CN118134293A - User side energy management system and method - Google Patents

Abstract

The present invention relates to the field of energy management, and in particular, to a system and a method for user side energy management. The content comprises: acquiring and structuring real-time energy consumption data and environment parameter data; further performing preliminary analysis to obtain a preliminary analysis result; based on the preliminary analysis, carrying out deep analysis on the historical energy consumption data, the structured real-time energy consumption data and the environmental parameter data to obtain a deep analysis result; according to the preliminary analysis result, the deep analysis result and the user preference and demand, an energy optimization strategy is prepared; and generating an equipment adjusting instruction based on the energy optimizing strategy, and automatically adjusting the setting of the energy using equipment. The problem that energy consumption cannot be adjusted due to untimely monitoring of energy consumption peaks is solved; under changing environmental conditions, the influence of environmental factors on energy consumption cannot be accurately quantified; and in environments where demand and supply dynamically change, it is impossible to ensure user comfort while optimizing energy consumption accurately.

Description

User side energy management system and method

Technical Field

The present invention relates to the field of energy management, and in particular, to a system and a method for user side energy management.

Background

In the current energy management field, systems are often faced with challenges in how to effectively manage and optimize energy consumption to meet environmental sustainability and economic benefits. Conventional energy management systems rely primarily on static energy consumption monitoring and control strategies, which often fail to respond in real time to changes in the environment or dynamic adjustments of user demand. In addition, many systems lack the ability to combine historical data with real-time data for in-depth analysis, resulting in inefficient energy use and the inability to fully utilize existing data resources to optimize energy allocation and consumption. Environmental factors such as temperature, humidity, illumination and the like have significant effects on energy consumption, but conventional systems often fail to effectively quantify the specific effects of these factors on energy consumption, and it is difficult to adjust energy use strategies according to environmental changes. Furthermore, user comfort is also an important consideration in energy management, however many existing solutions may ignore the user's actual experience and comfort while pursuing energy efficiency.

However, at least the following technical problems exist: the problem that the energy consumption cannot be adjusted due to the fact that the peak value of the energy consumption is not monitored in time, so that the energy use efficiency and the cost efficiency cannot be maximized; under changing environmental conditions, the influence of environmental factors on energy consumption cannot be accurately quantified; and in environments where demand and supply dynamically change, it is impossible to ensure user comfort while optimizing energy consumption accurately.

Disclosure of Invention

The invention provides a system and a method for managing energy of a user side, which aim to solve the problems that energy consumption cannot be adjusted due to untimely monitoring of energy consumption peaks, so that energy use efficiency and cost efficiency cannot be maximized; under changing environmental conditions, the influence of environmental factors on energy consumption cannot be accurately quantified; and in environments where demand and supply dynamically change, it is impossible to ensure user comfort while optimizing energy consumption accurately.

The invention relates to a system and a method for managing energy sources at a user side, which concretely comprise the following technical schemes:

The method for managing the energy of the user side comprises the steps of carrying out structuring treatment on real-time energy consumption data and environment parameter data, carrying out preliminary analysis on the structured real-time energy consumption data and environment parameter data, and further carrying out deep analysis, and is characterized in that the preliminary analysis comprises the following steps: carrying out preliminary analysis on the structured real-time energy consumption data and environment parameter data through an energy flow matrix algorithm and an environment influence response algorithm to obtain a preliminary analysis result;

The in-depth analysis includes: based on the preliminary analysis, carrying out deep analysis on the historical energy consumption data, the structured real-time energy consumption data and the environmental parameter data to obtain a deep analysis result;

Further, according to the preliminary analysis result, the deep analysis result and the user preference and demand, an energy optimization strategy is prepared; and generating an equipment adjusting instruction based on the energy optimizing strategy, and automatically adjusting the setting of the energy using equipment.

Preferably, the preliminary analysis specifically includes:

In the process of preliminary analysis, an energy flow matrix algorithm is introduced to predict and locate peak periods of energy consumption.

Preferably, the energy flow direction matrix algorithm specifically includes:

the specific implementation process of the energy flow matrix algorithm is as follows:

Firstly, defining an energy flow matrix;

And then calculating the energy consumption fluctuation of the time window by using a sliding window technology, wherein the specific formula is as follows:

，

Wherein, Expressed in time/>Time within time window (th)Fluctuation degree of energy consumption of the individual devices; /(I)Is the window size; /(I)Is/>Within each time period/>The energy consumption of the individual devices; /(I)Is/>Average energy consumption of individual devices;

finally, the peak period is determined ：

，

Wherein,Representing a peak period; /(I)Indicating the total number of devices to be monitored;

Further, the time of the energy consumption peak is determined by the peak period.

