and reliability, and improves the efficiency and flexibility of overall energy management.

[0086] Furthermore, the energy flow path is defined as the energy transmission route from the power source to the load and energy storage device. Each path consists of multiple nodes (such as photovoltaic units, energy storage devices, loads, etc.) and edges (energy transmission channels) connecting these nodes. The nodes are defined as the photovoltaic panels, battery packs and electrical equipment in each smart cabin, and the edges are defined as the energy transmission channels between each node. The attributes of the edges include transmission capacity and efficiency. The energy flow network is constructed by nodes and edges. The preliminary energy flow path is set according to the geographical location, energy demand and production capacity of the smart cabin, and the basic parameters of each edge, such as the maximum transmission capacity and loss rate, are determined. The load voltage, load current, input current and input voltage of each smart cabin are extracted, and the extracted data are integrated to form a comprehensive data set. The input energy input and output are calculated. The formula is:

[0087] P in =V exi (t)·I exi (t)

[0088] p ex =V ini (t)·I ini (t)

[0089] Among them, P in is the input power, p ex is the output power;

[0090] In this embodiment, the energy flow path is defined to ensure that energy can be efficiently and orderly transmitted in the system, avoiding energy loss or delay during the transmission process. By clarifying the energy flow path, the system can more reasonably plan the energy transmission line, reduce energy loss during the transmission process, and improve energy supply efficiency. Its role is to optimize the speed and stability of energy transmission, ensure that energy can be distributed to the required smart cabin in a timely and accurate manner, and thus improve the overall operating efficiency and reliability of the system.

[0091] In this embodiment, the purpose of calculating the input power and output power is to accurately evaluate the conversion and transmission efficiency of energy within the system. The input power reflects the available energy provided by photovoltaic panels and other energy sources, while the output power indicates the energy actually consumed by the electrical equipment. By comparing the two, the system can identify the links of energy loss, optimize the energy flow path, ensure the efficient use of energy, reduce unnecessary losses, and thus improve the overall energy management efficiency and economy of the smart cabin. In addition, this process also helps to dynamically adjust the charging and discharging strategy of the battery pack to ensure the balance of energy supply and demand under different load conditions.

[0092] The integrated data is used to analyze the energy input and output of each warehouse, compare the energy input and output of each warehouse, calculate the energy surplus or shortage, and generate corresponding charts (such as bar charts or line charts) to intuitively display the energy status and generate energy flow reports to evaluate the current balance of energy supply and demand.

[0093] In this embodiment, the purpose of evaluating the current energy supply and demand balance is to grasp the energy demand and supply of each smart cabin in the system in real time and ensure that the energy sharing mechanism can operate effectively. By evaluating the supply and demand balance, potential energy shortages or surpluses can be discovered in a timely manner, and corresponding adjustments can be made to avoid uneven energy distribution or waste. Its role is to help the system maintain efficient and stable operation in a dynamic environment, ensure that each smart cabin completes its tasks under the premise of sufficient energy, and improve the overall energy utilization and reliability of the system.

[0094] Furthermore, the input voltage, input current, output voltage and output current of each path in the energy flow network are collected, the energy input and energy output of each path are calculated, and the energy loss in the transmission process is calculated according to the input power and output power of each path. The formula for energy loss is:

[0095] loss(E tra , i) = E input，i ―E output，i

[0096] Among them, loss(E tra , i) represents the energy loss of the i-th path during the energy transmission process, E input，irepresents the energy input of the ith path, E output，i represents the energy output of the i-th path;

[0097] In this embodiment, the purpose of calculating energy loss through energy input and energy output is to identify efficiency bottlenecks in the system and optimize energy utilization. By determining the energy loss in different links (such as power generation, storage, and transmission), the system can accurately locate the source of energy loss, so as to take targeted measures, such as improving equipment performance, adjusting power scheduling strategies, or reducing losses in transmission. This process can significantly improve the energy efficiency of the overall system, reduce energy waste, and ensure that the smart cabin can provide maximum energy output with minimal energy loss during operation, thereby reducing operating costs and improving sustainability.

[0098] Construct the objective function, the objective function is:

[0099]

[0100] Where N is the number of all paths in the system;

[0101] In this embodiment, the purpose of constructing the objective function is to provide a clear direction and standard for the optimization of the system. The objective function usually combines the key parameters of the system such as energy input, output, and loss to set goals such as minimizing losses, maximizing energy efficiency, reducing costs, or balancing energy supply and demand. Through this mathematical expression, the system can automatically optimize according to the preset goals to ensure that the selection of energy flow paths conforms to the global optimization strategy, thereby improving the overall operating efficiency, stability, and sustainability of the smart cabin.

