Photovoltaic lithium battery factory energy consumption data intelligent adjusting and optimizing system based on cloud computing

Abstract

The invention relates to the field of energy consumption intelligent regulation and control, in particular to a photovoltaic lithium battery factory energy consumption data intelligent regulation and optimization system based on cloud computing, which comprises a photovoltaic lithium battery data acquisition unit for acquiring related parameters of a related photovoltaic lithium battery factory according to sensors of a photovoltaic module, a lithium battery and power equipment; the photovoltaic system power generation prediction unit is used for establishing a photovoltaic system power generation prediction neural network model according to the obtained related data parameters of the photovoltaic lithium battery factory so as to obtain the predicted power generation condition of the photovoltaic power generation system; calculating an energy self-sufficiency rate and grading, and setting a production plan variation; the intelligent adjustment and optimization unit is used for optimizing the energy utilization efficiency to realize intelligent adjustment and optimization of energy consumption in combination with the real-time energy consumption data, the power generation prediction result and the energy cost factor; and the photovoltaic lithium battery factory energy consumption adjusting and monitoring unit establishes a photovoltaic lithium battery factory energy consumption adjusting and monitoring model according to the obtained photovoltaic lithium battery factory production plan variable quantity and the minimum photovoltaic lithium battery factory energy cost.

Description

Technical Field

[0001] The present invention relates to the field of intelligent energy consumption regulation, and particularly to an intelligent adjustment and optimization system for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing. Background Art

[0002] With the increasingly serious global energy crisis and environmental problems, the energy structure has gradually begun to transform. As important components of clean energy and energy storage technologies, photovoltaic power generation and lithium battery technologies have been widely used. However, photovoltaic and lithium battery factories have high energy consumption during the production process, and are affected by multiple factors such as weather, equipment status, and production plans, resulting in large fluctuations in energy consumption and low efficiency.

[0003] Traditional energy consumption management methods often rely on manual experience and simple data analysis, making it difficult to achieve accurate energy consumption prediction and optimization adjustment. The development of cloud computing technology has provided new possibilities for the real-time collection, storage, and analysis of energy consumption data, and it has gradually become possible to perform intelligent adjustment and optimization of the energy consumption of photovoltaic and lithium battery factories based on big data. However, the existing technologies still have the following problems: they do not clarify the energy supply situation according to the power generation situation of the photovoltaic system combined with real-time energy, and cannot efficiently and accurately set and regulate the change amount of the production plan; they do not consider the influencing factors related to the energy consumption of photovoltaic and lithium battery factories from multiple angles, resulting in a difference between the regulation of the production plan and the actual situation, leading to an increase in energy consumption and inability to further optimize; due to not conforming to the state of the lithium battery and the real-time situation of photovoltaic power generation, there is a deviation in energy cost, and it is impossible to minimize the energy consumption cost of photovoltaic and lithium battery factories, interfering with energy consumption adjustment; and they do not effectively monitor the energy consumption situation of photovoltaic and lithium battery factories in real time, making the energy consumption adjustment and optimization system lack stability and causing energy waste.

[0004] Therefore, an intelligent adjustment and optimization system for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing is needed. Summary of the Invention

[0005] The intelligent adjustment and optimization system for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing provided by the present invention aims to use cloud computing technology to efficiently and accurately set and regulate the change amount of the production plan according to the real-time power generation situation of the photovoltaic system combined with the energy supply situation, so as to optimize energy utilization to the greatest extent; consider the influencing factors related to the energy consumption of photovoltaic and lithium battery factories from multiple angles to ensure that the regulation of the production plan conforms to the actual situation, avoid an increase in energy consumption, and further optimize the energy utilization efficiency of photovoltaic and lithium battery factories; consider the state of the lithium battery and the real-time situation of photovoltaic power generation, and the system can accurately adjust the energy cost, reduce energy waste, and improve the accuracy and efficiency of energy consumption adjustment; effectively monitor the energy consumption situation of photovoltaic and lithium battery factories in real time to ensure the stability of the energy consumption adjustment and optimization system.

