Photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system

Abstract

The invention belongs to the technical field of photovoltaic energy storage all-electric kitchens, and discloses photovoltaic energy storage all-electric kitchen equipment and a low-carbon data energy management optimization system. Comprising the following modules: a data acquisition module for acquiring low-carbon data of all-electric kitchen equipment in real time through acquisition equipment; according to the method, the power consumption prediction model and the power generation prediction model are set, demand prediction is carried out on the power consumption side based on low-carbon scores, prediction is carried out on the power generation side in combination with environmental factors, and the optimal energy scheduling strategy is generated through contrastive analysis of prediction results on the two sides; the problem of optimization of energy storage configuration is effectively solved by adopting a double-storage-battery recycling mechanism, the system accurately calculates the required expansion time according to an electric quantity gap, accurate release of temporary power generation resources is realized, and compared with a traditional fixedly-mounted photovoltaic system, the photovoltaic utilization efficiency of a unit area is greatly improved through the expandable design, and the energy consumption is reduced. And the elastic expansion of the power generation capacity is realized in a limited roof space.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic energy storage all-electric kitchen technology, and more specifically, to a photovoltaic energy storage all-electric kitchen device and a low-carbon data energy management optimization system. Background Technology

[0002] With the advancement of global energy transition and dual-carbon goals, the green and low-carbon transformation of the catering industry, as a major energy consumer, has become an important issue. All-electric kitchens, with their high efficiency, safety, and cleanliness, are gradually replacing traditional gas kitchens. However, relying solely on grid power still leads to a high carbon footprint. Photovoltaic energy storage systems provide a green power solution for all-electric kitchens.

[0003] Currently, photovoltaic kitchen systems on the market lack intelligent energy management mechanisms. Traditional systems often control charging and discharging based on fixed thresholds, failing to dynamically adjust according to the actual energy consumption characteristics of the kitchen and environmental factors. On the power generation side, photovoltaic output prediction relies heavily on historical averages, ignoring the impact of dynamic factors such as weather, seasons, and equipment status, resulting in insufficient prediction accuracy. On the energy consumption side, existing systems have a rather crude understanding of the energy consumption characteristics of kitchen equipment, failing to distinguish between different energy consumption patterns during periods of human use and standby, and lacking quantitative assessment of users' energy-saving habits. In terms of energy management strategies, the matching degree between photovoltaic power generation and kitchen electricity consumption is not high, often resulting in energy waste when there is excess power generation or power shortages when there is insufficient power generation. The system lacks a comprehensive assessment of multiple dimensions such as equipment energy efficiency, user behavior, and environmental factors, making it difficult to achieve refined energy consumption management. The lack of intelligent scheduling mechanisms for temporary power generation equipment makes it impossible to dynamically adjust power generation capacity according to real-time supply and demand. Summary of the Invention

[0004] To address the problems in the background art, this invention proposes a photovoltaic energy storage all-electric kitchen device and a low-carbon data energy management optimization system.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a photovoltaic energy storage all-electric kitchen device and a low-carbon data energy management optimization system, comprising the following modules: The data acquisition module collects low-carbon data from all-electric kitchen equipment in real time through acquisition devices; The low-carbon assessment module is used to generate real-time low-carbon scores for all-electric kitchen equipment based on the collected low-carbon data, and to derive the low-carbon score change rate and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores. The electricity consumption prediction module is used to acquire historical electricity consumption data and build an electricity consumption prediction model, and use the electricity consumption prediction model to predict the electricity consumption of all-electric kitchen equipment throughout the day. The power generation prediction module is used to acquire historical power generation data and build a power generation prediction model, and then use the power generation prediction model to predict the power generation of perovskite solar cells throughout the day. The power generation decision module compares the predicted electricity consumption with the predicted power generation and decides whether to deploy temporary perovskite solar cells to increase power generation.

[0006] Furthermore, the all-electric kitchen equipment includes common kitchen appliances such as electric stoves, water heaters, and refrigerators. The electricity for the all-electric kitchen equipment comes from the power generation of perovskite solar cells. The low-carbon data includes real-time energy self-sufficiency rate, equipment energy efficiency ratio, carbon intensity factor, behavioral energy saving index, and environmental temperature adaptability. The real-time energy self-sufficiency rate is obtained by dividing the power generation of the perovskite solar cells by the real-time total power of the all-electric kitchen equipment.

[0007] In the formula, V is the real-time energy self-sufficiency rate, E is the power generation of the perovskite solar cell, and P is the real-time total power of the all-electric kitchen equipment. The energy efficiency ratio of an equipment refers to the efficiency of converting electrical energy into useful output. It is calculated by dividing the output energy of an all-electric kitchen equipment by its input energy.

[0008] In the formula, W represents the equipment energy efficiency ratio. This refers to the actual equipment energy efficiency ratio. The rated energy efficiency ratio of the equipment; Obtain real-time carbon intensity data from power grid operators;

[0009] In the formula, X is the carbon strength factor. For actual carbon strength, The highest carbon strength; The behavioral energy efficiency index assesses a user's energy-saving habits when using devices and whether the device is turned off in a timely manner.

[0010] In the formula, Y is the behavioral energy-saving index. For the actual number of energy-saving cycles, Total number of uses; Ambient temperature is obtained through a temperature sensor. Ambient temperature adaptability refers to the degree of compatibility between the ambient temperature and the suitable operating temperature of the equipment.