[0102] Genetic algorithm is used to optimize the energy flow path.

[0103] In this embodiment, the genetic algorithm is an optimization algorithm based on the principles of natural selection and genetics, which simulates the biological evolution process to find the optimal solution to the problem. Its main advantage is that it can effectively handle complex, high-dimensional search spaces and is applicable to various optimization problems, including function optimization, combinatorial optimization, and parameter tuning. The genetic algorithm iteratively generates new candidate solutions through operations such as selection, crossover, and mutation, and continuously retains solutions with higher fitness, thereby gradually approaching the optimal solution. When processing multi-peak functions or having multiple local optimal solutions, the genetic algorithm can jump out of the local optimum and find the global optimal solution. Therefore, it has been widely used in many practical applications, such as engineering design, scheduling problems, and machine learning.

[0104] Furthermore, the steps of optimizing the energy flow path using genetic algorithm are as follows:

[0105] The initial population is randomly generated. Each individual in the population represents a possible energy flow path. Each individual consists of a node and an edge.

[0106] Calculate the fitness of each individual. The fitness reflects the quality of the path. The higher the fitness, the lower the loss. The fitness function is defined as:

[0107]

[0108] Among them, Fitness(x) represents the fitness of the xth individual;

[0109] Traverse each individual, calculate its fitness value, and sort the individuals according to the fitness value for subsequent selection operations.

[0110] Randomly select a number of individuals from the population to compete, and select the individual with the highest fitness;

[0111] Generate new individuals through crossover operation. Select two parent individuals, randomly exchange some of their genes (nodes or edges of the path), and generate two new individuals. The crossover method can be single-point crossover, multi-point crossover or uniform crossover, etc. Example: Assume that individuals A and B are represented as paths:

[0112] A:[PV unit 1, energy storage device 1, load 1]

[0113] B:[PV unit 2, energy storage device 2, load 2]

[0114] After crossover, new individuals C and D are obtained:

[0115] C:[PV unit 1, energy storage device 2, load 1]

[0116] D:[PV unit 2, energy storage device 1, load 2

[0117] Randomly select certain genes in individuals for mutation to increase the diversity of the population. Mutation is to randomly change a node, change the direction of the path, or change the connection of the edge, and control the frequency of mutation to between 1% and 5%;

[0118] Repeat crossover and mutation, evaluate the fitness after each crossover and mutation, eliminate individuals with low fitness, retain individuals with high fitness, and set the fitness threshold to 0.95;

[0119] The individual with the highest fitness is selected from the final population as the optimal energy flow path.

[0120] In this embodiment, through the above steps, the genetic algorithm can efficiently optimize the energy flow path, minimize energy transmission loss, and improve the overall energy efficiency of the system. This method combines the principles of natural selection and genetics, and uses mechanisms such as fitness evaluation, selection, crossover and mutation to explore and find the optimal solution while ensuring the diversity and convergence of the algorithm.

[0121] In this embodiment, the genetic algorithm has a powerful global optimization capability and can effectively find the optimal solution in complex multi-objective problems. For the energy sharing mechanism, multiple factors need to be considered (such as the remaining energy of each smart cabin, priority, supply and demand balance, etc.) to achieve optimal energy allocation, and these factors often constitute a complex multi-objective optimization problem. By simulating the natural evolution process and using operations such as selection, crossover, and mutation, the genetic algorithm can quickly search a vast solution space to find the optimal or near-optimal energy allocation solution, thereby improving the overall efficiency and fairness of the system. Its role is to help the system dynamically adjust energy sharing decisions to ensure optimal resource allocation under different conditions.

[0122] Furthermore, the historical data of the previous 24 hours is extracted from the state monitoring matrix. If part of the data of a warehouse is missing at a certain moment, the missing data can be filled using linear interpolation or spline interpolation to ensure the integrity of the state monitoring matrix. Use normalization to scale the data to the [0,1] interval, the formula is:

[0123]

[0124] Among them, X norm represents the standardized data, X represents the historical data that needs to be standardized, and X max Indicates the maximum value of the same type of historical data extracted in the previous 24 hours, X max Indicates the minimum value of the same type of historical data extracted in the previous 24 hours.