[0006] The technical solution of the present invention is specifically as follows: A smart adjustment and optimization system for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing, including the following: A photovoltaic and lithium battery data acquisition unit, a photovoltaic system power generation prediction unit, a smart adjustment and optimization unit, and a photovoltaic and lithium battery factory energy consumption adjustment and monitoring unit; The photovoltaic and lithium battery data acquisition unit obtains relevant parameters of the photovoltaic and lithium battery factory according to the sensors of photovoltaic modules, lithium batteries, and power equipment, and transmits the data to the photovoltaic system power generation prediction unit; The photovoltaic system power generation prediction unit establishes a photovoltaic system power generation prediction neural network model based on the obtained relevant data parameters of the photovoltaic and lithium battery factory to obtain the predicted power generation situation of the photovoltaic power generation system; calculates the energy self-sufficiency rate and divides it into levels, and sets the production plan change amount; The smart adjustment and optimization unit is used to optimize the energy utilization efficiency to achieve intelligent adjustment and optimization of energy consumption by combining real-time energy consumption data, power generation prediction results, and energy cost factors; The photovoltaic and lithium battery factory energy consumption adjustment and monitoring unit establishes a photovoltaic and lithium battery factory energy consumption adjustment and monitoring model based on the obtained production plan change amount of the photovoltaic and lithium battery factory and the minimum energy cost of the photovoltaic and lithium battery factory; The smart adjustment and optimization unit includes a primary adjustment module, a secondary adjustment module, and a tertiary adjustment module; The primary adjustment module calculates the production plan change amount correction coefficient according to the carbon emission, production plan flexibility, and error term; The secondary adjustment module analyzes and compares the lithium battery charge and discharge loss with the standard lithium battery charge and discharge loss situation, and determines whether to perform a secondary adjustment on the production plan change amount according to the comparison result; The tertiary adjustment module adjusts the energy cost of the photovoltaic and lithium battery factory according to the lithium battery state and the real-time situation of photovoltaic power generation.

[0007] Furthermore, in the photovoltaic system power generation prediction unit, it specifically includes: The photovoltaic system power generation prediction neural network model includes an input layer, an evaluation layer, a prediction layer, and an output layer; the input layer transmits the photovoltaic system operation data to the evaluation layer for measurement, analyzes the photovoltaic system power generation situation in the prediction layer, and outputs the prediction result in the output layer .

[0008] Furthermore, in the photovoltaic system power generation prediction unit, according to the predicted power generation of the photovoltaic power generation system and the monitored real-time energy demand , calculates the energy self-sufficiency rate , defines the thresholds representing low energy self-sufficiency rate and medium energy self-sufficiency rate; Represents the threshold between medium and high energy self - sufficiency rates, classifies the energy self - sufficiency rate of photovoltaic and lithium - battery factories, and sets the initial change amount of the production plan , and the specific process is as follows: When , the level is A at this time, and the preset first production plan change amount is , , represents the production plan adjustment coefficient corresponding to level A; When , the level is B at this time, and the preset first production plan change amount is , , represents the production plan adjustment coefficient corresponding to level B; When , the level is C at this time, and the preset first production plan change amount is , , represents the production plan adjustment coefficient corresponding to level C.

[0009] Furthermore, calculate the production plan change amount correction coefficient in the first - level adjustment module , and the specific process is as follows: ; Among them, represents the low - carbon emission correction coefficient; represents the high - carbon emission correction coefficient; represents the maximum value of carbon emissions; represents the influence coefficient of production plan flexibility. Specifically, , represents the production plan flexibility coefficient, represents the flexibility correction coefficient, , indicates complete flexibility, indicates complete rigidity; represents the influence coefficient of the error term. Specifically, , represents the prediction error of photovoltaic power generation, represents the maximum allowable error; represents the error correction coefficient; represents the carbon emissions; represents the threshold of carbon emissions.

[0010] Furthermore, in the first - level adjustment module, by comparing the production plan change amount correction coefficient with the comparison value of the preset production plan change amount correction coefficient and according to the comparison result, the production plan change amount Make adjustments, ; The specific process is as follows: If , then adjust the production plan change amount to , then define ; If , then adjust the production plan change amount to , then define ; If , then adjust the production plan change amount to , then define .

[0011] Furthermore, in the secondary adjustment module, represents the charge and discharge loss of the lithium battery, represents the charge and discharge loss situation of the standard lithium battery: ; Among them, represents the charge and discharge loss comparison coefficient of the lithium battery; if , it means that the actual charge and discharge loss is higher than the standard loss, and secondary adjustment is required; If , it means that the actual charge and discharge loss is lower than or equal to the standard loss, indicating that the energy consumption is currently within a reasonable range and no secondary adjustment is required.

[0012] Furthermore, when performing secondary adjustment, calculate the ratio of the charge and discharge loss comparison coefficient of the lithium battery to the preset charge and discharge loss comparison coefficient , ; At the same time, set the first ratio parameter and the second ratio parameter , and , respectively compare with and ; The specific process is as follows: If , then adjust the production plan change amount to ; If , then adjust the production plan change amount to ; If , then adjust the production plan change amount to ; Among them, Represent the corresponding control coefficients respectively, which are used to control the adjustment amplitude.

[0013] Furthermore, the three-level adjustment module specifically includes: Define the energy cost of the photovoltaic and lithium battery factory as , wherein, represents the photovoltaic power generation cost; represents the grid electricity price; indicates that only the part of electricity purchased from the grid is calculated; represents the photovoltaic power generation power; Introduce the health state factor to correct the energy cost of the photovoltaic and lithium battery factory. The specific process is as follows: ; wherein, represents the corrected energy cost of the photovoltaic and lithium battery factory.

