Electric energy substitution benefit evaluation method and system

Abstract

The invention discloses an electric energy substitution benefit evaluation method and system, and relates to the technical field of electric energy benefit evaluation, and the method comprises the steps: deploying non-intrusive monitoring equipment, collecting user power consumption data, carrying out the preprocessing, and extracting the characteristics of the user power consumption data; performing clustering analysis according to the user power consumption data features to obtain user tags, and analyzing user behaviors by using a machine learning algorithm according to the user tags and the power consumption data features to construct a user behavior model; establishing an electric energy alternative scheme library based on the user behavior model, and evaluating alternative scheme benefits to generate an evaluation report; and obtaining and displaying the evaluation report, and storing the evaluation report in a database. According to the method, the accuracy of user behavior analysis is improved under the condition that the privacy security of the user is guaranteed, the relevance between the user features and the user tags and the user is improved, the decision-making efficiency and scientificity of the user are improved, and the user satisfaction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy benefit evaluation, and in particular to an electric energy substitution benefit evaluation method and system. Background Art

[0002] With the continuous growth of global energy demand and the increasing environmental pressure, how to effectively utilize clean energy and improve energy efficiency has become an urgent need of modern society. As one of the core means to cope with energy crisis and environmental protection, electric energy substitution technology has received widespread attention and application in recent years. Electric energy substitution usually refers to the introduction of renewable energy such as solar energy, wind energy, natural gas to replace traditional fossil energy in order to reduce carbon emissions and optimize the energy structure. However, the existing electric energy substitution evaluation method mainly relies on macro-power load analysis, and fails to accurately analyze the electricity consumption behavior, characteristics and adaptability of individual users to different alternatives. It not only ignores the personalized needs of users, but also makes it difficult to provide effective alternative suggestions, thus affecting the maximization of the benefits of electric energy substitution. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing electric energy substitution benefit evaluation method and system, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the existing electric energy substitution evaluation method mainly relies on macroscopic power load analysis, and fails to accurately analyze the electricity consumption behavior, characteristics and adaptability of individual users to different alternative solutions.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for evaluating the benefits of electric energy substitution, which includes deploying non-invasive monitoring equipment to collect user electricity consumption data for preprocessing and extracting user electricity consumption data features; performing cluster analysis based on user electricity consumption data features to obtain user tags, and using a machine learning algorithm to analyze user behavior based on user tags and electricity consumption data features to construct a user behavior model; establishing an electric energy substitution solution library based on the user behavior model, and evaluating the benefits of the substitution solutions to generate an evaluation report; obtaining the evaluation report for display and storing it in a database.

[0006] As a preferred solution of the electric energy substitution benefit evaluation method of the present invention, the non-intrusive monitoring equipment is deployed to collect user electricity consumption data for pre-processing, and the user electricity consumption data features are extracted. The non-intrusive load monitoring equipment is deployed in the user's electricity consumption environment to collect user electricity consumption data in combination with smart meters and the Internet of Things, and the user electricity consumption data is cleaned, denoised and standardized, and the quarterly imbalance coefficient K and annual load factor L of the standardized user electricity consumption data are extracted: , ;in is the maximum load in the ith month, is the annual maximum load, is the electricity consumption in the ith month, is the total number of hours in a year; the quarterly imbalance coefficient K and the annual load factor L are concatenated to form the user characteristic X.

[0007] As a preferred solution of the electric energy substitution benefit evaluation method of the present invention, wherein: the cluster analysis is performed according to the user's electricity consumption data characteristics to obtain user tags, and the user behavior is analyzed using a machine learning algorithm according to the user tags and electricity consumption data characteristics to construct a user behavior model, including: Set the number of clusters c and the fuzziness parameter m, randomly generate the membership value of each user feature X belonging to the cluster and perform normalization to obtain the initial membership value Constructing the initial membership matrix , and the sum of all initial memberships is 1; according to the initial membership matrix Calculate the initial cluster center of each cluster : in is the initial membership of the k-th user to the i-th cluster, is the user feature of the kth user, n is the number of users; get the initial cluster center Then, update the membership matrix : in and are the distances between the kth user and the i-th cluster center and the j-th cluster center respectively; The cluster center is updated again through the updated membership matrix, and the cluster center and the membership matrix are updated iteratively until the change of the membership matrix is ​​less than the preset threshold. Cluster labels are added to users according to the clustering results, and the final membership matrix and user cluster labels are output; Use ARIMA model to predict user electricity consumption based on user electricity consumption data The user characteristics and membership matrix are input into the SVM model to analyze the user behavior and predict the user's electricity consumption. , user behavior and user tags to establish a user behavior model.

