Light-heat-storage combined system based on clustering analysis

Abstract

The invention provides a light-heat-storage combined system based on clustering analysis, and relates to the technical field of photovoltaic heat pump energy storage. A heat pump module; the energy storage module adopts a clustering analysis method to perform clustering according to energy demand characteristics in different time periods, selects a K-means clustering algorithm for each cluster to calculate an optimal charging and discharging strategy, and stores electric quantity in advance according to a clustering result and stably supplies the electric quantity to a heat pump or other loads when photovoltaic output is unstable; the control module is responsible for monitoring and managing the operation of the whole system and optimizing the coordination work among the components; the power conversion module is used for converting the electric energy generated by the photovoltaic module into alternating current; a heat exchange module; according to the invention, a K-means clustering algorithm is adopted to calculate a charging and discharging strategy, so that the probability that charging and discharging opportunities are missed on the current day, charging at a low point of electricity price and discharging at a high point of electricity price cannot be realized, and the energy storage income is obviously lower than the theoretical income is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic heat pump energy storage, and particularly to a light-thermal-storage combined system based on cluster analysis. Background Art

[0002] A photovoltaic heat pump energy storage system is a system that combines solar photovoltaic power generation, heat pump technology, and energy storage technology, aiming to improve energy utilization efficiency, achieve efficient utilization of renewable energy, and ensure stable energy supply. Such a system is usually used in residential, commercial buildings, and industrial facilities to reduce dependence on fossil fuels, lower carbon emissions, and enhance energy self-sufficiency.

[0003] Currently, the photovoltaic heat pump energy storage system adopts a peak-valley electricity price strategy. Utilizing the difference in peak-valley electricity prices at different times of the power grid, during the valley electricity period, the energy storage module charges from the power grid at a lower price; during the peak electricity period, it discharges to the power grid at a higher price or supplies local loads, achieving peak-valley arbitrage. When calculating, it is first necessary to obtain the peak-valley electricity price periods and corresponding prices of the local power grid, and combine the electricity load prediction and photovoltaic power generation prediction of the photovoltaic heat pump system. During the valley electricity period, if the photovoltaic power generation is less than the maximum charging power of the energy storage module and meets the system operation constraints, the energy storage module charges at the maximum power; during the peak electricity period, if the system electricity load is less than the sum of the photovoltaic power generation and the maximum discharge power of the energy storage module and meets the constraints, the energy storage module discharges to meet the load demand, and the insufficient part is supplemented by photovoltaic power generation. By calculating the charge and discharge powers at different times in this way, a charge and discharge strategy is formed. However, when the photovoltaic heat pump energy storage system adopts the peak-valley electricity price strategy, since the period division and price of the peak-valley electricity price are not fixed and are affected by various factors such as seasons, economic situations, and energy policies, it is difficult for the energy storage module to formulate an accurate operation strategy based on this. If the charge and discharge price threshold is set inappropriately, it may result in missing the charge and discharge opportunities on the same day, being unable to charge at the low electricity price and discharge at the high price, and making the energy storage income significantly lower than the theoretical income.

[0004] Therefore, it is necessary to provide a novel light-thermal-storage combined system based on cluster analysis to solve the above technical problems. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a light-thermal-storage combined system based on cluster analysis.

[0006] The light-thermal-storage combined system based on cluster analysis provided by the present invention includes a photovoltaic module for directly converting sunlight into electrical energy;

[0007] A heat pump module for extracting heat from a low-temperature heat source and transferring it to a device at a higher temperature;

[0008] Energy storage module, which is used to store excess electric energy and release this energy when needed. By using the clustering analysis method, clustering is carried out according to the characteristics of energy demand in different time periods. For each cluster, the K-means clustering algorithm is selected to calculate the optimal charge-discharge strategy. When the photovoltaic output is unstable, the energy storage module reserves electricity in advance according to the clustering results and stably supplies it to the heat pump or other loads;

[0009] Control module, which is responsible for monitoring and managing the operation of the whole system and optimizing the coordinated work among various components;

[0010] Power conversion module, which is used to convert the electric energy generated by the photovoltaic module into alternating current to provide electric energy for the heat pump and other AC electrical equipment;

[0011] Heat exchange module, which is used to realize the heat exchange between the refrigerant and water and air media;

[0012] Auxiliary module, which is used to distribute and control the output of the circuit.