Preferably, the preliminary analysis further comprises:

in the process of preliminary analysis, an environmental impact response algorithm is introduced to quantitatively process the influence of environmental parameters on energy consumption.

Preferably, the environmental impact response algorithm specifically includes:

The environmental impact response algorithm models by analyzing the correlation between environmental parameters and energy consumption, and quantifies the influence of environmental factors; the specific implementation process of the environment influence response algorithm is as follows:

First, define the environmental impact response function Modeling is realized:

，

Wherein, 、/>And/>Time/>, respectivelyTemperature, humidity and air pressure; /(I),/>,/>,/>,/>,/>Is a model parameter;

further, the model parameters are optimized:

，

Wherein, Representing the correlation coefficient,/>Is time/>Is not limited by the total energy consumption of (2);

Finally obtaining the quantized result of the influence of the environmental parameters on the energy consumption 。

Preferably, the adjustment of the energy optimization strategy specifically includes:

a dynamic preference adjustment algorithm is introduced to dynamically adjust the energy optimization strategy based on real-time feedback and historical preferences of the user.

Preferably, the dynamic preference adjustment algorithm specifically includes:

In the implementation process of the dynamic preference adjustment algorithm, a user satisfaction function is established to obtain a user satisfaction score; the specific implementation process is as follows:

，

Wherein, Representing a user satisfaction score; /(I)Expressed in time/>Is set in the environment of the vehicle; Is at time/> Is a user-preferred temperature of (1); /(I)To adjust parameters of preference sensitivity.

Preferably, the dynamic preference adjustment algorithm further includes:

Introducing a dynamic adjustment factor in the implementation process of the dynamic preference adjustment algorithm, and calculating the dynamic adjustment factor according to the user satisfaction degree score; the specific formula is as follows:

，

Wherein, Is a dynamic adjustment factor; /(I)Is an adjustment coefficient; /(I)And/>Is a fourier coefficient; /(I)Is the fundamental frequency, representing the time of day frequency of variation; /(I)Representing the number of the expansion of the Fourier series; /(I)Represents the/>An expansion series of the individual fourier;

Applying the dynamic adjustment factor to the current energy setting and adjusting the energy setting parameters;

，

Wherein, Is the energy setting change rate; /(I)Is the attenuation coefficient; /(I)The amplitude coefficient is adjusted; /(I)Expressed in time/>Energy consumption setting of (a);

Finally, calculate the differential equation The obtained solution is the energy setting parameter of the next time step, and the device adjusting operation is implemented according to the adjusted energy setting parameter.

A user side energy management system is applied to the user side energy management method, and comprises the following parts:

the system comprises a real-time energy monitoring module, a structured processing module, a data primary analysis module, a database, a data deep analysis module, an intelligent energy optimization module and a feedback mechanism module;

The real-time energy monitoring module is used for collecting and recording real-time data of energy consumption and environmental conditions in real time, obtaining real-time energy consumption data and environmental parameter data, and sending the real-time energy consumption data and the environmental parameter data to the structural processing module;

The structuring processing module is used for structuring the real-time energy consumption data and the environment parameter data and sending the structured real-time energy consumption data and the structured environment parameter data to the data primary analysis module;

The database is used for storing historical energy consumption data and user historical preference;

the data preliminary analysis module is used for carrying out preliminary analysis on the structured real-time energy consumption data and the environment parameter data to obtain a preliminary analysis result; the preliminary analysis result is sent to an intelligent energy optimization module;

The data deep analysis module is used for obtaining a deep analysis result by analyzing historical energy consumption data and structured real-time energy consumption data and environmental parameter data on the basis of preliminary analysis; transmitting the deep analysis result to an intelligent energy optimization module;

The intelligent energy optimization module is used for preparing an energy optimization strategy according to the preliminary analysis result, the deep analysis result, the user preference and the requirement; generating an equipment adjustment instruction based on an energy optimization strategy to automatically adjust the setting of energy using equipment;

The feedback mechanism module acquires user preference and demand and feeds the user preference and demand back to the intelligent energy optimization module.