[0011] In the formula, Z represents the environmental temperature adaptability. This refers to the actual ambient temperature. For the ideal ambient temperature, This refers to the temperature range.

[0012] Furthermore, the process of generating real-time low-carbon scores for all-electric kitchen equipment based on the collected low-carbon data includes: Low-carbon rating S for all-electric kitchen equipment:

[0013] In the formula, , , and These are weighting coefficients, obtained through training based on historical data.

[0014] Furthermore, the process of deriving the rate of change and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores includes: The operation of all-electric kitchen equipment throughout the day is divided into working periods when the equipment is used by humans and standby periods when the equipment is not used by humans. During working periods, the intensity and frequency of human use of kitchen equipment are high. During standby periods, some equipment in the all-electric kitchen is still in working condition, such as refrigerators and water heaters, which need to be kept running at all times. A first assessment cycle is set during the period of human use of all-electric kitchen equipment, and a second assessment cycle is set during the period of non-human use of all-electric kitchen equipment. During the period of human use of all-electric kitchen equipment, a corresponding real-time first low-carbon score needs to be obtained for each first assessment cycle. During the period of non-human use of all-electric kitchen equipment, a corresponding real-time second low-carbon score needs to be obtained for each second assessment cycle. The average first low-carbon score is calculated based on multiple first low-carbon scores throughout the day, and the average second low-carbon score is calculated based on multiple second low-carbon scores throughout the day. Take the first low-carbon scores for 2n first assessment periods, arrange the 2n first low-carbon scores in chronological order, calculate the average of the first n first low-carbon scores to obtain the average third low-carbon score, calculate the average of the last n first low-carbon scores to obtain the average fourth low-carbon score, subtract the average third low-carbon score from the average fourth low-carbon score to obtain the score difference, divide the absolute value of the score difference by the average third low-carbon score to obtain the change rate of the first low-carbon score, and obtain the change rate of the second low-carbon score using the same method.

[0015] Furthermore, the process of acquiring historical electricity consumption data and constructing an electricity consumption prediction model, and then using this model to predict the daily electricity consumption of all-electric kitchen equipment, includes: Factors affecting the daily electricity consumption of all-electric kitchen equipment include: the rate of change of the first low-carbon score, the average first low-carbon score, the rate of change of the second low-carbon score, the average second low-carbon score, the planned human usage time of the equipment, the non-human usage time of the equipment, and the historical average electricity consumption. Planned human usage time refers to the planned duration of human use of the device throughout the day, which is obtained based on the user's device usage plan. Non-human-caused equipment usage time refers to the total time spent using the equipment throughout the day excluding planned human-caused equipment usage time; Historical average electricity consumption refers to the average daily electricity consumption of all-electric kitchen equipment over a period of time. Obtain historical electricity consumption data of all-electric kitchen equipment throughout the day. The historical electricity consumption data includes the change rate of the first low-carbon score of all-electric kitchen equipment throughout the day, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the historical electricity consumption of all-electric kitchen equipment throughout the day. Based on the daily change rate of the first low-carbon score of all-electric kitchen equipment, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the corresponding historical electricity consumption, an electricity consumption prediction set is generated and divided into the first training set and the first test set. Construct a first convolutional neural network, and use the change rate of the first low-carbon score, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human-used equipment time, the non-human-used equipment time, and the historical average electricity consumption in different historical electricity consumption data in the first training set as the input data of the first convolutional neural network, and use the corresponding historical electricity consumption in the first training set as the output data of the first convolutional neural network. The first convolutional neural network is trained to obtain the first initial convolutional neural network. The first initial convolutional neural network is validated using the first test set. The first initial convolutional neural network, whose output is less than or equal to the preset first test error threshold, is used as the electricity consumption prediction model. The changes in the first low-carbon score of the all-electric kitchen equipment throughout the day, the average first low-carbon score, the changes in the second low-carbon score, the average second low-carbon score, the planned human usage time, the non-human usage time, and the historical average electricity consumption are input into the electricity consumption prediction model to obtain the predicted electricity consumption of the all-electric kitchen equipment throughout the day.

[0016] Furthermore, the process of acquiring historical power generation data and constructing a power generation prediction model, and then using this model to predict the power generation of perovskite solar cells throughout the day, includes: Factors affecting the daily power generation of perovskite solar cells include: solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation. Obtain real-time solar radiation intensity from irradiance sensors or weather APIs; Obtain real-time cloud cover data from the weather API and calculate the percentage of cloud cover in the sky to obtain the cloud cover rate; The output efficiency of photovoltaic panels is obtained by dividing the actual power generation by the theoretical maximum power generation through monitoring and calculation of the output efficiency of photovoltaic panels. The output efficiency of photovoltaic panels is positively correlated with the cleanliness of photovoltaic panels. Historical average power generation refers to the average power generation data of perovskite solar cells over a past period. Obtain historical power generation data of perovskite solar cells throughout the day. The historical power generation data includes the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and historical power generation of perovskite solar cells throughout the day. Based on the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and corresponding historical power generation of perovskite solar cells throughout the day from different historical power generation data, a power generation prediction set is generated and divided into a second training set and a second test set. A second convolutional neural network is constructed. The solar radiation intensity, cloud cover rate, photovoltaic panel cleanliness and historical average power generation in different historical power generation data in the second training set are used as the input data of the second convolutional neural network, and the corresponding historical power generation in the second training set is used as the output data of the second convolutional neural network. The second convolutional neural network is trained to obtain the second initial convolutional neural network. The second initial convolutional neural network is validated using the second test set. The second initial convolutional neural network that outputs a second test error threshold less than or equal to the preset second test error threshold is used as the power generation prediction model. The solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation of the perovskite solar cell throughout the day are input into the power generation prediction model to obtain the predicted power generation of the perovskite solar cell throughout the day.