[0013] Preferably, the usage process of the clustering analysis method includes the following steps:

[0014] S1. Data collection and preprocessing. Collect various relevant data of the energy storage module. At the same time, it is also necessary to record the timestamp information and clean the collected data, removing outliers and incorrect data;

[0015] S2. Feature selection and extraction. According to the purpose of clustering analysis and the characteristics of the energy storage module, select appropriate features as the basis for clustering. After selecting the appropriate clustering basis, combine the selected features into a feature vector;

[0016] S3. Clustering algorithm selection and application. Select an appropriate clustering algorithm according to the characteristics of the data and the requirements of clustering analysis, and then apply the selected algorithm to the place where calculation is needed;

[0017] S4. Clustering structure analysis and application. Analyze the clustered structure and optimize the control strategy of the energy storage module according to the results of clustering analysis.

[0018] Preferably, the calculation of the charge-discharge strategy by the K-means clustering algorithm specifically includes the following steps;

[0019] S10. Data collection and preprocessing. Collect data related to the energy storage module, clean the collected data, remove outliers and incorrect data, and normalize the data so that data of different magnitudes can be analyzed on the same scale;

[0020] S20. Feature selection and construction of feature vector. Select features closely related to the charge-discharge strategy and construct a feature vector for each data point;

[0021] S30. Apply the K-means clustering algorithm to determine the number of clusters K through experience or the elbow method. Then randomly initialize K cluster centers, calculate the distances from each data point to these cluster centers, and update the cluster centers according to the existing data points assigned to each cluster.

[0022] S40. Analyze the clustering results to formulate a charge-discharge strategy, calculate the central feature vectors of each cluster, and formulate a charge-discharge strategy based on the characteristics of the cluster centers.

[0023] S50. Strategy optimization and verification. Optimize the formulated charge-discharge strategy according to the operating conditions and performance requirements of the actual system, and use historical data or conduct actual tests to verify the effectiveness of the charge-discharge strategy.

[0024] Preferably, the various relevant data described in step S1 include the state of charge of the battery, charge and discharge current, charge and discharge voltage, power generation power of the photovoltaic system, operating power of the heat pump system, and ambient temperature.

[0025] Preferably, the control module includes a programmable logic controller, a power sensor, a temperature sensor, an inverter, and a switching device. The programmable logic controller is used to precisely control various devices in the system according to the pre-written program logic. The power sensor is used to monitor the power generation power of the photovoltaic panels in real time. The temperature sensor is used to measure the external ambient temperature. The inverter is used to convert the direct current generated by the photovoltaic panels into alternating current. The switching device is used to control the on-off of the circuit.

[0026] Preferably, the auxiliary module includes a monitoring and display device, a safety and protection device, a communication and connection device, and an auxiliary energy device. The monitoring and display device is responsible for collecting the operating data of each device in the system. The safety and protection device is used to prevent the device from being damaged due to overcurrent. The communication and connection device is used to achieve communication between the internal devices of the system and between the system and external devices. The auxiliary energy device is used when the power generation of the photovoltaic system is insufficient and the energy storage device is out of power, and the standby generator can be used as a supplementary energy source.

[0027] Compared with the related technology, a photovoltaic-thermal-energy storage combined system based on clustering analysis provided by the present invention has the following beneficial effects:

[0028] The present invention calculates the charging and discharging strategy by using the K-means clustering algorithm, selects the features closely related to the charging and discharging strategy, constructs a feature vector for each data point, determines the number of clusters K through experience or the elbow method, then randomly initializes K cluster centers, calculates the distances from each data point to these cluster centers, updates the cluster centers according to the existing data points assigned to each cluster, calculates the central feature vector of each cluster, formulates the charging and discharging strategy based on the features of the cluster centers, optimizes the formulated charging and discharging strategy according to the operating conditions and performance requirements of the actual system, and verifies the effectiveness of the charging and discharging strategy by using historical data or conducting actual tests, reducing the probability of missing the charging and discharging opportunities on the same day, being unable to charge at the low electricity price and discharge at the high electricity price, and making the energy storage income significantly lower than the theoretical income. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 FIG. is a logical structure diagram of a photovoltaic-thermal-energy storage combined system based on clustering analysis provided by the present invention;