The technical scheme of the invention has the beneficial effects that:

1. According to the method, the energy consumption peak period is dynamically captured by introducing an energy flow matrix algorithm and combining a sliding window technology; the environmental impact response algorithm quantifies the influence of environmental factors by establishing a model between environmental parameters and energy consumption, so that the energy management strategy is adapted to different environmental conditions, and the adaptability and the efficiency of the energy management system are improved.

2. According to the invention, by combining history and real-time data and combining characteristic engineering and characteristic derivative technology, the energy management system can deeply understand the influence of energy consumption modes and environmental factors, so that data analysis is more comprehensive, and a scientific basis is provided for formulating a more effective energy management strategy; introducing a dynamic adjustment algorithm based on real-time feedback and historical preference to realize real-time optimization of energy setting, and optimizing energy consumption while ensuring user comfort; based on the comprehensive analysis result and the user preference, a specific device adjustment instruction is generated by using a rule engine technology, and the energy optimization strategy is automatically implemented.

Drawings

FIG. 1 is a block diagram of a client energy management system according to the present invention;

Fig. 2 is a flowchart of a method for managing energy at a user terminal according to the present invention.

Detailed Description

In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

The following specifically describes a specific scheme of a system and a method for user side energy management provided by the invention with reference to the accompanying drawings.

Referring to fig. 1, a block diagram of a client energy management system according to an embodiment of the present invention is shown, where the system includes the following parts:

the system comprises a real-time energy monitoring module, a structured processing module, a data primary analysis module, a database, a data deep analysis module, an intelligent energy optimization module and a feedback mechanism module;

The real-time energy monitoring module is used for collecting and recording real-time data of energy consumption and environmental conditions in real time through various intelligent sensors and meters arranged at a user side to obtain real-time energy consumption data and environmental parameter data, and sending the real-time energy consumption data and the environmental parameter data to the structural processing module;

the intelligent sensors and meters such as electric energy meters, temperature and humidity sensors and lighting controllers are used for providing real-time data about energy consumption and environmental conditions;

the energy consumption data such as power consumption amount, ambient temperature;

The structuring processing module is used for structuring the real-time energy consumption data and the environment parameter data to obtain structured real-time energy consumption data and environment parameter data, and sending the structured real-time energy consumption data and the structured environment parameter data to the data primary analysis module;

The database is used for storing historical energy consumption data and user historical preference;

The data preliminary analysis module is used for carrying out preliminary analysis on the structured real-time energy consumption data and the environment parameter data to obtain a preliminary analysis result; the primary analysis result comprises an energy use mode and an energy waste point; the preliminary analysis result is sent to an intelligent energy optimization module;

The data deep analysis module is used for identifying potential energy saving opportunities by analyzing historical energy consumption data, structured real-time energy consumption data and environment parameter data on the basis of preliminary analysis and obtaining deep analysis results; the deep analysis result comprises an energy conservation proposal and an optimization strategy, and is sent to an intelligent energy optimization module;

The intelligent energy optimization module is used for preparing an energy optimization strategy according to the preliminary analysis result, the deep analysis result, the user preference and the requirement, and automatically adjusting the setting of energy using equipment based on an energy optimization strategy generation equipment adjustment instruction so as to realize the energy management of a user side;

The energy optimization strategy comprises the steps of adjusting temperature setting of an air conditioner and a heating system, adjusting illumination brightness and optimizing equipment operation time;

The feedback mechanism module acquires user preference and demand and feeds the user preference and demand back to the intelligent energy optimization module.

Referring to fig. 2, a flowchart of a method for managing energy at a user terminal according to an embodiment of the present invention is shown, where the method includes the following steps:

S1, acquiring real-time energy consumption data and environment parameter data, and adopting an intelligent energy data structuring processing algorithm to carry out structuring processing on the real-time energy consumption data and the environment parameter data; performing preliminary analysis on the structured real-time energy consumption data and the environment parameter data to obtain a preliminary analysis result;

real-time data of energy consumption and environmental conditions are collected and recorded in real time through various intelligent sensors and meters arranged at a user side, and real-time energy consumption data and environmental parameter data are obtained; intelligent sensors and meters such as electric energy meters, temperature and humidity sensors, lighting controllers for providing real-time data about energy consumption and environmental conditions; energy consumption data such as power consumption amount, room temperature;