[0125] In this embodiment, normalization is the process of converting data of different scales or distributions into a uniform range. The main benefit of this technology is that it improves the comparability of data and the training efficiency of the model. By eliminating the dimensional differences between features, normalization can accelerate the convergence speed of optimization algorithms such as gradient descent, avoid certain features dominating the learning process of the model, and thus improve the performance and accuracy of the model. In addition, normalization can also enhance the robustness of the model to outliers, making data analysis and result interpretation more reliable. Therefore, normalization in the data preprocessing stage is an important step to ensure the success of subsequent analysis and modeling.

[0126] Furthermore, the energy input and energy output of each smart cabin are calculated based on the data in the status monitoring matrix. The available remaining energy of each smart cabin is calculated through the energy input and energy output of each smart cabin. The available remaining energy of each smart cabin is managed in a unified manner to establish a virtual energy pool. In order to prevent excessive concentration of energy in a certain warehouse, the virtual energy pool will set the upper and lower limits of shared energy according to the maximum storage capacity of each warehouse. When the energy of a warehouse overflows the upper limit, it will be shared with the warehouse with insufficient energy first. The status of the energy pool is updated in real time through the status monitoring matrix. The formula is:

[0127] E excess (t) = E generated (t)―E consumed (t)―B(t)

[0128] Among them, E excess (t) represents the excess energy of each bin at time t, E generated (t) represents the input energy of each bin at time t, E consumed (t) is the output energy of each bin at time t, and B(t) is the storage energy of each bin at time t;

[0129] In this embodiment, the purpose of calculating the available remaining energy of each smart cabin is to determine the supply and demand status of each smart cabin in the energy sharing network and provide data support for energy sharing decisions. By accurately calculating the remaining available energy of each smart cabin, the system can identify which smart cabins have excess energy to share and which smart cabins need additional energy replenishment, thereby achieving accurate and efficient energy scheduling and allocation, ensuring the maximum energy utilization in the entire network, while maintaining the stable operation and energy supply balance of each smart cabin.

[0130] Set the conditions for participating in energy sharing. Warehouses that meet the following conditions will be given priority to join the sharing:

[0131] Energy surplus warehouse: The warehouse whose power generation exceeds the demand and whose energy storage equipment is close to full load can actively share the excess energy.

[0132] Energy-deficient warehouses: Warehouses where the current photovoltaic power generation is insufficient to meet the load demand and the power level of the energy storage device is below the threshold can obtain energy from the shared battery.

[0133] Each smart cabin decides whether to participate in energy sharing based on the real-time energy status:

[0134] If E excess (t)>0, the smart cabin injects energy into the shared pool;

[0135] If E excess (t)<0, the smart cabin obtains energy from the shared pool;

[0136] If E excess (t) = 0, the smart cabin is in an energy balance state, neither obtaining energy from the shared pool nor injecting energy into the shared pool.

[0137] In this embodiment, the conditions for participating in energy sharing are set to ensure fairness, stability and efficiency in the energy sharing process. By setting conditions, such as the minimum remaining energy threshold, sharing priority, load demand, etc., it is possible to avoid excessive sharing of individual smart cabins leading to insufficient energy, or the inability to guarantee their own needs at critical moments. Its role is to ensure the sustainability of energy sharing, prevent individual cabins from falling into energy shortages due to energy sharing, and at the same time improve the overall energy utilization efficiency and reliability of the system through a regularized sharing mechanism.

[0138] Furthermore, based on the state monitoring matrix and the energy flow path model, the energy state of each warehouse is judged in real time. Based on the prediction results of the long short-term memory network model, the system adjusts the energy sharing strategy in advance and sets the sharing priority rules:

[0139] High-demand warehouses are prioritized: warehouses with high load demand, low input power, and energy storage that is close to exhaustion are given priority to obtain energy from the shared pool;

[0140] Low-demand bins come second: Bins with lower load demands come second;

[0141] Priority in supplying excess energy warehouses: Excess energy warehouses are given priority in being injected into the shared pool.

[0142] In this embodiment, the sharing priority rule is set to reasonably allocate limited resources when the energy supply is insufficient, ensuring that the key units of the system or high-priority smart cabins can get energy first. Its role is to ensure that important cabins (such as cabins that run core functions or carry key tasks) will not be interrupted due to insufficient energy by setting priorities, thereby improving the stability and efficiency of the entire system. At the same time, sharing priorities help optimize the energy flow path, making energy resource allocation more efficient and reasonable.