[0030] Figure 2 FIG. is a flow block diagram of the clustering analysis method provided by the present invention;

[0031] Figure 3 FIG. is a flow block diagram of the calculation of the charging and discharging strategy by the K-means clustering algorithm provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The present invention will be further described below in conjunction with the drawings and embodiments.

[0033] Please refer to Figure 1 , Figure 2 and Figure 3 , where Figure 1 is a logical structure diagram of a photovoltaic-thermal-energy storage combined system based on clustering analysis provided by the present invention; Figure 2 is a flow block diagram of the clustering analysis method provided by the present invention; Figure 3 is a flow block diagram of the calculation of the charging and discharging strategy by the K-means clustering algorithm provided by the present invention.

[0034] In the specific implementation process, as Figures 1 to 3 shown, a photovoltaic-thermal-energy storage combined system based on clustering analysis includes a photovoltaic module for directly converting sunlight into electric energy;

[0035] It should be noted that the main components of the photovoltaic module include: photovoltaic cells, encapsulation materials, glass covers, frames, and junction boxes;

[0036] Its characteristics and advantages are high-efficiency power generation: select high-efficiency photovoltaic materials and technologies to ensure that as much solar energy as possible is collected;

[0037] Long lifespan: High-quality materials and manufacturing processes ensure that the photovoltaic module can operate stably for a long time in harsh environments;

[0038] Low maintenance requirements: Almost no additional maintenance work is required except for regular cleaning;

[0039] Integration and optimization, integrated into the inverter or as an independent controller, adjust the input voltage in real time to operate at the maximum power output point of the photovoltaic module, and combined with the integrated energy management system (EMS), intelligently dispatch the power generation of the photovoltaic module according to factors such as weather forecasts and user needs, maximize the self-use rate, and reduce unnecessary electricity expenses;

[0040] The integrated energy management system (EMS) is a crucial control core in the photovoltaic-thermal-storage combined system based on clustering analysis. It ensures the high efficiency, reliability, and economy of the entire system by integrating and optimizing the operation of multiple energy subsystems. And the sensors of the integrated energy management system deployed in each subsystem are responsible for collecting key operation parameters, including but not limited to voltage, current, temperature, humidity, SOC (state of charge), SOH (state of health);

[0041] Heat pump module, used to extract heat from a low-temperature heat source and transfer it to a device at a higher temperature;

[0042] It should be noted that the working principle of the heat pump module is based on the thermodynamic cycle. By consuming a small amount of electrical energy to drive the compressor to work, it absorbs heat from a low-temperature heat source (such as air, water, or soil), and then transfers it to a high-temperature heat source (such as an indoor heating system or a hot water system). In the photovoltaic-thermal-storage combined system based on clustering analysis, the heat pump module can be driven by the electrical energy generated by the photovoltaic power generation system to achieve efficient energy utilization;

[0043] Moreover, the types of heat pump modules include compressors, evaporators, condensers, and expansion valves. The compressor is the core component of the heat pump, and its function is to compress the refrigerant gas at low temperature and low pressure into a gas at high temperature and high pressure. By consuming electrical energy, the refrigerant is compressed, increasing its temperature and pressure. The evaporator is the component in the heat pump system where the refrigerant absorbs heat. In the evaporator, the refrigerant liquid at low temperature and low pressure evaporates at a relatively low temperature, absorbing heat from the surrounding environment (such as air, water, etc.). The condenser is the component where the refrigerant releases heat. The high-temperature and high-pressure refrigerant gas after being compressed by the compressor enters the condenser, and through heat exchange with the cooling medium (such as water, air, etc.), the heat is released, and the refrigerant gas cools and condenses into a liquid. The expansion valve is located between the condenser and the evaporator, and its main function is to throttle and depressurize the refrigerant. When the high-temperature and high-pressure refrigerant liquid passes through the expansion valve, the pressure and temperature of the refrigerant drop sharply, becoming a low-temperature and low-pressure liquid-mist mixture, creating conditions for the refrigerant to evaporate and absorb heat in the evaporator;