[0017] Furthermore, the process of comparing predicted electricity consumption with predicted electricity generation includes: The electricity consumption of the all-electric kitchen equipment throughout the day is predicted by the electricity consumption prediction model, and the power generation of the perovskite solar cells throughout the day is predicted by the power generation prediction model. The predicted electricity consumption and predicted power generation are then compared. If the predicted power consumption is less than the predicted power generation, it means that the power generation of the perovskite solar cells can meet the power consumption of the all-electric kitchen equipment for the whole day. Subtracting the predicted power consumption from the predicted power generation gives the surplus power, which can be stored in the energy storage battery. All-electric kitchens are usually equipped with two batteries. On the current day, one battery is the power supply battery and is fully charged to provide power to the all-electric kitchen equipment. The power generated by the perovskite solar cells is preferentially supplied to this battery. The other battery is the energy storage battery, which is used to receive the surplus power and needs to be charged through the grid until it is fully charged to prepare for the next day. On the next day, the power supply battery of the previous day becomes the energy storage battery, and the energy storage battery of the previous day becomes the power supply battery, and so on in a cycle. If the predicted electricity consumption is greater than the predicted power generation, it means that the power generation of the perovskite solar cells is not enough to meet the daily power consumption of the all-electric kitchen equipment. Subtracting the predicted power generation from the predicted electricity consumption gives the power gap, which needs to be filled by increasing the power generation of the perovskite solar cells. If increasing the power generation of the perovskite solar cells is still not enough to meet the power gap, then the energy storage battery needs to be temporarily activated.

[0018] Furthermore, one way to increase the power generation of perovskite solar cells is to deploy temporary perovskite solar cells, the specific process of which includes: The temporary perovskite solar cells equipped in the all-electric kitchen are automatically deployed and put into power generation mode. Since the roof of the all-electric kitchen is already covered with the largest area of ​​perovskite solar cells, the temporary perovskite solar cells are usually hidden under the perovskite solar cells. They will only be temporarily deployed to generate electricity when there is a power shortage. The temporary perovskite solar cells cannot be deployed stably for a long time. Based on the prediction model of the area and power generation of temporary perovskite solar cells, the predicted temporary power generation of the temporary perovskite solar cells can be predicted. The predicted temporary power generation is compared with the power shortage. If the predicted temporary power generation is greater than the power shortage, it means that the temporary perovskite solar cells can fill the power shortage. The power generation rate of a unit area of ​​temporary perovskite solar cells is the same as that of a unit area of ​​perovskite solar cells. The deployment time is obtained by dividing the power shortage by the power generation rate of a unit area of ​​temporary perovskite solar cells. If the predicted temporary power generation is less than the power shortage, it means that the temporary perovskite solar cells are insufficient to fill the power shortage, and it is necessary to temporarily activate the energy storage battery.

[0019] The technical effects and advantages of the photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system of the present invention are as follows: (1) By setting up a power consumption prediction model and a power generation prediction model, the precise supply and demand matching realizes the efficient use of energy. On the power consumption side, demand is predicted based on low carbon scores, and on the power generation side, environmental factors are combined for prediction. Through comparative analysis of the prediction results of both sides, the optimal energy dispatch strategy is generated. In terms of power generation prediction, the cleanliness of photovoltaic panels is introduced. Perovskite solar cells are more sensitive to surface cleanliness than traditional silicon-based cells. The system evaluates the cleanliness status in real time by monitoring the output efficiency, which significantly improves the accuracy of power generation prediction. The dual-battery cycle mechanism effectively solves the optimization problem of energy storage configuration. By setting the role rotation of power supply batteries and energy storage batteries, the reliability of power supply on the day is guaranteed, and sufficient energy is reserved for the next day. The system accurately calculates the required deployment time according to the power shortage, realizing the precise deployment of temporary power generation resources. Compared with traditional fixed-installation photovoltaic systems, the deployable design greatly improves the photovoltaic utilization efficiency per unit area and realizes the flexible expansion of power generation capacity in limited roof space.