Carrying out structuring processing on the real-time energy consumption data and the environment parameter data by utilizing an intelligent energy data structuring processing algorithm to obtain structured real-time energy consumption data and environment parameter data; the specific implementation process is as follows:

Firstly, carrying out data cleaning on real-time energy consumption data and environment parameter data, wherein the data cleaning comprises the steps of identifying abnormal values by using a statistical method (such as a box graph method), and correcting (such as an average value of adjacent points) or marking as invalid for data points which are beyond a reasonable range (such as indoor readings with the temperature lower than a freezing point) so as to be eliminated during further analysis; for fewer missing data points, the missing values may be filled with average, median, or domain-specific knowledge (e.g., seasonal variations); for time series data, filling the missing values by adopting interpolation methods (such as linear interpolation and a time series prediction model) of similar time points; identifying and processing duplicate records, identifying duplicate records based on key fields (such as time stamp and equipment ID), and determining whether to keep one record, merge the records or delete all duplicate items according to business logic for the duplicate records; obtaining the cleaned real-time energy consumption data and environment parameter data; formatting the cleaned real-time energy consumption data and environment parameter data to obtain real-time energy consumption data and environment parameter data in a unified format; and carrying out standardization processing on the formatted real-time energy consumption data and environment parameter data to obtain the standardized real-time energy consumption data and environment parameter data, and carrying out structuring processing on the standardized real-time energy consumption data and data points in the environment parameter data after metadata are added to obtain the structured real-time energy consumption data and environment parameter data. The formatting, normalization and structuring are all technical means well known to those skilled in the art, and will not be described in detail herein.

Performing preliminary analysis on the structured real-time energy consumption data and the environment parameter data to obtain a preliminary analysis result; the specific implementation process is as follows:

firstly, extracting features by using the existing feature engineering extraction method to obtain features which are convenient to analyze, such as total energy consumption, peak energy consumption time period and environmental temperature change in each hour or every day; simultaneously determining analysis indexes, wherein the analysis indexes comprise energy use intensity, load and environmental impact analysis; the energy efficiency of a building or equipment in unit area or unit time can be quantified by the energy use intensity, and the energy efficiency is one of key indexes for identifying an energy use mode and detecting energy waste points; the load refers to the energy demand of the energy management system at any given time point or time period, and the change of the energy demand along with time is represented by a load curve so as to analyze the energy demand; environmental impact analysis, which considers the impact of environmental parameters such as temperature, humidity and the like on energy consumption; based on analysis indexes, the change modes of energy consumption along with time are analyzed by using the existing time sequence analysis algorithm, including seasonal change, weekend and difference between workdays, and meanwhile, similar energy use behaviors are classified by using the existing cluster analysis algorithm, and typical energy use modes such as night illumination and air conditioner use peaks are identified; further detecting energy waste points; identifying abnormal energy consumption behaviors by using a statistical method, and determining energy waste points based on the abnormal energy consumption behaviors, such as energy leakage caused by equipment not being closed; comparing the actual energy use data with an energy efficiency reference or an expected target through a comparison analysis method, and identifying areas or equipment with low energy use efficiency; and finally, obtaining a preliminary analysis result according to the processing, wherein the preliminary analysis result comprises an energy use mode and an energy waste point.

In order to accurately predict and position the peak period of energy consumption, introducing an energy flow direction matrix algorithm; the energy flow matrix algorithm is used for enhancing the dynamic performance of peak detection by constructing an energy flow matrix and introducing a sliding window technology of a time sequence; the specific implementation process of the energy flow matrix algorithm is as follows:

Each row of the energy flow matrix represents a time period, each column represents a device, and the elements in the energy flow matrix represent the energy consumption of the device in the time period;

First, define an energy flow matrix ：

，

Wherein,Is/>Within each time period/>Energy consumption of individual devices,/>，/>；/>Representing the total number of time periods analyzed throughout the observation period; /(I)Indicating the total number of devices to be monitored;

Then, calculating the energy consumption fluctuation of the time window by using a sliding window technology; the energy consumption fluctuation of each device in each time window is calculated by using a sliding window method, so that the dynamic capturing capability of energy consumption change is enhanced:

，

Wherein, Is the window size,/>Is/>Average energy consumption of individual devices; /(I)Expressed in time/>When in a specific time window, the first/>Fluctuation degree of energy consumption of the individual devices; /(I)Is/>Within each time period/>The energy consumption of the individual devices;

further, a peak period is determined ：

，

The peak period can be used to determine which point in time has the greatest sum of the energy consumption fluctuations among all time windows, and thus the time of the energy consumption peak.