[0044] The energy storage module usually adopts high-performance battery technology (such as lithium-ion batteries), has the ability of fast charging and discharging, and can complete the absorption and release of energy in a short time;

[0045] Moreover, the heat pump module integrates an advanced sensor network and an intelligent control system, which can monitor the state parameters of each subsystem in real time and perform optimal scheduling based on big data analysis and machine learning algorithms;

[0046] Moreover, through cluster analysis, the operating states of the heat pump module can be classified according to different factors such as ambient temperature, light intensity, and heat load, and corresponding operating strategies can be formulated;

[0047] Cluster analysis can help determine the best collaborative working mode between the heat pump module, the photovoltaic system, and the energy storage module. At the same time, according to the heat production situation of the solar thermal system and the energy storage state of the energy storage module, the start-stop and operating power of the heat pump are reasonably controlled to achieve the complementarity and optimal configuration of light, heat, and storage, and improve the overall energy utilization efficiency of the system;

[0048] Performing cluster analysis on the performance indicators of the heat pump module can evaluate its operating performance in the light-thermal-storage combined system, promptly discover potential faults and problems, cluster heat pump modules with similar operating states together, facilitate centralized monitoring and management, and improve the reliability and maintenance efficiency of the system. The performance indicators of the heat pump module include heating efficiency, energy consumption, and operating pressure;

[0049] Energy storage module, which is used to store excess electric energy and release this energy when needed. The clustering analysis method is adopted to perform clustering according to the characteristics of energy demand in different time periods. For each cluster, the K-means clustering algorithm is used to calculate the optimal charge-discharge strategy. When the photovoltaic output is unstable, the energy storage module can reserve electricity in advance according to the clustering results and stably supply it to the heat pump or other loads;

[0050] It should be noted that the K-Means clustering algorithm is used to analyze the operation data of the energy storage module. By clustering the charge-discharge voltage, current, and temperature data of the energy storage module through the K-Means algorithm, the energy storage units with similar operating states can be classified into one category, which is convenient for targeted management and maintenance. The physical model and mathematical model of the energy storage module are established, and clustering is carried out according to the model parameters and operating characteristics;

[0051] The usage process of the clustering analysis method includes the following steps:

[0052] S1. Data collection and preprocessing: Collect various relevant data of the energy storage module. At the same time, it is also necessary to record the timestamp information and clean the collected data to remove outliers and incorrect data;

[0053] It should be noted that various relevant data in step S1 include the state of charge of the battery, charge-discharge current, charge-discharge voltage, power generation power of the photovoltaic system, operating power of the heat pump system, and ambient temperature;

[0054] S2. Feature selection and extraction: According to the purpose of clustering analysis and the characteristics of the energy storage module, select appropriate features as the basis for clustering. After selecting the appropriate clustering basis, combine the selected features into a feature vector;

[0055] It should be noted that features are selected based on the purpose of clustering analysis. If the purpose is to optimize the charge-discharge strategy of the energy storage module, features directly related to the charge-discharge process can be selected, such as the state of charge of the energy storage module, charge-discharge power, and charge-discharge efficiency;

[0056] Features are selected based on the characteristics of the energy storage module. The physical characteristics of the energy storage module determine its basic performance and operating mode. For battery energy storage, battery type, electrode material, and battery size can be selected as features;

[0057] S3. Clustering algorithm selection and application: Select an appropriate clustering algorithm according to the characteristics of the data and the requirements of clustering analysis, and then apply the selected algorithm to the place where calculation is required;

[0058] S4. Clustering structure analysis and application: Analyze the clustered structure and optimize the control strategy of the energy storage module according to the results of clustering analysis.