[0014] Furthermore, in the energy consumption adjustment and monitoring unit of the photovoltaic and lithium battery factory, an energy consumption adjustment and monitoring model of the photovoltaic and lithium battery factory is established through adaptive learning. The adaptive network model combines the change in the production plan of the photovoltaic and lithium battery factory and the minimum energy cost of the photovoltaic and lithium battery factory to establish the connection between them. At the same time, an attention mechanism optimization algorithm is introduced to monitor the energy consumption of the factory in real time and dynamically adjust according to the actual situation: ; wherein, represents the output result of the energy consumption adjustment and monitoring model of the photovoltaic and lithium battery factory; represents the learning factor; represents the focus factor; represents the discount factor; represents the th moment in the monitoring; represents the optimized attention mechanism; represents the complexity; represents the number of neurons; represents the th weight of the neuron; represents the feature matrix of the input user power consumption prediction data information; represents the introduced additional attention guidance matrix.

[0015] Beneficial effects

[0016] 1. The present invention predicts the photovoltaic power generation through a neural network model for photovoltaic system power generation prediction, which can understand the power generation situation in advance, optimize energy distribution, and calculate the energy self-sufficiency rate in combination with real-time energy demand; by calculating the energy self-sufficiency rate and dividing it into levels, the energy supply situation is clarified, the production plan change amount is set according to different corresponding levels, and the production schedule is adjusted, and the production plan is adjusted according to the actual situation to better match energy supply and demand, avoid energy waste, improve energy utilization efficiency, provide data support for managers, and optimize production plan and energy scheduling decisions; at the same time, based on the cloud computing platform, real-time collection, processing and analysis of data are realized, and management efficiency is improved.

[0017] 2. By calculating the correction coefficient of the production plan change amount, the present invention can adjust the production plan more accurately to adapt to the actual energy consumption data and production situation. At the same time, considering the carbon emission factor, it can reduce carbon emissions, contribute to the realization of the factory's carbon neutrality and environmental protection goals, and by calculating the correction coefficient through the error term, it can reduce the impact of prediction errors on the production plan, improve the accuracy of the plan, and realize the adjustment and optimization of the energy consumption of the photovoltaic lithium battery factory; according to the flexibility of the production plan, it can quickly respond to changes in market demand and improve resource utilization efficiency; by dynamically adjusting the production plan change amount, the production plan is made more in line with the actual situation, which is more conducive to the intelligent control of the energy consumption of the photovoltaic lithium battery factory.

[0018] 3. The present invention can be adjusted according to the lithium battery state and the real-time situation of photovoltaic power generation, which can maximize the utilization of renewable energy and improve the energy utilization efficiency of the photovoltaic power generation system; by intelligently adjusting the energy cost, the factory can reasonably adjust the energy use during peak and off-peak periods, reduce the energy cost during high-energy consumption periods, thereby reducing the overall energy cost; according to the real-time situation of photovoltaic power generation, the energy supply can be flexibly adjusted, better respond to market demand and price fluctuations, optimize the energy procurement strategy, and provide data support for the subsequent energy consumption adjustment and monitoring process of the photovoltaic lithium battery factory.

[0019] 4. Through the monitoring model, the present invention can monitor the energy consumption situation of the photovoltaic lithium battery factory in real time, adjust according to the actual production plan change amount and the minimum energy cost, ensure the high efficiency and economy of energy utilization and the optimal energy consumption, and avoid energy waste; by dynamically adjusting the energy consumption through the model, reduce energy consumption fluctuations, improve the stability of the energy consumption adjustment and optimization system, reduce the operation cost of the photovoltaic lithium battery factory, and improve competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the structural diagram of the intelligent adjustment and optimization system for energy consumption data of a photovoltaic lithium battery factory based on cloud computing according to the present invention; Figure 2 is the schematic diagram of the adjustment and optimization unit according to the present invention; Figure 3This is a flowchart of the intelligent adjustment and optimization method for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing in the present invention. Specific embodiments