In order to accurately capture the influence of environmental parameters on energy consumption, an environmental influence response algorithm is introduced, and the quantitative treatment of the influence of the environmental parameters on the energy consumption is realized; the environmental impact response algorithm models by analyzing the correlation between environmental parameters and energy consumption to quantify the impact of environmental factors; the specific implementation process of the environment influence response algorithm is as follows:

First, define the environmental impact response function Modeling is realized:

，

Wherein, 、/>And/>Time/>, respectivelyTemperature, humidity and air pressure; /(I),/>,/>,/>,/>,/>Is a model parameter;

further, the model parameters are optimized to maximize the correlation between the environmental parameters and the energy consumption data:

，

Wherein, Representing the correlation coefficient,/>Is time/>Is not limited by the total energy consumption of (2);

Finally obtaining the quantized result of the influence of the environmental parameters on the energy consumption Providing a data basis for subsequent processing.

S2, carrying out deep analysis on the historical energy consumption data, the structured real-time energy consumption data and the environmental parameter data on the basis of preliminary analysis to obtain a deep analysis result; according to the preliminary analysis result, the deep analysis result and the user preference and demand, an energy optimization strategy is prepared; and generating an equipment adjusting instruction based on the energy optimizing strategy, and automatically adjusting the setting of the energy using equipment.

On the basis of preliminary analysis, carrying out deep analysis on historical energy consumption data, structured real-time energy consumption data and environmental parameter data from a database, identifying potential energy saving opportunities and obtaining a deep analysis result; the specific implementation process is as follows:

Firstly, integrating historical energy consumption data, structured real-time energy consumption data and environmental parameter data by using the existing data fusion technology to obtain a fused data set; simultaneously, carrying out format unification processing on the fused data set to obtain a data set with uniform format so as to facilitate processing; carrying out feature engineering treatment on the data set with uniform format, and simultaneously carrying out feature derivatization treatment by adopting the existing feature derivatization technology to obtain a comprehensive feature set; identifying energy use modes by using a clustering algorithm for the comprehensive feature set, such as using a K-means or hierarchical clustering algorithm to divide the data into several groups, each group representing a specific energy use behavior; meanwhile, an association rule mining technology is used for finding out the energy use relation between equipment or different time periods, such as the association between the use peak of certain equipment and specific environmental parameters; finally, the existing machine learning model is used for deep analysis, the energy consumption trend is predicted, the potential energy saving opportunity is identified, and the future energy demand and the use mode are predicted through time sequence analysis, so that the energy distribution and the use strategy are optimized; obtaining an in-depth analysis result according to the identified potential energy saving opportunities and the prediction result obtained through time sequence analysis; the in-depth analysis results include energy conservation recommendations and optimization strategies, such as strategies to reduce energy usage for a particular time period or condition, to adjust operating parameters of heating and cooling systems, to optimize lighting control strategies, or to adjust equipment usage schedules to reduce energy waste.

Further, according to the preliminary analysis result, the deep analysis result, the user preference and the requirement, an energy optimization strategy is prepared, and an equipment adjustment instruction is generated based on the energy optimization strategy to automatically adjust the setting of energy using equipment so as to realize the energy management of a user side; the specific implementation process is as follows:

Firstly, integrating the results of preliminary analysis and deep analysis to obtain a comprehensive analysis result; the comprehensive analysis result comprises an identified energy use mode, an energy saving opportunity and a suggested optimization strategy; user preference and demand, such as temperature preference, illumination intensity and equipment use time, are obtained through user feedback; based on comprehensive analysis results and user preferences, using a rule engine technology to balance analysis suggestions and user demands, and based on different scenes and conditions (such as seasonal changes, holidays and special events), continuously adjusting and optimizing to adapt to the changes to obtain an energy optimization strategy; converting the energy optimization strategy into specific equipment adjustment instructions, such as adjusting temperature settings of air conditioning and heating systems, adjusting brightness of illumination, or optimizing operation time of important equipment; the device automatically adjusts the setting according to the received adjusting instruction so as to realize the energy management of the user side.