[0059] The calculation of the charge-discharge strategy by the K-means clustering algorithm specifically includes the following steps;

[0060] S10. Data collection and preprocessing: Collect data related to the energy storage module, clean the collected data, remove outliers and incorrect data, and normalize the data so that data of different magnitudes can be analyzed on the same scale;

[0061] It should be noted that the data related to the energy storage module includes the state of charge (SOC) of the battery, charge-discharge current, charge-discharge voltage, power generation power of the photovoltaic system, operating power of the heat pump system, and ambient temperature;

[0062] S20. Feature selection and construction of feature vectors: Select features closely related to the charge-discharge strategy, and for each data point, construct a feature vector;

[0063] It should be noted that in feature selection, the photovoltaic-heat pump power difference (P pu-hp ) is also important. When P pu-hp >0, there is excess energy for charging. However, when P pu-hp <0, the battery needs to discharge to supplement the energy;

[0064] Among them, the photovoltaic-heat pump power difference (P pu-hp ) refers to the difference between the photovoltaic power generation power and the heat pump consumption power in the photovoltaic-thermal-energy storage combined system based on clustering analysis;

[0065] And the ambient temperature (T enu ) also affects the battery performance and heat pump efficiency;

[0066] The specific form of the feature vector is as follows:

[0067] X = [SOC, P pu-hp , T enu

[0068] In the formula, SOC is the state of charge, which is used to describe the amount of remaining power in the energy storage device (such as a storage battery), and the calculation formula of SOC is:

[0069]

[0070] Among them, Q current is the current battery power, and Q rated is the rated capacity of the battery;

[0071] ​Meanwhile, features closely related to the charge-discharge strategy can be selected from the perspective of the energy storage module state. The state of charge reflects the proportion of the remaining power in the energy storage module, usually in the range of 0 to 1. When the state of charge is low, the strategy may tend to charge. When constructing the feature vector, the state of charge is an essential feature, which enables the clustering algorithm to classify data points according to the power situation;

[0072] Battery temperature has a significant impact on the performance and safety of the battery. At different battery temperatures, the charge-discharge efficiency and capacity of the battery will change. Taking the battery temperature as a feature can make the charge-discharge strategy take into account the temperature factor and adjust the charge-discharge power or take cooling / heating measures when the temperature is abnormal;

[0073] State of health (SOH) of the battery. The state of health of the battery represents the health degree of the battery, which is related to the aging degree of the battery. For batteries with a low state of health, it may be necessary to limit their maximum charge-discharge power to extend the battery life;

[0074] Considering the relevant features of the photovoltaic system, the photovoltaic power generation efficiency is an important source of the system's energy input. Its magnitude and changes directly affect the charge-discharge strategy of the energy storage module. When the light is sufficient, the photovoltaic power generation efficiency is large. When the heat pump power demand is small, the energy storage module has more energy available for charging. The photovoltaic power generation power can be used as a dynamic feature to enable the clustering algorithm to classify the system state according to different photovoltaic power generation situations, so as to formulate a reasonable charge-discharge strategy under different light conditions;

[0075] Predicted value of photovoltaic power. By predicting the photovoltaic power, the charge-discharge strategy of the energy storage module can be planned in advance, and this feature is very useful for coping with the volatility and intermittency of photovoltaic power;

[0076] Combining the key features of the heat pump system, the heat pump power demand. The heat pump power demand reflects the energy consumption situation of the system, which is related to factors such as the ambient temperature and the temperature set by the user. Taking the heat pump power demand as a feature can make the charge-discharge strategy better adapt to the change of the heat pump's energy demand;

[0077] Operating mode (cooling / heating) of the heat pump. Different operating modes of the heat pump have different characteristics of energy demand. In the cooling mode, the power demand is usually larger when the ambient temperature is higher during the day; in the heating mode, the power demand may be larger when the ambient temperature is lower at night. According to the operating mode of the heat pump, the charge-discharge strategy of the energy storage module can be adjusted to better meet the energy demand of the system. The feature of the heat pump operating mode can help the clustering algorithm distinguish the system states under different operating modes, so as to formulate targeted charge-discharge strategies;

[0078] S30, applying the K-means clustering algorithm, determining the number of clusters K by experience or the elbow method, and then randomly initializing K cluster centers, and then calculating the distance from each data point to these cluster centers, and updating the cluster centers according to the existing data points assigned to each cluster;