[0021] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments. At the same time, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] Referring to the appendix Figure 1 , this embodiment provides an intelligent adjustment and optimization system for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing, including the following: A photovoltaic and lithium battery data acquisition unit, a photovoltaic system power generation prediction unit, an intelligent adjustment and optimization unit, and a photovoltaic and lithium battery factory energy consumption adjustment and monitoring unit; The photovoltaic and lithium battery data acquisition unit obtains relevant parameters of the photovoltaic and lithium battery factory according to the sensors of photovoltaic modules, lithium batteries, and power equipment, and transmits the data to the photovoltaic system power generation prediction unit; The photovoltaic system power generation prediction unit establishes a photovoltaic system power generation prediction neural network model based on the obtained relevant data parameters of the photovoltaic and lithium battery factory to obtain the predicted power generation situation of the photovoltaic power generation system; calculates the energy self-sufficiency rate and divides it into levels, and sets the production plan change amount; The intelligent adjustment and optimization unit is used to optimize the energy utilization efficiency to achieve intelligent adjustment and optimization of energy consumption by combining factors such as real-time energy consumption data, power generation prediction results, and energy costs; The photovoltaic and lithium battery factory energy consumption adjustment and monitoring unit establishes a photovoltaic and lithium battery factory energy consumption adjustment and monitoring model according to the obtained production plan change amount of the photovoltaic and lithium battery factory and the minimum energy cost of the photovoltaic and lithium battery factory, and finds the optimal energy consumption adjustment plan; Referring to the appendix Figure 2 , the adjustment and optimization unit includes a primary adjustment module, a secondary adjustment module, and a tertiary adjustment module; The primary adjustment module calculates the production plan change amount correction coefficient according to the carbon emission, production plan flexibility, and error term; compares the production plan change amount correction coefficient with the preset production plan change amount correction coefficient comparison value, and adjusts the production plan change amount according to the comparison result; The secondary adjustment module compares the lithium battery charge and discharge loss with the standard lithium battery charge and discharge loss situation, and determines whether to perform a secondary adjustment on the production plan change amount according to the comparison result; The tertiary adjustment module adjusts the energy cost of the photovoltaic and lithium battery factory according to the state of the lithium battery and the real-time situation of photovoltaic power generation.

[0023] Referring to the appendix Figure 3, this embodiment provides an intelligent adjustment and optimization method for energy consumption data of a photovoltaic and lithium battery factory based on cloud computing, including the following steps: S1. Obtain relevant parameters of the photovoltaic and lithium battery factory according to the sensors of photovoltaic modules, lithium batteries, and power equipment, establish a neural network model for predicting power generation of the photovoltaic system, obtain the predicted power generation situation of the photovoltaic power generation system, calculate the energy self-sufficiency rate and divide it into levels, and set the change amount of the production plan. Install high-precision sensors at key positions such as photovoltaic modules, lithium batteries, and power equipment. The types of sensors include but are not limited to current sensors, voltage sensors, temperature sensors, humidity sensors, fiber optic sensors, etc., which are used to collect and monitor relevant parameters in real time, including photovoltaic power generation data, lithium battery energy storage data, power consumption data, environmental data, equipment operation data, etc. The data acquisition terminal is used to receive the data collected by the sensors, and perform preliminary processing and storage. At the same time, wired (such as Ethernet, RS485) or wireless (such as Wi-Fi, LoRa, ZigBee) communication technologies are used to transmit the data collected by the sensors to the cloud computing platform. Specifically, wireless communication technology is particularly suitable for distributed photovoltaic and lithium battery factories, which can reduce the wiring cost. In the embodiment of the present invention, edge computing capabilities are integrated into the data acquisition terminal or gateway device, and the collected data is preliminarily processed through existing technologies such as filtering, compression, and anomaly detection, reducing the data transmission volume and improving the real-time performance.

[0024] In the embodiment of the present invention, a neural network model for predicting power generation of the photovoltaic system is established, and the historical photovoltaic system operation-related data after data preprocessing is used as the training sample and the input data of the neural network model for predicting power generation of the photovoltaic system. The model is trained through deep learning. The neural network model for predicting power generation of the photovoltaic system includes an input layer, an evaluation layer, a prediction layer, and an output layer.

[0025] The training sample is expressed as , represents the operation data of the photovoltaic system obtained at any moment. Among them, , represents different moments when obtained. The types of data information collected at each moment are expressed as , where is the input of the neural network model for predicting power generation of the photovoltaic system. There are neurons in the input layer. The input layer transmits to the evaluation layer for analysis and determination. The specific process is as follows: ; ; Among them, represents the input of the evaluation layer; Represents the connection weight between the input layer and the evaluation layer; Represents the output result of the input layer; Represents the bias of the evaluation layer; Represents the output of the evaluation layer; Represents the influence coefficient of light intensity on the power generation of the photovoltaic system; Represents the influence coefficient of temperature on the power generation of the photovoltaic system; Represents at The light intensity information obtained at this time; Represents the average value of light intensity within the recording period; Represents at The temperature information obtained at this time; Represents the maximum value of the temperature difference within the recording period; Represents at The wind speed information obtained at this time; Represents the wind speed change rate; Represents the change function generated over time; Represents the influence coefficient generated by the change of environmental parameters during the evaluation process; Represents the total historical recording period; Represents The performance state of the photovoltaic module at this time; Represents the balance coefficient.