In the implementation process of using a rule engine to balance analysis suggestions and user demands, in order to accurately realize dynamic adjustment of user preferences and energy-saving measures, a dynamic preference adjustment algorithm is introduced, and an energy optimization strategy is dynamically adjusted based on real-time feedback of users and user history preferences from a database so as to improve the user satisfaction and the energy efficiency of an energy management system, and the operation of the energy management system is aimed at being adjusted in real time so as to meet the changing preferences of users, thereby improving the energy efficiency and the user satisfaction, and the implementation process is as follows:

Establishing a user satisfaction function:

establishing a user satisfaction function according to user behaviors and feedback Calculating a deviation between the actual environment setting and the user setting preference:

，

Wherein, Representing a user satisfaction degree score, reflecting the acceptance degree of the user on the current environment setting; Expressed in time/> Is set in the environment of the vehicle; /(I)Is at time/>Is a user-preferred temperature of (1); /(I)Controlling the reaction speed of satisfaction to temperature deviation for adjusting the parameter of preference sensitivity;

Further, introducing a dynamic adjustment factor, calculating the dynamic adjustment factor according to the user satisfaction score and introducing a Fourier series ：

，

Wherein,Is a dynamic adjustment factor, and is used for adjusting energy setting according to an adjustment coefficient obtained by calculation of a user satisfaction degree score so as to improve user comfort degree; /(I)Is an adjustment coefficient for controlling the coefficient of the dynamic adjustment factor amplitude; /(I)AndIs a fourier coefficient; the Fourier coefficient considers the influence of a time periodicity factor on a dynamic adjustment factor, so that the continuity and periodicity of the adjustment energy optimization strategy are ensured; /(I)Is a fundamental frequency representing the time-of-day variation frequency for periodically adjusting the calculation of the dynamic adjustment factor; /(I)Representing the number of the expansion of the Fourier series; /(I)Represents the/>An expansion series of the individual fourier;

further, applying a dynamic adjustment factor to the current energy setting, adjusting the energy setting parameters to accommodate the user preferences:

，

Wherein, Is the rate of change of the energy setting, describing the rate of change of the energy setting over time; /(I)Is an attenuation coefficient describing the rate at which the energy setting naturally decreases over time; /(I)The amplitude coefficient is adjusted, and the intensity of the adjustment action is controlled so as to realize ideal energy use efficiency and user comfort level; /(I)Expressed in time/>Energy consumption setting of (a);

Finally, calculating differential equation by using Euler method The obtained solution is the energy setting parameter of the next time step, and the equipment adjusting operation, such as the air conditioning temperature and the illumination brightness, is implemented according to the adjusted energy setting parameter.

In summary, the invention completes a system and a method for managing user side energy.

The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.

The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (9)

1. The method for managing the energy of the user side comprises the steps of carrying out structuring treatment on real-time energy consumption data and environment parameter data, carrying out preliminary analysis on the structured real-time energy consumption data and environment parameter data, and further carrying out deep analysis, and is characterized in that the preliminary analysis comprises the following steps: carrying out preliminary analysis on the structured real-time energy consumption data and environment parameter data through an energy flow matrix algorithm and an environment influence response algorithm to obtain a preliminary analysis result;

The in-depth analysis includes: based on the preliminary analysis, carrying out deep analysis on the historical energy consumption data, the structured real-time energy consumption data and the environmental parameter data to obtain a deep analysis result;

Further, according to the preliminary analysis result, the deep analysis result and the user preference and demand, an energy optimization strategy is prepared; and generating an equipment adjusting instruction based on the energy optimizing strategy, and automatically adjusting the setting of the energy using equipment.

2. The method for managing energy of a user terminal according to claim 1, wherein the preliminary analysis specifically comprises:

In the process of preliminary analysis, an energy flow matrix algorithm is introduced to predict and locate peak periods of energy consumption.

3. The method for managing energy resources at a user terminal according to claim 2, wherein said energy flow matrix algorithm comprises:

the specific implementation process of the energy flow matrix algorithm is as follows:

Firstly, defining an energy flow matrix;

And then calculating the energy consumption fluctuation of the time window by using a sliding window technology, wherein the specific formula is as follows:

，

Wherein, Expressed in time/>Time within time window (th)Fluctuation degree of energy consumption of the individual devices; /(I)Is the window size; is/> Within each time period/>The energy consumption of the individual devices; /(I)Is/>Average energy consumption of individual devices;

finally, the peak period is determined ：

，

Wherein,Representing a peak period; /(I)Indicating the total number of devices to be monitored;

Further, the time of the energy consumption peak is determined by the peak period.