[0079] It should be noted that for the data point x i and cluster center μ j The distance calculation formula is as follows:

[0080]

[0081] Among them, n is the dimension of the feature vector, x ik For data point x i The kth feature of jk When the cluster center μ j The kth feature of

[0082] At the same time, for the clusters, the equations in the new clusters are as follows:

[0083]

[0084] Among them, N j is cluster C j The number of data points in ;

[0085] At the same time, the empirical method determines the cluster number K: Based on the prior knowledge of the system, if there is sufficient understanding of the solar-thermal-storage combined system based on cluster analysis, the cluster number K can be determined based on actual experience. For example, from the perspective of the system operation mode, if it is known that the system usually operates in three typical states, "PV energy surplus and high energy storage capacity, PV energy balance and moderate energy storage capacity, and PV energy shortage and low energy storage capacity", then K = 3 can be preliminarily set. This method relies on the familiarity of system energy flow, equipment performance, and user needs;

[0086] The elbow method determines the number of clusters K, principle and calculation steps:

[0087] Calculate the sum of squares of clustering errors (SSE). First, for different cluster numbers K (usually start with K=1), run the K-means clustering algorithm. After each clustering, calculate the sum of squares of the distances from each data point to the center of its cluster. This sum is the sum of squares of clustering errors. The sum of squares of clustering errors reflects the compactness of clustering. The smaller the sum of squares of clustering errors, the tighter the distribution of data points in the clusters and the better the clustering effect.

[0088] Observe the curve of calculating the sum of squared errors of clustering. As K increases, the calculated sum of squared errors of clustering will gradually decrease. Plot the values of the calculated sum of squared errors of clustering corresponding to different K values as a curve, which is shaped like an elbow. At the starting part of the curve, the calculated sum of squared errors of clustering drops rapidly as K increases; after K increases to a certain extent, the downward trend of the calculated sum of squared errors of clustering will become gentle;

[0089] Determine the elbow point (optimal K value). The K value corresponding to the elbow point is the better number of clusters. This point is usually the turning point where the curve changes from a steep descent to a gentle descent. Intuitively, before this point, increasing the number of clusters can significantly improve the clustering effect;

[0090] S40. Analyze the clustering results to formulate a charge-discharge strategy. Calculate the central feature vector of each cluster, and formulate a charge-discharge strategy according to the characteristics of the cluster center;

[0091] It should be noted that first, review the number and type of features selected when constructing the feature vector, including the state of charge of the energy storage module. Then, calculate for each cluster, set an accumulative variable for each feature dimension, with the initial value set to 0. Assume the feature vector has n dimensions, create an array sum-uector of length n, where its element sum-uector[i] corresponds to the accumulative value of the i-th feature dimension, sum-uector = [0, 0,..., 0]. Traverse all data points belonging to this cluster one by one, count the number of data points in this cluster, denoted as N k , divide the value of each accumulative variable by N k , and the result obtained is the value of the cluster center on the corresponding feature dimension, that is, the cluster center feature vector:

[0092]

[0093] S50. Strategy optimization and verification. Optimize the formulated charge-discharge strategy according to the operating conditions and performance requirements of the actual system, and use historical data or conduct actual tests to verify the effectiveness of the charge-discharge strategy;

[0094] It should be noted that the K-means clustering algorithm is an unsupervised learning algorithm mainly used to divide a dataset into K different clusters. Its core idea is to make the data points within the same cluster as similar as possible and the data points between different clusters as different as possible through an iterative method;

[0095] Moreover, through cluster analysis, the energy storage modules in the photovoltaic-thermal-energy storage combined system can be classified and evaluated. According to different lighting conditions, heat demands, and electricity load factors, the energy storage modules can be reasonably configured to determine the capacity and proportion of different types of energy storage modules;

[0096] Cluster analysis can help monitor and analyze the operating status of energy storage modules, clustering energy storage modules with similar operating statuses together for centralized management and control, promptly detecting abnormal modules, and improving the reliability and stability of the system;