[0026] In the prediction layer, a prediction analysis of the power generation of the photovoltaic system is carried out, and the specific process is as follows: ; ; Among them, Represents the input of the prediction layer; Represents the connection weight value between the evaluation layer and the prediction layer; Represents the bias of the prediction layer; Represents the light intensity; Represents the orientation angle of the photovoltaic angle, that is, the angle between the direction directly facing the photovoltaic panel and the south direction; Represents the solar azimuth angle; Represents the tilt angle of the photovoltaic panel; Represents the dynamic change coefficient of cloud cover of the photovoltaic system; Represents at The cloud cover obtained at this time; Represents at The cloud cover obtained at this time; Represents the early stopping strategy coefficient of the model; Represents at The energy at this time; Represents at The expected energy at this time; Represents the output of the prediction layer; Represents the correction coefficient for the stability requirement of the power generation process of the photovoltaic system; Represents the total historical recording period.

[0027] The result is output in the output layer, specifically expressed as: ; Among them, Represents the output result of the output layer; Represents the connection weight between the prediction layer and the output layer; Represents the bias of the prediction layer. Finally, the power generation situation of the predicted photovoltaic power generation system is output in the output layer.

[0028] According to the predicted power generation of the photovoltaic power generation system And the monitored real-time energy demand , calculate the energy self-sufficiency rate ; In the embodiment of the present invention, the energy self-sufficiency rate represents the ratio of the predicted power generation of the photovoltaic power generation system to the real-time energy demand, reflecting the coverage degree of the photovoltaic power generation system for the energy demand; divide the level according to the energy self-sufficiency rate; the specific process is as follows: ; Among them, Represents the predicted; Represents the real-time energy demand obtained through monitoring; Represents the lithium battery at The discharge amount at this time; Represents the lithium battery at The charge amount at this time; Represents the energy utilization efficiency.

[0029] Now according to The value of and practical experience, define Represents the thresholds for low and medium energy self-sufficiency rates; Represents the threshold between medium and high self-sufficiency rates, and divides the energy self-sufficiency rate of the photovoltaic-lithium battery factory into levels. The specific process is as follows: When , the level is A at this time, indicating that the photovoltaic power generation is lower than the energy demand and the energy supply is insufficient; in the embodiment of the present invention, The value of is 0.6, The value of is 0.3. When , it indicates that the energy self-sufficiency rate is a low energy self-sufficiency rate; when , it indicates an extremely low energy self-sufficiency rate; When , the level is B at this time, indicating that the photovoltaic power generation is close to the energy demand and the energy supply is basically balanced; When When the level is C at this time, it indicates that the photovoltaic power generation is close to fully meeting the energy demand and the energy supply is sufficient; in the embodiment of the present invention, takes a value of 0.9, takes a value of 0.3. When , it indicates that the energy self-sufficiency rate is a high energy self-sufficiency rate; when , it indicates complete self-sufficiency and is basically in an ideal state; According to different corresponding levels, set the initial production plan change amount , adjust the production schedule to reduce the dependence on the external power grid, optimize energy consumption, optimize energy utilization efficiency, and thus intelligently adjust energy consumption.

[0030] When the level is A, preset the first production plan change amount to be , , represents the production plan adjustment coefficient corresponding to level A; When the level is B, preset the first production plan change amount to be , , represents the production plan adjustment coefficient corresponding to level B; When the level is C, preset the first production plan change amount to be , , represents the production plan adjustment coefficient corresponding to level C.

[0031] The present invention predicts the photovoltaic power generation through a photovoltaic system power generation prediction neural network model, can understand the power generation situation in advance, optimize energy distribution, and calculate the energy self-sufficiency rate in combination with real-time energy demand; by calculating the energy self-sufficiency rate and dividing levels, clarify the energy supply situation, set the production plan change amount according to different corresponding levels, and adjust the production schedule, adjust the production plan according to the actual situation, better match energy supply and demand, avoid energy waste, improve energy utilization efficiency, provide data support for managers, and optimize production plan and energy scheduling decisions; at the same time, based on the cloud computing platform, realize real-time data collection, processing and analysis, and improve management efficiency.

[0032] S2. Calculate the production plan change amount correction coefficient according to the carbon emission , production plan flexibility , error term . By comparing the production plan change amount correction coefficient with the comparison value of the preset production plan change amount correction coefficient, and adjusting the production plan change amount according to the comparison result.

[0033] In the primary adjustment module, according to the carbon emission , production plan flexibility , error term , so as to calculate the correction coefficient of the production plan change ; specifically, the error term refers to the error generated in historical data and the prediction process, which may affect the accuracy of the energy self-sufficiency rate and thus affect the adjustment of the production plan change; In the embodiment of the present invention, the carbon emission is obtained through the prior art , ; Among them, represents the direct carbon emission generated during the production process; represents the indirect carbon emission generated by the purchased energy, for example: grid power; According to historical experience and experiments, the threshold value of the carbon emission is defined , if , it represents low carbon emission; if , it represents high carbon emission.