4. The method for managing energy at a client according to claim 1, wherein said preliminary analysis further comprises:

in the process of preliminary analysis, an environmental impact response algorithm is introduced to quantitatively process the influence of environmental parameters on energy consumption.

5. The method for managing energy of a client according to claim 4, wherein the environmental impact response algorithm specifically comprises:

The environmental impact response algorithm models by analyzing the correlation between environmental parameters and energy consumption, and quantifies the influence of environmental factors; the specific implementation process of the environment influence response algorithm is as follows:

First, define the environmental impact response function Modeling is realized:

，

Wherein, 、/>And/>Time/>, respectivelyTemperature, humidity and air pressure; /(I),/>,/>,/>,/>,/>Is a model parameter;

further, the model parameters are optimized:

，

Wherein, Representing the correlation coefficient,/>Is time/>Is not limited by the total energy consumption of (2);

Finally obtaining the quantized result of the influence of the environmental parameters on the energy consumption 。

6. The method for managing energy at a user terminal according to claim 1, wherein the adjusting of the energy optimization strategy specifically comprises:

a dynamic preference adjustment algorithm is introduced to dynamically adjust the energy optimization strategy based on real-time feedback and historical preferences of the user.

7. The method for managing energy of a client according to claim 6, wherein the dynamic preference adjustment algorithm specifically comprises:

In the implementation process of the dynamic preference adjustment algorithm, a user satisfaction function is established to obtain a user satisfaction score; the specific implementation process is as follows:

，

Wherein, Representing a user satisfaction score; /(I)Expressed in time/>Is set in the environment of the vehicle; Is at time/> Is a user-preferred temperature of (1); /(I)To adjust parameters of preference sensitivity.

8. The method for managing energy at a client according to claim 7, wherein said dynamic preference adjustment algorithm further comprises:

Introducing a dynamic adjustment factor in the implementation process of the dynamic preference adjustment algorithm, and calculating the dynamic adjustment factor according to the user satisfaction degree score; the specific formula is as follows:

，

Wherein, Is a dynamic adjustment factor; /(I)Is an adjustment coefficient; /(I)And/>Is a fourier coefficient; /(I)Is the fundamental frequency, representing the time of day frequency of variation; /(I)Representing the number of the expansion of the Fourier series; /(I)Represents the/>An expansion series of the individual fourier;

Applying the dynamic adjustment factor to the current energy setting and adjusting the energy setting parameters;

，

Wherein, Is the energy setting change rate; /(I)Is the attenuation coefficient; /(I)The amplitude coefficient is adjusted; /(I)Expressed in time/>Energy consumption setting of (a);

Finally, calculate the differential equation The obtained solution is the energy setting parameter of the next time step, and the device adjusting operation is implemented according to the adjusted energy setting parameter.

9. A customer premise energy management system for use in a customer premise energy management method as claimed in claim 1, comprising the steps of:

the system comprises a real-time energy monitoring module, a structured processing module, a data primary analysis module, a database, a data deep analysis module, an intelligent energy optimization module and a feedback mechanism module;

The real-time energy monitoring module is used for collecting and recording real-time data of energy consumption and environmental conditions in real time, obtaining real-time energy consumption data and environmental parameter data, and sending the real-time energy consumption data and the environmental parameter data to the structural processing module;

The structuring processing module is used for structuring the real-time energy consumption data and the environment parameter data and sending the structured real-time energy consumption data and the structured environment parameter data to the data primary analysis module;

The database is used for storing historical energy consumption data and user historical preference;

the data preliminary analysis module is used for carrying out preliminary analysis on the structured real-time energy consumption data and the environment parameter data to obtain a preliminary analysis result; the preliminary analysis result is sent to an intelligent energy optimization module;

The data deep analysis module is used for obtaining a deep analysis result by analyzing historical energy consumption data and structured real-time energy consumption data and environmental parameter data on the basis of preliminary analysis; transmitting the deep analysis result to an intelligent energy optimization module;

The intelligent energy optimization module is used for preparing an energy optimization strategy according to the preliminary analysis result, the deep analysis result, the user preference and the requirement; generating an equipment adjustment instruction based on an energy optimization strategy to automatically adjust the setting of energy using equipment;

The feedback mechanism module acquires user preference and demand and feeds the user preference and demand back to the intelligent energy optimization module.