[0097] Meanwhile, performing cluster analysis on the performance indicators of energy storage modules can evaluate the applicability, advantages, and disadvantages of different energy storage modules in the photovoltaic-thermal-energy storage combined system, providing a basis for system optimization and upgrading;

[0098] The performance indicators of energy storage modules include energy storage efficiency, charge and discharge speed, and cycle life;

[0099] The control module is responsible for monitoring and managing the operation of the entire system and optimizing the coordinated work among various components;

[0100] It should be noted that the control module includes a programmable logic controller, a power sensor, a temperature sensor, an inverter, and switchgear. The programmable logic controller is used to precisely control various devices in the system according to pre-written program logic. The power sensor is used to monitor the power generation of photovoltaic panels in real time. The temperature sensor is used to measure the external environmental temperature. The inverter is used to convert the direct current generated by photovoltaic panels into alternating current. The switchgear is used to control the on and off of the circuit;

[0101] The power conversion module is used to convert the electrical energy generated by photovoltaic modules into alternating current to provide electrical energy for heat pumps and other AC electrical equipment;

[0102] It should be noted that the main types of power conversion modules include inverters, rectifiers, and DC-DC converters. Inverter: Converts the direct current generated by photovoltaic modules into alternating current for grid connection or for use by AC loads;

[0103] Rectifier: Mainly used to convert alternating current into direct current for charging energy storage modules, etc. In the photovoltaic-thermal-energy storage combined system, when it is necessary to convert the alternating current in the power grid or the alternating current generated by the photovoltaic-thermal system through thermoelectric conversion, etc. into direct current for storage, a rectifier is required. By clustering and analyzing data such as the input and output voltage and current waveforms of the rectifier, it is possible to determine whether it is operating normally and whether there are potential fault hazards;

[0104] DC-DC converter: Used to achieve conversion between different DC voltage levels, playing a role in voltage matching and power regulation among photovoltaic modules, energy storage modules, and other DC loads;

[0105] The heat exchange module is used to achieve heat exchange between the refrigerant and water and air media;

[0106] It should be noted that the heat exchange module usually includes an evaporator and a condenser;

[0107] In a heat pump system, the evaporator is a key component where the refrigerant absorbs heat. When the refrigerant flows through the evaporator, its pressure is relatively low, and it is in a liquid-vapor mixed state or liquid state;

[0108] The condenser is a component where the refrigerant releases heat. In the heat pump cycle, after being compressed by the compressor, the refrigerant becomes a high-temperature and high-pressure gas and enters the condenser. At this time, the temperature of the condenser is lower than that of the refrigerant. The refrigerant transfers heat by exchanging heat with the cooling medium around the condenser and cools and condenses from a gaseous state to a liquid state by itself;

[0109] An auxiliary module for distributing and controlling the output of the circuit;

[0110] It should be noted that the auxiliary module includes monitoring and display devices, safety and protection devices, communication and connection devices, and auxiliary energy devices. The monitoring and display devices are responsible for collecting the operation data of each device in the system. The safety and protection devices are used to prevent the devices from being damaged due to overcurrent. The communication and connection devices are used to realize the communication between the internal devices of the system and between the system and external devices. The auxiliary energy device is used when the photovoltaic system generates insufficient electricity and the energy storage device runs out of power. The standby generator can be used as a supplementary energy source;

[0111] Operation status evaluation clustering: Using clustering analysis to analyze a large amount of monitoring data collected by the control and management module, the operation status of the auxiliary module is divided into different categories, such as normal operation status, warning status, and fault status;

[0112] Performance optimization clustering: Clustering the data provided by the monitoring and metering module, analyzing the performance of the auxiliary module under different working conditions, finding out the working condition categories with the best and worst performance, and providing guidance for the optimized operation of the system;

[0113] Fault diagnosis clustering: Based on the fault information and monitoring data recorded by the protection module, using a clustering algorithm to classify similar fault modes, which helps to quickly locate the cause of the fault and formulate corresponding maintenance strategies.