[0034] Calculate the correction coefficient of the production plan change , and the specific process is as follows:

[0035] Among them, represents the low carbon emission correction coefficient; represents the high carbon emission correction coefficient; represents the maximum value of the carbon emission; represents the influence coefficient of the production plan flexibility. Specifically, , represents the production plan flexibility coefficient, represents the production plan flexibility coefficient, represents the flexibility correction coefficient, , indicates complete flexibility, indicates complete rigidity; represents the error term influence coefficient. Specifically, , represents the prediction error of photovoltaic power generation, represents the maximum allowable error; represents the error correction coefficient; By comparing the correction coefficient of the production plan change with the preset comparison value of the correction coefficient of the production plan change and adjusting the production plan change according to the comparison result, ; the specific process is as follows: If , then adjust the production plan change to , then define ; If , then adjust the production plan change to , then define ; If , then adjust the production plan change to , then define .

[0036] In the secondary adjustment module, based on the charge and discharge loss of the lithium battery , and the standard charge and discharge loss situation of the lithium battery for analysis and comparison, and determine whether to perform secondary adjustment on the production plan change according to the comparison result; in the embodiment of the present invention, the charge and discharge loss situation of the battery is inferred by analyzing historical charge and discharge data through the prior art, understanding the change trend and loss situation of the battery performance, and analyzing in combination with the battery characteristic curve to obtain the real-time charge and discharge loss situation; the specific process is as follows:

[0037] Among them, represents the charge and discharge loss comparison coefficient of the lithium battery; if , it indicates that the actual charge and discharge loss is higher than the standard loss, indicating higher energy consumption or a decline in battery performance, and secondary adjustment is required; If , it indicates that the actual charge and discharge loss is lower than or equal to the standard loss, indicating that the energy consumption is currently within a reasonable range and secondary adjustment is not required; Specifically, preset the charge and discharge loss comparison coefficient of the lithium battery as , calculate the ratio of the charge and discharge loss comparison coefficient of the lithium battery to the preset charge and discharge loss comparison coefficient , ; at the same time, set the first ratio parameter and the second ratio parameter , and , respectively compare with and ; the specific process is as follows: If , then adjust the production plan change to ; If , then adjust the production plan change to ; If , the production plan change amount is adjusted to ; where represent the corresponding control coefficients respectively, which are used to control the adjustment amplitude.

[0038] By calculating the correction coefficient of the production plan change amount, the present invention can adjust the production plan more accurately to adapt to the actual energy consumption data and production situation. At the same time, considering the carbon emission factor, it can reduce the carbon emission, contribute to the realization of the carbon neutrality and environmental protection goals of the factory. Moreover, by calculating the correction coefficient through the error term, it can reduce the influence of prediction error on the production plan, improve the accuracy of the plan, and realize the adjustment and optimization of the energy consumption of the photovoltaic and lithium battery factory; according to the flexibility of the production plan, it can quickly respond to the changes in market demand and improve the resource utilization efficiency; by dynamically adjusting the production plan change amount, the production plan can be made more in line with the actual situation, which is more conducive to the intelligent control of the energy consumption of the photovoltaic and lithium battery factory.

[0039] S3. In the three-level adjustment module, according to the state of the lithium battery and the real-time situation of photovoltaic power generation, the energy cost of the photovoltaic and lithium battery factory is adjusted.

[0040] Define the charging and discharging power of the lithium battery as , , where represents the rated power,[[]] represents the charging and discharging efficiency of the lithium battery,[[]] represents the current power,[[]] represents the health state of the lithium battery; specifically, if , it means that the lithium battery is charging; if , it means that the lithium battery is discharging; Define the grid power distribution , , where represents the factory load power,[[]] represents the photovoltaic power generation power; Then define the energy cost of the photovoltaic and lithium battery factory as , where represents the photovoltaic power generation cost; represents the grid electricity price; represents only calculating the part of purchasing electricity from the grid.[[]]

[0041] The health state of the lithium battery affects its charging and discharging efficiency and service life, and thus affects the energy cost. Now introduce the health state factor to correct the energy cost of the photovoltaic and lithium battery factory. The specific process is as follows:[[]]

[0042] Among them, represents the corrected energy cost of the photovoltaic and lithium battery factory; At the same time, the goal of adjustment and optimization is to minimize the energy cost of the photovoltaic and lithium battery factory, that is: , while meeting the factory load demand and lithium battery state constraints; Constraint conditions:

[0043] Among them, represents the maximum charge and discharge power of the lithium battery; represents the maximum allowable power of the power grid; finally, use to represent the corrected optimal energy cost of the photovoltaic and lithium battery factory.