[0143] The system dynamically adjusts the amount of energy shared based on the predicted energy supply and demand. If the demand of a warehouse is predicted to increase in the future, the system will allocate more energy to it before its demand increases. On the contrary, if the demand of a warehouse decreases, the allocation will be reduced. In order to cope with sudden energy demand, the system will keep a certain amount of energy reserves in the shared pool, which can be quickly called when a warehouse has a sudden energy shortage. When a warehouse suddenly has a large energy gap and cannot meet the demand through local energy storage, the system will give priority to calling energy from the shared pool and urgently allocate it to the warehouse. When an emergency occurs, the sharing rules may be temporarily adjusted. For example, priority is given to warehouses with urgent needs, while energy extraction from warehouses with non-urgent needs is restricted. The effect of the energy sharing mechanism is evaluated by monitoring indicators such as energy utilization efficiency before and after sharing, load balance of each warehouse, and utilization rate of energy storage equipment. The system records the energy efficiency and loss of each energy sharing and generates a report. Compare the energy demand predicted by LSTM with the actual demand, analyze the deviation and gradually optimize the prediction model to improve the accuracy of the sharing mechanism. Re-evaluate the energy transmission path based on the path optimization feedback of each energy sharing, and make dynamic optimization adjustments. Optimize the sharing strategy based on the evaluation results of the sharing effect. For example, if a warehouse always consumes too much energy during load peaks, its priority can be adjusted or storage can be increased to reduce its reliance on the shared pool.

[0144] See also Figure 2 The present invention also provides a smart cabin multi-warehouse collaborative intelligent management and control method, which is executed by the above-mentioned smart cabin multi-warehouse collaborative intelligent management and control system, including:

[0145] Step 1: Collect the real-time energy data and information data of each warehouse, including the input current and input voltage of the smart cabin, the current consumed by the load, the voltage consumed by the load, and the energy stored;

[0146] Step 2: Generate a status monitoring matrix with the real-time energy data and information data of each warehouse, and standardize the matrix data;

[0147] Step 3: Define the energy flow path, build an energy flow network by defining the energy flow path, establish an energy flow model, and optimize the energy flow path with the goal of minimizing the loss in the energy transmission process;

[0148] Step 4: Build a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, and normalize the extracted historical data. Use the processed historical data as the training set, and use the load demand of the smart cabin in the next hour as the label to train the long short-term memory network model.

[0149] Step 5: Establish a shared energy pool, update the status of the energy pool in real time through the status monitoring matrix, and set the rules and strategies for energy sharing.

[0150] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0151] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. The smart cabin multi-warehouse collaborative intelligent management and control system is characterized by: include: An information collection module, which is used to collect real-time energy data and information data of each compartment, including the input current of the smart cabin, the input voltage, the current consumed by the load, the voltage consumed by the load, and the energy stored; An information flow management module, the information flow management module is used to generate a state monitoring matrix from the real-time energy data and information data of each warehouse, and perform data standardization processing on the matrix; Energy flow module, which is used to define the energy flow path, build an energy flow network by defining the energy flow path, establish an energy flow model, and optimize the energy flow path with the goal of minimizing the loss during energy transmission: An energy prediction module is used to construct a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, normalize the extracted historical data, use the processed historical data as a training set, and use the load demand of the smart cabin in the next hour as a label to train the long short-term memory network model; An energy sharing module is used to establish a shared energy pool, update the state of the energy pool in real time through a state monitoring matrix, and set rules and strategies for energy sharing.

2. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 1 is characterized by: A state monitoring matrix is ​​generated based on the real-time energy data and information data of each warehouse, and the state monitoring matrix is: Among them, V exi (t) represents the load voltage of the i-th smart cabin at time t, I exi (t) represents the load current of the i-th smart cabin at time t, I ini (t) represents the input current of the i-th smart cabin at time t, B i (t) represents the energy stored in the i-th smart cabin at time t, V ini (t) represents the input voltage of the i-th smart cabin at time t, and S(t) represents the state monitoring matrix.

3. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 2 is characterized by: The energy flow path is defined as the energy transmission route from the power source to the load and the energy storage device. The node is defined as each smart cabin and the photovoltaic panels, battery packs and power-consuming devices in each smart cabin. The edge is defined as the energy transmission channel between each node. The energy flow network is constructed by nodes and edges. The load voltage, load current, input current and input voltage of each smart cabin are extracted. The extracted data are integrated to form a comprehensive data set to calculate the input energy input and output. The formula is: P in =V exi (t)·I exi (t) p ex =V ini (t)·I ini (t) Among them, P in is the input power, p ex is the output power; The integrated data is used to analyze the energy input and output of each warehouse, generate energy flow reports, and evaluate the current balance of energy supply and demand.

4. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 3 is characterized by: The input voltage, input current, output voltage and output current of each path in the energy flow network are collected, the energy input and energy output of each path are calculated, and the energy loss in the transmission process is calculated according to the input power and output power of each path. The formula for the energy loss is: loss(E tra ,i)=E input ,iE output，i Among them, loss(E tra , i) represents the energy loss of the i-th path during the energy transmission process, E input，i represents the energy input of the ith path, E output，i represents the energy output of the i-th path; Construct the objective function, the objective function is: Where N is the number of all paths in the system; Genetic algorithm is used to optimize the energy flow path.

5. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 4 is characterized by: The steps of optimizing the energy flow path using the genetic algorithm are as follows: The initial population is randomly generated. Each individual in the population represents a possible energy flow path. The genes of each individual include nodes and edges. Calculate the fitness of each individual, and the fitness function is defined as: Among them, Fitness(x) represents the fitness of the xth individual; Randomly select a number of individuals from the population to compete, and select the individual with the highest fitness; Generate new individuals through crossover operation, select two parent individuals, randomly exchange some of their genes, generate two new individuals, randomly select some genes in the individuals for mutation, the mutation is to randomly change a node, change the direction of the path or change the connection of the edge, and control the frequency of mutation to between 1% and 5%; Repeat crossover and mutation, evaluate the fitness after each crossover and mutation, eliminate individuals with low fitness, retain individuals with high fitness, and set the fitness threshold to 0.95; The individual with the highest fitness is selected from the final population as the optimal energy flow path.

6. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 2 is characterized by: The historical data of the previous 24 hours are extracted from the state monitoring matrix, and the data are scaled to the [0, 1] interval using normalization. The formula is: Among them, X norm represents the standardized data, X represents the historical data that needs to be standardized, and X max Indicates the maximum value of the same type of historical data extracted in the previous 24 hours, X max Indicates the minimum value of the same type of historical data extracted in the previous 24 hours.

7. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 3 is characterized by: The energy input and energy output of each smart cabin are calculated according to the data in the state monitoring matrix. The available residual energy of each smart cabin is calculated through the energy input and energy output of each smart cabin. The available residual energy of each smart cabin is managed in a unified manner to establish a virtual energy pool. The state of the energy pool is updated in real time through the state monitoring matrix. The formula is: E excess (t)=E generated (t)-E consumed (t)-B(t) Among them, E excess (t) represents the excess energy of each bin at time t, E generated (t) represents the input energy of each bin at time t, E consumed (t) is the output energy of each bin at time t, and B(t) is the storage energy of each bin at time t; Each smart cabin decides whether to participate in energy sharing based on the real-time energy status: If E excess (t)>0, the smart cabin injects energy into the shared pool; If E excess (t)<0, the smart cabin obtains energy from the shared pool; If E excess (t) = 0, the smart cabin is in an energy balance state, neither obtaining energy from the shared pool nor injecting energy into the shared pool.

8. The smart cabin multi-compartment collaborative intelligent management and control system according to claim 7 is characterized by: According to the state monitoring matrix and the energy flow path model, the energy state of each warehouse is judged in real time. According to the prediction results of the long short-term memory network model, the system adjusts the energy sharing strategy in advance and sets the sharing priority rules: High-demand warehouses are prioritized: warehouses with high load demand, low input power, and energy storage that is close to exhaustion are given priority to obtain energy from the shared pool; Low-demand bins come second: Bins with lower load demands come second; Priority in supplying excess energy warehouses: Excess energy warehouses are given priority in being injected into the shared pool.

9. The intelligent management and control method for multi-warehouse collaboration in a smart cabin is characterized by: The smart cabin multi-warehouse collaborative intelligent management and control method is executed by the smart cabin multi-warehouse collaborative intelligent management and control system described in any one of claims 1 to 8, including: Step 1: Collecting real-time energy data and information data of each warehouse, including the input current of the smart cabin, the input voltage, the current consumed by the load, the voltage consumed by the load, and the energy stored; Step 2: Generate a status monitoring matrix using the real-time energy data and information data of each warehouse, and standardize the matrix data: Step 3: Define the energy flow path, build an energy flow network by defining the energy flow path, establish an energy flow model, and optimize the energy flow path with the goal of minimizing the loss in the energy transmission process; Step 4: Build a long short-term memory network model, extract the historical data of the previous 24 hours from the state monitoring matrix, normalize the extracted historical data, use the processed historical data as the training set, and use the load demand of the smart cabin in the next hour as the label to train the long short-term memory network model; Step 5: Establish a shared energy pool, update the status of the energy pool in real time through the status monitoring matrix, and set the rules and strategies for energy sharing.

Images