[0114] The above are only embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A light-thermal-energy storage combined system based on clustering analysis, characterized in that, including a photovoltaic module for directly converting sunlight into electrical energy; a heat pump module for extracting heat from a low-temperature heat source and transferring it to a device at a higher temperature; a energy storage module which is used to store excess electrical energy and release this energy when needed. The clustering analysis method is adopted to cluster according to the characteristics of energy demand in different time periods. For each cluster, the K-means clustering algorithm is used to calculate the optimal charge-discharge strategy. And when the photovoltaic output is unstable, the electricity is reserved in advance according to the clustering result and stably supplied to the heat pump or other loads; a control module responsible for monitoring and managing the operation of the entire system and optimizing the coordinated work among various components; a power conversion module for converting the electrical energy generated by the photovoltaic module into alternating current to provide electrical energy for the heat pump and other AC electrical equipment; a heat exchange module for realizing heat exchange between the refrigerant and water and air media; an auxiliary module for distributing and controlling the output of the circuit.

2. The optical-thermal-storage combined system based on clustering analysis according to claim 1, characterized in that, The usage process of the clustering analysis method includes the following steps: S1. Data collection and preprocessing: Collect various relevant data of the energy storage module. At the same time, it is also necessary to record the timestamp information, and clean the collected data, remove outliers and error data; S2. Feature selection and extraction: According to the purpose of clustering analysis and the characteristics of the energy storage module, select appropriate features as the basis for clustering. After selecting the appropriate clustering basis, combine the selected features into a feature vector; S3. Clustering algorithm selection and application: Select an appropriate clustering algorithm according to the characteristics of the data and the requirements of clustering analysis, and then apply the selected algorithm to the place where calculation is needed; S4. Clustering structure analysis and application: Analyze the clustered structure, and optimize the control strategy of the energy storage module according to the results of clustering analysis.

3. The optical-thermal-storage combined system based on cluster analysis according to claim 2, wherein The calculation of the charge-discharge strategy by the K-means clustering algorithm specifically includes the following steps; S10. Data collection and preprocessing: Collect data related to the energy storage module, clean the collected data, remove outliers and error data, and normalize the data so that data of different magnitudes can be analyzed on the same scale; S20. Feature selection and construction of feature vector: Select features closely related to the charge-discharge strategy, and for each data point, construct a feature vector; S30. Apply the K-means clustering algorithm: Determine the number of clusters K through experience or the elbow method, then randomly initialize K cluster centers, and then calculate the distance from each data point to these cluster centers, and update the cluster centers according to the existing data points assigned to each cluster; S40. Analyze the clustering results to formulate the charge-discharge strategy: Calculate the central feature vector of each cluster, and formulate the charge-discharge strategy according to the characteristics of the cluster center; S50. Strategy optimization and verification: Optimize the formulated charge-discharge strategy according to the actual operation conditions and performance requirements of the system, and use historical data or conduct actual tests to verify the effectiveness of the charge-discharge strategy.

4. The optical-thermal-storage combined system based on clustering analysis according to claim 3, characterized in that, The various relevant data described in step S1 include the state of charge of the battery, the charge and discharge current, the charge and discharge voltage, the power generation power of the photovoltaic system, the operating power of the heat pump system, and the ambient temperature.

5. The optical-thermal-storage combined system based on clustering analysis according to claim 4, characterized in that, The control module includes a programmable logic controller, a power sensor, a temperature sensor, an inverter, and a switching device. The programmable logic controller is used to precisely control various devices in the system according to the pre-written program logic. The power sensor is used to monitor the power generation power of the photovoltaic panels in real time. The temperature sensor is used to measure the external ambient temperature. The inverter is used to convert the direct current generated by the photovoltaic panels into alternating current. The switching device is used to control the on and off of the circuit.

6. The optical-thermal-storage combined system based on cluster analysis according to claim 5, wherein The auxiliary module includes a monitoring and display device, a safety and protection device, a communication and connection device, and an auxiliary energy device. The monitoring and display device is responsible for collecting the operating data of each device in the system. The safety and protection device is used to prevent the device from being damaged due to overcurrent. The communication and connection device is used to achieve communication between the internal devices of the system and between the system and external devices. The auxiliary energy device is used when the power generation of the photovoltaic system is insufficient and the energy storage device is out of power, and the standby generator can be used as a supplementary energy source.

Images