[0020] (2) By setting a low-carbon score, the system achieves in-depth perception and accurate prediction of the energy consumption characteristics of the all-electric kitchen. Traditional energy management methods often only consider the single dimension of electricity consumption, which cannot reflect the quality and efficiency of energy use. The system further distinguishes between human use time and standby time, and sets different evaluation cycles to reflect the spatiotemporal characteristics of kitchen energy use. In the first evaluation cycle, the score changes are monitored at a higher frequency to capture the real-time impact of user operations on energy efficiency. In the second evaluation cycle, the basic energy consumption level is evaluated at a lower frequency. This differentiated monitoring strategy not only ensures the timeliness of the data, but also avoids the waste of resources caused by over-monitoring. The system calculates the score change rate and average score. These dynamic indicators can effectively reflect the energy efficiency trend. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the system of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0023] Reference Figure 1 A photovoltaic energy storage all-electric kitchen device and a low-carbon data energy management optimization system, comprising the following modules: The data acquisition module collects low-carbon data from all-electric kitchen equipment in real time through acquisition devices; The low-carbon assessment module is used to generate real-time low-carbon scores for all-electric kitchen equipment based on the collected low-carbon data, and to derive the low-carbon score change rate and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores. The electricity consumption prediction module is used to acquire historical electricity consumption data and build an electricity consumption prediction model, and use the electricity consumption prediction model to predict the electricity consumption of all-electric kitchen equipment throughout the day. The power generation prediction module is used to acquire historical power generation data and build a power generation prediction model, and then use the power generation prediction model to predict the power generation of perovskite solar cells throughout the day. The power generation decision module compares the predicted electricity consumption with the predicted power generation and decides whether to deploy temporary perovskite solar cells to increase power generation.

[0024] It should be further explained that, in the specific implementation process, the all-electric kitchen equipment includes common kitchen equipment such as electric stoves, water heaters and refrigerators. The electricity used by the all-electric kitchen equipment comes from the power generation of perovskite solar cells. The low-carbon data includes real-time energy self-sufficiency rate, equipment energy efficiency ratio, carbon intensity factor, behavioral energy saving index and environmental temperature adaptability. The real-time energy self-sufficiency rate is obtained by dividing the power generation of the perovskite solar cells by the real-time total power of the all-electric kitchen equipment.

[0025] In the formula, V is the real-time energy self-sufficiency rate, E is the power generation of the perovskite solar cell, and P is the real-time total power of the all-electric kitchen equipment. The energy efficiency ratio of an equipment refers to the efficiency of converting electrical energy into useful output. It is calculated by dividing the output energy of an all-electric kitchen equipment by its input energy.

[0026] In the formula, W represents the equipment energy efficiency ratio. This refers to the actual equipment energy efficiency ratio. The rated energy efficiency ratio of the equipment is specifically 90%. Obtain real-time carbon intensity data from power grid operators;

[0027] In the formula, X is the carbon strength factor. For actual carbon strength, The maximum carbon strength is 500. ; The behavioral energy efficiency index assesses a user's energy-saving habits when using devices and whether the device is turned off in a timely manner.

[0028] In the formula, Y is the behavioral energy-saving index. For the actual number of energy-saving cycles, Total number of uses; Ambient temperature is obtained through a temperature sensor. Ambient temperature adaptability refers to the degree of compatibility between the ambient temperature and the suitable operating temperature of the equipment.

[0029] In the formula, Z represents the environmental temperature adaptability. This refers to the actual ambient temperature. The ideal ambient temperature is 25°C. This refers to the temperature range, specifically 10℃.

[0030] It should be further explained that, in the specific implementation process, the process of generating real-time low-carbon scores for all-electric kitchen equipment based on the collected low-carbon data includes: Low-carbon rating S for all-electric kitchen equipment:

[0031] In the formula, , , and These are weighting coefficients, obtained from training on historical data, and set to 0.25, 0.25, 0.2, 0.15, and 0.15 respectively. If at a certain moment the real-time low-carbon data of the all-electric kitchen equipment is: E = 5kW, P = 10kW It is 85%. 300 , It is 6. It is 10. If the value is 30, then the real-time low-carbon score S of the all-electric kitchen equipment at that moment is 0.606.

[0032] It should be further explained that, in the specific implementation process, the process of deriving the change rate and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores includes: The operation of all-electric kitchen equipment throughout the day is divided into working periods when the equipment is used by humans and standby periods when the equipment is not used by humans. During working periods, the intensity and frequency of human use of kitchen equipment are high. During standby periods, some equipment in the all-electric kitchen is still in working condition, such as refrigerators and water heaters, which need to be kept running at all times. A first assessment cycle is set during the period of human use of all-electric kitchen equipment, and a second assessment cycle is set during the period of non-human use of all-electric kitchen equipment. During the period of human use of all-electric kitchen equipment, a corresponding real-time first low-carbon score needs to be obtained for each first assessment cycle. During the period of non-human use of all-electric kitchen equipment, a corresponding real-time second low-carbon score needs to be obtained for each second assessment cycle. The average first low-carbon score is calculated based on multiple first low-carbon scores throughout the day, and the average second low-carbon score is calculated based on multiple second low-carbon scores throughout the day. Take the first low-carbon scores for 2n first assessment periods, arrange the 2n first low-carbon scores in chronological order, calculate the average of the first n first low-carbon scores to obtain the average third low-carbon score, calculate the average of the last n first low-carbon scores to obtain the average fourth low-carbon score, subtract the average third low-carbon score from the average fourth low-carbon score to obtain the score difference, divide the absolute value of the score difference by the average third low-carbon score to obtain the change rate of the first low-carbon score, and obtain the change rate of the second low-carbon score using the same method.