[0044] The present invention adjusts according to the state of the lithium battery and the real-time situation of photovoltaic power generation, can make the most of renewable energy, and improve the energy utilization efficiency of the photovoltaic power generation system; by intelligently adjusting the energy cost, the factory can reasonably adjust the energy use during peak and off-peak periods, reduce the energy cost during high-energy consumption periods, thereby reducing the overall energy cost; according to the real-time situation of photovoltaic power generation, the energy supply can be flexibly adjusted, better respond to market demand and price fluctuations, optimize the energy procurement strategy, and provide data support for the subsequent energy consumption adjustment and monitoring process of the photovoltaic and lithium battery factory.

[0045] S4. According to the obtained change amount of the production plan of the photovoltaic and lithium battery factory and the minimum energy cost of the photovoltaic and lithium battery factory , establish an energy consumption adjustment and monitoring model for the photovoltaic and lithium battery factory to find the optimal energy consumption adjustment plan.

[0046] An energy consumption adjustment and monitoring model for the photovoltaic and lithium battery factory is established through adaptive learning. The adaptive network model combines the change amount of the production plan of the photovoltaic and lithium battery factory with the minimum energy cost of the photovoltaic and lithium battery factory . At the same time, an attention mechanism optimization algorithm is introduced to make the model pay more attention to key input information, monitor the energy consumption of the factory in real time, and dynamically adjust according to the actual situation to make the energy utilization more efficient.

[0047] By learning the attention weights, more attention is placed on important features in order to better understand the working conditions of the photovoltaic and lithium battery factory and extract useful information. The specific adjustment and optimization process is as follows: ; ; Among them, represents the output result of the energy consumption adjustment and monitoring model of the photovoltaic and lithium battery factory; represents the learning factor; represents the focus factor; represents the discount factor, which is used to measure the importance of future costs or rewards in current decisions; represents the th moment in monitoring; represents the optimized attention mechanism; represents the complexity, which is used to measure the complexity of non - linearity; represents the number of neurons; represents the weight of the th neuron; represents the introduced additional attention - guiding matrix; represents the activation function; represents the weight matrix, which is used to map the input features to the attention score space; represents the bias term, which is used to adjust the baseline value of the attention score; represents the value matrix; represents the dimension of the key vector.

[0048] Through the monitoring model, the present invention can monitor the energy consumption of the photovoltaic and lithium - battery factory in real time, adjust according to the actual production plan change amount and the minimum energy cost, ensure the high efficiency and economy of energy utilization and the optimal energy consumption, and avoid energy waste; by dynamically adjusting the energy consumption through the model, reduce the energy consumption fluctuation, improve the stability of the energy consumption regulation and optimization system, reduce the operation cost of the photovoltaic and lithium - battery factory, and improve the competitiveness.

[0049] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general - purpose computer, a special - purpose computer, an embedded processor, or other programmable data - processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data - processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0050] These computer program instructions can also be stored in a computer - readable memory that can direct a computer or other programmable data - processing device to work in a specific manner, so that the instructions stored in the computer - readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or multiple processes and / or blocks Figure 1 in one block or multiple blocks. Figure 1 steps.

[0052] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0053] The above content is only for explaining the technical idea of the present invention and cannot limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. The intelligent adjustment and optimization system for energy consumption data of photovoltaic lithium battery factories based on cloud computing is characterized by: Includes the following: Photovoltaic lithium battery data acquisition unit, photovoltaic system power generation prediction unit, intelligent regulation and optimization unit, photovoltaic lithium battery factory energy consumption regulation and monitoring unit; The photovoltaic lithium battery data acquisition unit acquires relevant parameters of the photovoltaic lithium battery factory according to the sensors of the photovoltaic components, lithium batteries and power equipment, and transmits the data to the photovoltaic system power generation prediction unit; The photovoltaic system power generation prediction unit establishes a photovoltaic system power generation prediction neural network model based on the obtained photovoltaic lithium battery factory related data parameters to obtain the predicted power generation of the photovoltaic power generation system; calculates the energy self-sufficiency rate and divides it into grades, and sets the production plan change amount; The intelligent adjustment and optimization unit is used to optimize energy utilization efficiency and realize intelligent adjustment and optimization of energy consumption by combining real-time energy consumption data, power generation prediction results and energy cost factors; The photovoltaic lithium battery factory energy consumption regulation monitoring unit establishes a photovoltaic lithium battery factory energy consumption regulation monitoring model according to the obtained photovoltaic lithium battery factory production plan change amount and photovoltaic lithium battery factory energy cost; The intelligent adjustment and optimization unit includes a primary adjustment module, a secondary adjustment module, and a tertiary adjustment module; The first-level adjustment module calculates the production plan change correction coefficient according to the carbon emissions, production plan flexibility, and error terms; The secondary adjustment module analyzes and compares the charge and discharge loss of the lithium battery with the charge and discharge loss of the standard lithium battery, and determines whether to make a secondary adjustment to the production plan change according to the comparison result; The three-level adjustment module adjusts the energy cost of the photovoltaic lithium battery factory according to the status of the lithium battery and the real-time situation of photovoltaic power generation.