[0033] It should be further explained that, in the specific implementation process, the process of acquiring historical electricity consumption data and building an electricity consumption prediction model, and then using the electricity consumption prediction model to predict the electricity consumption of all-electric kitchen equipment throughout the day, includes: Factors affecting the daily electricity consumption of all-electric kitchen equipment include: the rate of change of the first low-carbon score, the average first low-carbon score, the rate of change of the second low-carbon score, the average second low-carbon score, the planned human usage time of the equipment, the non-human usage time of the equipment, and the historical average electricity consumption. Planned human usage time refers to the planned duration of human use of the device throughout the day, which is obtained based on the user's device usage plan. Non-human-caused equipment usage time refers to the total time spent using the equipment throughout the day excluding planned human-caused equipment usage time; Historical average electricity consumption refers to the average daily electricity consumption of all-electric kitchen equipment over a period of time. Obtain historical electricity consumption data of all-electric kitchen equipment throughout the day. The historical electricity consumption data includes the change rate of the first low-carbon score of all-electric kitchen equipment throughout the day, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the historical electricity consumption of all-electric kitchen equipment throughout the day. Based on the daily change rate of the first low-carbon score of all-electric kitchen equipment, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the corresponding historical electricity consumption, an electricity consumption prediction set is generated and divided into the first training set and the first test set. Construct a first convolutional neural network, and use the change rate of the first low-carbon score, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human-used equipment time, the non-human-used equipment time, and the historical average electricity consumption in different historical electricity consumption data in the first training set as the input data of the first convolutional neural network, and use the corresponding historical electricity consumption in the first training set as the output data of the first convolutional neural network. The first convolutional neural network is trained to obtain the first initial convolutional neural network. The first initial convolutional neural network is validated using the first test set. The first initial convolutional neural network, whose output is less than or equal to the preset first test error threshold, is used as the electricity consumption prediction model. The change rate of the first low-carbon score of the all-electric kitchen equipment throughout the day, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, and the historical average electricity consumption are input into the electricity consumption prediction model to obtain the predicted electricity consumption of the all-electric kitchen equipment throughout the day. In an embodiment of the present invention, the predicted electricity consumption of the all-electric kitchen equipment throughout the day is obtained through an electricity consumption prediction model. The predicted electricity consumption is related to the change rate of the first low-carbon score, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, and the historical average electricity consumption. The rate of change of the first low-carbon score directly affects the amount of predicted electricity consumption. The higher the rate of change of the first low-carbon score, the better the energy efficiency, the more energy-efficient the equipment is during human use, and the less electricity is predicted. Therefore, the rate of change of the first low-carbon score is negatively correlated with the predicted electricity consumption. The average first low carbon score directly affects the amount of predicted electricity consumption. The higher the average first low carbon score, the higher the energy efficiency of the equipment when used by humans, and the less predicted electricity consumption. Therefore, the average first low carbon score is negatively correlated with the predicted electricity consumption. The rate of change of the second low-carbon score directly affects the amount of predicted electricity consumption. The higher the rate of change of the second low-carbon score, the better the energy efficiency during non-human use, the less basic energy consumption, and the less predicted electricity consumption. Therefore, the rate of change of the second low-carbon score is negatively correlated with the predicted electricity consumption. The average second low carbon score directly affects the amount of predicted electricity consumption. The higher the average second low carbon score, the higher the energy efficiency of the equipment when not used by humans, the lower the energy consumption in standby or automatic operation, and the less predicted electricity consumption. Therefore, the average second low carbon score is negatively correlated with the predicted electricity consumption. The length of time that people plan to use the equipment directly affects the amount of electricity consumption predicted. The longer the planned time that people use the equipment, the longer the equipment runs, the more energy is accumulated, and the more electricity is predicted. Therefore, the planned time that people use the equipment is positively correlated with the predicted electricity consumption. The duration of non-human-caused equipment use directly affects the amount of predicted electricity consumption. The longer the non-human-caused equipment use, the more basic energy consumption is accumulated, and the more predicted electricity consumption is. Therefore, the duration of non-human-caused equipment use is positively correlated with the predicted electricity consumption. The amount of historical average electricity consumption directly affects the amount of predicted electricity consumption. The higher the historical average electricity consumption, the higher the energy consumption trend of users or equipment, and the higher the predicted electricity consumption. Therefore, historical average electricity consumption and predicted electricity consumption are positively correlated.