2. According to the cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 1, it is characterized in that: The photovoltaic system power generation prediction unit specifically includes: The photovoltaic system power generation prediction neural network model includes an input layer, an evaluation layer, a prediction layer, and an output layer; the input layer transmits the photovoltaic system operation data to the evaluation layer for measurement, analyzes the photovoltaic system power generation situation in the prediction layer, and outputs the prediction results in the output layer .

3. The cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 2 is characterized in that: In the photovoltaic system power generation prediction unit, according to the predicted power generation of the photovoltaic power generation system Real-time energy demand monitoring , calculate the energy self-sufficiency rate ,definition indicating the thresholds for low and medium energy self-sufficiency rates; Indicates the threshold between medium energy self-sufficiency and high energy self-sufficiency, classifies the energy self-sufficiency of photovoltaic lithium battery factories, and sets the initial production plan change , the specific process is as follows: when When the level is A, the preset first production plan change is , , Indicates the production plan adjustment coefficient corresponding to level A; when When the level is B, the preset first production plan change is , , It indicates the production plan adjustment coefficient corresponding to level B; when When the level is C, the preset first production plan change is , , Indicates the production plan adjustment coefficient corresponding to level C.

4. The cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 1 is characterized in that: Calculate the production plan change correction coefficient in the first-level adjustment module , the specific process is as follows: ； in, represents the low carbon emission correction factor; Indicates the high carbon emission correction factor; Indicates the maximum carbon emission; represents the production plan flexibility influence coefficient. Specifically, , represents the production plan flexibility coefficient, represents the flexibility correction factor, , Description is completely flexible. Description Complete rigidity; represents the error term influence coefficient. Specifically, , represents the photovoltaic power generation prediction error, Indicates the maximum allowable error; represents the error correction factor; represents carbon emissions; Indicates the threshold value of carbon emissions.

5. The photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system based on cloud computing according to any one of claims 3 or 4, characterized in that: In the first-level adjustment module, the production plan change correction coefficient is Comparison value with the preset production plan change correction coefficient Compare and adjust the production plan changes according to the comparison results Make adjustments, ; The specific process is as follows: if , then the production plan change Adjust to , then define ; if , then the production plan change Adjust to , then define ; if , then the production plan change Adjust to , then define .

6. The cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 1 is characterized in that: In the secondary regulation module, Indicates the charge and discharge loss of lithium batteries. Indicates the charge and discharge loss of standard lithium batteries: ； in, Indicates the comparison coefficient of lithium battery charge and discharge loss; if , it means that the actual charge and discharge loss is higher than the standard loss, and secondary adjustment is required; if , it means that the actual charging and discharging loss is lower than or equal to the standard loss, which means that the energy consumption is currently within a reasonable range and no secondary adjustment is required.

7. The cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 6 is characterized in that: When performing secondary adjustment, calculate the comparison coefficient of lithium battery charge and discharge loss Comparison coefficient with preset lithium battery charge and discharge loss Ratio , ; Set the first ratio parameter at the same time and the second ratio parameter ,and , respectively and and For comparison; the specific process is as follows: if , then adjust the production plan change to ; if , then adjust the production plan change to ; if , then adjust the production plan change to ;in, Represents the corresponding control coefficients, which are used to control the adjustment amplitude.

8. The cloud computing-based photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system according to claim 1 is characterized in that: The three-level regulation module specifically includes: The energy cost of a photovoltaic lithium battery factory is defined as , ,in, represents the cost of photovoltaic power generation; Indicates the grid electricity price; Indicates that only the electricity purchased from the power grid is calculated; Represents photovoltaic power generation; Introducing health status factor The energy cost of the photovoltaic lithium battery factory is corrected. The specific process is as follows: ； in, Represents the corrected energy cost of the photovoltaic lithium battery factory.

9. The photovoltaic lithium battery factory energy consumption data intelligent adjustment and optimization system based on cloud computing according to any one of claims 2 or 7, characterized in that: In the photovoltaic lithium battery factory energy consumption regulation monitoring unit, the photovoltaic lithium battery factory energy consumption regulation monitoring model is established through adaptive learning. The adaptive network model is combined with the photovoltaic lithium battery factory production plan change Energy costs of photovoltaic lithium battery factories At the same time, the attention mechanism optimization algorithm is introduced to monitor the energy consumption of the factory in real time and adjust it dynamically according to the actual situation: ； in, Represents the output results of the energy consumption regulation monitoring model of the photovoltaic lithium battery factory; represents the learning factor; represents the focus factor; represents the discount factor; Indicates the monitoring time; Represents the optimized attention mechanism; Represents complexity; represents the number of neurons; Indicates The weights of the neurons; A feature matrix representing input user power consumption forecast data information; Represents the additional attention guidance matrix introduced.

Images