[0034] It should be further explained that, in the specific implementation process, the process of acquiring historical power generation data and constructing a power generation prediction model, and then using the power generation prediction model to predict the power generation of perovskite solar cells throughout the day, includes: Factors affecting the daily power generation of perovskite solar cells include: solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation. Obtain real-time solar radiation intensity from irradiance sensors or weather APIs; Obtain real-time cloud cover data from the weather API and calculate the percentage of cloud cover in the sky to obtain the cloud cover rate; The output efficiency of photovoltaic panels is obtained by dividing the actual power generation by the theoretical maximum power generation through monitoring and calculation of the output efficiency of photovoltaic panels. The output efficiency of photovoltaic panels is positively correlated with the cleanliness of photovoltaic panels. Historical average power generation refers to the average power generation data of perovskite solar cells over a past period. Obtain historical power generation data of perovskite solar cells throughout the day. The historical power generation data includes the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and historical power generation of perovskite solar cells throughout the day. Based on the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and corresponding historical power generation of perovskite solar cells throughout the day from different historical power generation data, a power generation prediction set is generated and divided into a second training set and a second test set. A second convolutional neural network is constructed. The solar radiation intensity, cloud cover rate, photovoltaic panel cleanliness and historical average power generation in different historical power generation data in the second training set are used as the input data of the second convolutional neural network, and the corresponding historical power generation in the second training set is used as the output data of the second convolutional neural network. The second convolutional neural network is trained to obtain the second initial convolutional neural network. The second initial convolutional neural network is validated using the second test set. The second initial convolutional neural network that outputs a second test error threshold less than or equal to the preset second test error threshold is used as the power generation prediction model. The solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation of the perovskite solar cell throughout the day are input into the power generation prediction model to obtain the predicted power generation of the perovskite solar cell throughout the day. In an embodiment of the present invention, the predicted power generation of the perovskite solar cell throughout the day is obtained through a power generation prediction model. The predicted power generation is related to solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation. The intensity of sunlight directly affects the amount of predicted power generation. The stronger the sunlight, the more predicted power generation. Therefore, there is a positive correlation between sunlight intensity and predicted power generation. The amount of cloud cover directly affects the amount of predicted power generation. The greater the cloud cover, the weaker the solar radiation intensity, and the less predicted power generation. Therefore, cloud cover and predicted power generation are negatively correlated. The cleanliness of photovoltaic panels directly affects the amount of predicted power generation. The higher the cleanliness of the photovoltaic panels, the higher the power generation efficiency and the more predicted power generation. Therefore, there is a positive correlation between the cleanliness of photovoltaic panels and the predicted power generation. The amount of historical average power generation directly affects the amount of predicted power generation. The higher the historical average power generation, the higher the predicted power generation. Therefore, historical average power generation and predicted power generation are positively correlated.

[0035] It should be further explained that, in the specific implementation process, the comparison between the predicted electricity consumption and the predicted power generation includes: The electricity consumption of the all-electric kitchen equipment throughout the day is predicted by the electricity consumption prediction model, and the power generation of the perovskite solar cells throughout the day is predicted by the power generation prediction model. The predicted electricity consumption and predicted power generation are then compared. If the predicted power consumption is less than the predicted power generation, it means that the power generation of the perovskite solar cells can meet the power consumption of the all-electric kitchen equipment for the whole day. Subtracting the predicted power consumption from the predicted power generation gives the surplus power, which can be stored in the energy storage battery. All-electric kitchens are usually equipped with two batteries. On the current day, one battery is the power supply battery and is fully charged to provide power to the all-electric kitchen equipment. The power generated by the perovskite solar cells is preferentially supplied to this battery. The other battery is the energy storage battery, which is used to receive the surplus power and needs to be charged through the grid until it is fully charged to prepare for the next day. On the next day, the power supply battery of the previous day becomes the energy storage battery, and the energy storage battery of the previous day becomes the power supply battery, and so on in a cycle. If the predicted electricity consumption is greater than the predicted power generation, it means that the power generation of the perovskite solar cells is not enough to meet the daily power consumption of the all-electric kitchen equipment. Subtracting the predicted power generation from the predicted electricity consumption gives the power gap, which needs to be filled by increasing the power generation of the perovskite solar cells. If increasing the power generation of the perovskite solar cells is still not enough to meet the power gap, then the energy storage battery needs to be temporarily activated.

[0036] It should be further explained that, in the specific implementation process, the method to increase the power generation of perovskite solar cells is to deploy temporary perovskite solar cells. The specific process includes: The temporary perovskite solar cells equipped in the all-electric kitchen are automatically deployed and put into power generation mode. Since the roof of the all-electric kitchen is already covered with the largest area of ​​perovskite solar cells, the temporary perovskite solar cells are usually hidden under the perovskite solar cells. They will only be temporarily deployed to generate electricity when there is a power shortage. The temporary perovskite solar cells cannot be deployed stably for a long time. Based on the prediction model of the area and power generation of temporary perovskite solar cells, the predicted temporary power generation of the temporary perovskite solar cells can be predicted. The predicted temporary power generation is compared with the power shortage. If the predicted temporary power generation is greater than the power shortage, it means that the temporary perovskite solar cells can fill the power shortage. The power generation rate of a unit area of ​​temporary perovskite solar cells is the same as that of a unit area of ​​perovskite solar cells. The deployment time is obtained by dividing the power shortage by the power generation rate of a unit area of ​​temporary perovskite solar cells. If the predicted temporary power generation is less than the power shortage, it means that the temporary perovskite solar cells are insufficient to fill the power shortage, and it is necessary to temporarily activate the energy storage battery.

[0037] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0038] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A photovoltaic energy storage all-electric kitchen equipment and a low-carbon data energy management optimization system, characterized in that, Includes the following modules: The data acquisition module collects low-carbon data from all-electric kitchen equipment in real time through acquisition devices; The low-carbon assessment module is used to generate real-time low-carbon scores for all-electric kitchen equipment based on the collected low-carbon data, and to derive the low-carbon score change rate and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores. The electricity consumption prediction module is used to acquire historical electricity consumption data and build an electricity consumption prediction model, and use the electricity consumption prediction model to predict the electricity consumption of all-electric kitchen equipment throughout the day. The power generation prediction module is used to acquire historical power generation data and build a power generation prediction model, and then use the power generation prediction model to predict the power generation of perovskite solar cells throughout the day. The power generation decision module compares the predicted electricity consumption with the predicted power generation and decides whether to deploy temporary perovskite solar cells to increase power generation.

2. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 1, characterized in that, The all-electric kitchen equipment includes common kitchen appliances such as electric stoves, water heaters, and refrigerators. The electricity for the all-electric kitchen equipment comes from the power generation of perovskite solar cells. The low-carbon data includes real-time energy self-sufficiency rate, equipment energy efficiency ratio, carbon intensity factor, behavioral energy saving index, and environmental temperature adaptability. The real-time energy self-sufficiency rate is obtained by dividing the power generation of the perovskite solar cells by the real-time total power of the all-electric kitchen equipment. ； In the formula, V is the real-time energy self-sufficiency rate, E is the power generation of the perovskite solar cell, and P is the real-time total power of the all-electric kitchen equipment. The energy efficiency ratio of an equipment refers to the efficiency of converting electrical energy into useful output. It is calculated by dividing the output energy of an all-electric kitchen equipment by its input energy. ； In the formula, W represents the equipment energy efficiency ratio. This refers to the actual equipment energy efficiency ratio. The rated energy efficiency ratio of the equipment; Obtain real-time carbon intensity data from power grid operators; ； In the formula, X is the carbon strength factor. For actual carbon strength, The highest carbon strength; The behavioral energy efficiency index assesses a user's energy-saving habits when using devices and whether the device is turned off in a timely manner. ； In the formula, Y is the behavioral energy-saving index. For the actual number of energy-saving cycles, Total number of uses; Ambient temperature is obtained through a temperature sensor. Ambient temperature adaptability refers to the degree of compatibility between the ambient temperature and the suitable operating temperature of the equipment. ； In the formula, Z represents the environmental temperature adaptability. This refers to the actual ambient temperature. For the ideal ambient temperature, This refers to the temperature range.

3. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 2, characterized in that, The process of generating real-time low-carbon scores for all-electric kitchen equipment based on collected low-carbon data includes: Low-carbon rating S for all-electric kitchen equipment: In the formula, , , and These are weighting coefficients, obtained through training based on historical data.

4. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 3, characterized in that, The process of determining the rate of change and average low-carbon score of all-electric kitchen equipment based on multiple low-carbon scores includes: The operation of all-electric kitchen equipment throughout the day is divided into working periods when the equipment is used by humans and standby periods when the equipment is not used by humans. During working periods, the intensity and frequency of human use of kitchen equipment are high. During standby periods, some equipment in the all-electric kitchen is still in working condition, such as refrigerators and water heaters, which need to be kept running at all times. A first assessment cycle is set during the period of human use of all-electric kitchen equipment, and a second assessment cycle is set during the period of non-human use of all-electric kitchen equipment. During the period of human use of all-electric kitchen equipment, a corresponding real-time first low-carbon score needs to be obtained for each first assessment cycle. During the period of non-human use of all-electric kitchen equipment, a corresponding real-time second low-carbon score needs to be obtained for each second assessment cycle. The average first low-carbon score is calculated based on multiple first low-carbon scores throughout the day, and the average second low-carbon score is calculated based on multiple second low-carbon scores throughout the day. Take the first low-carbon scores for 2n first assessment periods, arrange the 2n first low-carbon scores in chronological order, calculate the average of the first n first low-carbon scores to obtain the average third low-carbon score, calculate the average of the last n first low-carbon scores to obtain the average fourth low-carbon score, subtract the average third low-carbon score from the average fourth low-carbon score to obtain the score difference, divide the absolute value of the score difference by the average third low-carbon score to obtain the change rate of the first low-carbon score, and obtain the change rate of the second low-carbon score using the same method.

5. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 4, characterized in that, The process of acquiring historical electricity consumption data and building an electricity consumption prediction model, and then using that model to predict the daily electricity consumption of all-electric kitchen appliances, includes: Factors affecting the daily electricity consumption of all-electric kitchen equipment include: the rate of change of the first low-carbon score, the average first low-carbon score, the rate of change of the second low-carbon score, the average second low-carbon score, the planned human usage time of the equipment, the non-human usage time of the equipment, and the historical average electricity consumption. Planned human usage time refers to the planned duration of human use of the device throughout the day, which is obtained based on the user's device usage plan. Non-human-caused equipment usage time refers to the total time spent using the equipment throughout the day excluding planned human-caused equipment usage time; Historical average electricity consumption refers to the average daily electricity consumption of all-electric kitchen equipment over a period of time. Obtain historical electricity consumption data of all-electric kitchen equipment throughout the day. The historical electricity consumption data includes the change rate of the first low-carbon score of all-electric kitchen equipment throughout the day, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the historical electricity consumption of all-electric kitchen equipment throughout the day. Based on the daily change rate of the first low-carbon score of all-electric kitchen equipment, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human use time of the equipment, the non-human use time of the equipment, the historical average electricity consumption, and the corresponding historical electricity consumption, an electricity consumption prediction set is generated and divided into the first training set and the first test set. Construct a first convolutional neural network, and use the change rate of the first low-carbon score, the average first low-carbon score, the change rate of the second low-carbon score, the average second low-carbon score, the planned human-used equipment time, the non-human-used equipment time, and the historical average electricity consumption in different historical electricity consumption data in the first training set as the input data of the first convolutional neural network, and use the corresponding historical electricity consumption in the first training set as the output data of the first convolutional neural network. The first convolutional neural network is trained to obtain the first initial convolutional neural network. The first initial convolutional neural network is validated using the first test set. The first initial convolutional neural network, whose output is less than or equal to the preset first test error threshold, is used as the electricity consumption prediction model. The changes in the first low-carbon score of the all-electric kitchen equipment throughout the day, the average first low-carbon score, the changes in the second low-carbon score, the average second low-carbon score, the planned human usage time, the non-human usage time, and the historical average electricity consumption are input into the electricity consumption prediction model to obtain the predicted electricity consumption of the all-electric kitchen equipment throughout the day.

6. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 5, characterized in that, The process of acquiring historical power generation data and constructing a power generation prediction model, and then using this model to predict the power generation of perovskite solar cells throughout the day, includes: Factors affecting the daily power generation of perovskite solar cells include: solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation. Obtain real-time solar radiation intensity from irradiance sensors or weather APIs; Obtain real-time cloud cover data from the weather API and calculate the percentage of cloud cover in the sky to obtain the cloud cover rate; The output efficiency of photovoltaic panels is obtained by dividing the actual power generation by the theoretical maximum power generation through monitoring and calculation of the output efficiency of photovoltaic panels. The output efficiency of photovoltaic panels is positively correlated with the cleanliness of photovoltaic panels. Historical average power generation refers to the average power generation data of perovskite solar cells over a past period. Obtain historical power generation data of perovskite solar cells throughout the day. The historical power generation data includes the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and historical power generation of perovskite solar cells throughout the day. Based on the solar irradiance, cloud cover, photovoltaic panel cleanliness, historical average power generation, and corresponding historical power generation of perovskite solar cells throughout the day from different historical power generation data, a power generation prediction set is generated and divided into a second training set and a second test set. A second convolutional neural network is constructed. The solar radiation intensity, cloud cover rate, photovoltaic panel cleanliness and historical average power generation in different historical power generation data in the second training set are used as the input data of the second convolutional neural network, and the corresponding historical power generation in the second training set is used as the output data of the second convolutional neural network. The second convolutional neural network is trained to obtain the second initial convolutional neural network. The second initial convolutional neural network is validated using the second test set. The second initial convolutional neural network that outputs a second test error threshold less than or equal to the preset second test error threshold is used as the power generation prediction model. The solar irradiance, cloud cover, photovoltaic panel cleanliness, and historical average power generation of the perovskite solar cell throughout the day are input into the power generation prediction model to obtain the predicted power generation of the perovskite solar cell throughout the day.

7. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 6, characterized in that, The process of comparing predicted electricity consumption with predicted electricity generation includes: The electricity consumption of the all-electric kitchen equipment throughout the day is predicted by the electricity consumption prediction model, and the power generation of the perovskite solar cells throughout the day is predicted by the power generation prediction model. The predicted electricity consumption and predicted power generation are then compared. If the predicted power consumption is less than the predicted power generation, it means that the power generation of the perovskite solar cells can meet the power consumption of the all-electric kitchen equipment for the whole day. Subtracting the predicted power consumption from the predicted power generation gives the surplus power, which can be stored in the energy storage battery. All-electric kitchens are usually equipped with two batteries. On the current day, one battery is the power supply battery and is fully charged to provide power to the all-electric kitchen equipment. The power generated by the perovskite solar cells is preferentially supplied to this battery. The other battery is the energy storage battery, which is used to receive the surplus power and needs to be charged through the grid until it is fully charged to prepare for the next day. On the next day, the power supply battery of the previous day becomes the energy storage battery, and the energy storage battery of the previous day becomes the power supply battery, and so on in a cycle. If the predicted electricity consumption is greater than the predicted power generation, it means that the power generation of the perovskite solar cells is not enough to meet the daily power consumption of the all-electric kitchen equipment. Subtracting the predicted power generation from the predicted electricity consumption gives the power gap, which needs to be filled by increasing the power generation of the perovskite solar cells. If increasing the power generation of the perovskite solar cells is still not enough to meet the power gap, then the energy storage battery needs to be temporarily activated.

8. The photovoltaic energy storage all-electric kitchen equipment and low-carbon data energy management optimization system according to claim 7, characterized in that, One way to increase the power generation of perovskite solar cells is to deploy temporary perovskite solar cells. The specific process includes: The temporary perovskite solar cells equipped in the all-electric kitchen are automatically deployed and put into power generation mode. Since the roof of the all-electric kitchen is already covered with the largest area of ​​perovskite solar cells, the temporary perovskite solar cells are usually hidden under the perovskite solar cells. They will only be temporarily deployed to generate electricity when there is a power shortage. The temporary perovskite solar cells cannot be deployed stably for a long time. Based on the prediction model of the area and power generation of temporary perovskite solar cells, the predicted temporary power generation of the temporary perovskite solar cells can be predicted. The predicted temporary power generation is compared with the power shortage. If the predicted temporary power generation is greater than the power shortage, it means that the temporary perovskite solar cells can fill the power shortage. The power generation rate of a unit area of ​​temporary perovskite solar cells is the same as that of a unit area of ​​perovskite solar cells. The deployment time is obtained by dividing the power shortage by the power generation rate of a unit area of ​​temporary perovskite solar cells. If the predicted temporary power generation is less than the power shortage, it means that the temporary perovskite solar cells are insufficient to fill the power shortage, and it is necessary to temporarily activate the energy storage battery.

Images