[0008] As a preferred solution of the electric energy substitution benefit evaluation method of the present invention, wherein: the establishment of an electric energy substitution solution library based on the user behavior model refers to setting the type of alternative energy, obtaining the parameters of each alternative energy including power, energy efficiency ratio and operating cost, and extracting the predicted user power consumption from the user behavior model. , calculate the power generation at the predicted time t according to the power and energy efficiency ratio of each alternative energy , and calculate the operating cost at the forecast time t, and the power generation at the forecast time t And predict user electricity consumption For comparison, if the power generation Greater than or equal to power consumption , then the parameters of alternative energy types, power generation and operating costs are used to form an electric energy alternative plan. Less than power consumption , then exclude the alternative energy from the types of alternative energy, and integrate all electric energy alternatives to establish an electric energy alternative solution library.

[0009] As a preferred solution of the method for evaluating the benefits of electric energy substitution described in the present invention, wherein: the evaluation of the benefits of the substitution solution to generate an evaluation report refers to extracting user tags and user behaviors in the user behavior model as user input; Construct a convolutional neural network, define the input as user input and electric energy alternatives, and the output as the benefits of the electric energy alternatives. Use the training set to iteratively train the convolutional neural network, and set the cross entropy loss function and Adam optimizer to iteratively optimize the convolutional neural network parameters. The user input and each electricity alternative are input into the convolutional neural network to obtain the benefits of each electricity alternative for the user, and the benefits are sorted from high to low to generate an evaluation report.

[0010] As a preferred scheme of the method for evaluating the benefits of electric energy substitution described in the present invention, wherein: obtaining the evaluation report for display refers to obtaining the benefit evaluation report of the electric energy substitution plan and displaying it to the user using a visual chart, recommending the electric energy substitution plan to the user based on the evaluation report, the user selecting the electric energy substitution plan through the evaluation report, and recording the electric energy substitution plan selected by the user.

[0011] As a preferred solution of the method for evaluating the benefits of electric energy substitution described in the present invention, the storage in the database refers to storing the evaluation report and the electric energy substitution plan selected by the user in a local database after obtaining them, performing vulnerability and integrity detection on the data stored in the local database each time storage is performed, and synchronously uploading the stored data to the blockchain for backup on a regular basis.

[0012] Another object of the present invention is to provide an electric energy substitution benefit evaluation system, which comprises: The data acquisition module is used to deploy load monitoring equipment to collect user power consumption data for preprocessing and extract user characteristics; The behavior analysis module is used to perform cluster analysis on user characteristics to obtain user tags, and use machine learning algorithms to analyze user behavior and establish a user behavior model; The scheme evaluation module is used to establish a library of electric energy alternative schemes based on the user behavior model, and to evaluate the benefits of the electric energy alternative schemes and generate an evaluation report to recommend to users; The display storage module is used to display and store backup of the assessment report.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned electric energy substitution benefit assessment method when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for evaluating the benefits of electric energy substitution.

[0015] The beneficial effects of the present invention are as follows: the present invention acquires user electricity consumption data by deploying non-invasive monitoring equipment to extract user characteristics, and constructs a user behavior model based on user characteristic analysis of user tags and user behaviors, thereby improving the accuracy of user behavior analysis while ensuring user privacy and security, and improving the relevance of user characteristics and user tags to users. At the same time, a user electricity alternative solution library is established through the user behavior model to conduct benefit evaluation, helping users analyze the benefits of different electricity alternative solutions, thereby improving user decision-making efficiency and scientificity, and improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is a flow chart of the electricity substitution benefit assessment method.

[0018] Figure 2 This is a structural diagram of the electric energy substitution benefit evaluation system. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments. Example

[0022] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for evaluating the benefits of electric energy substitution, the method for evaluating the benefits of electric energy substitution comprising: S1. Deploy non-intrusive monitoring equipment to collect user electricity consumption data for pre-processing and extract user electricity consumption data features; Specifically, deploy non-intrusive monitoring equipment to collect user electricity consumption data for pre-processing and extract the characteristics of user electricity consumption data. Deploy non-intrusive load monitoring equipment in the user's electricity consumption environment, combine smart meters and the Internet of Things to collect user electricity consumption data, and clean, denoise and standardize the user electricity consumption data to extract the quarterly imbalance coefficient K and annual load factor L of the standardized user electricity consumption data: , ;in is the maximum load in the ith month, is the annual maximum load, is the electricity consumption in the ith month, is the total number of hours in a year (calculated based on 365 days); the quarterly imbalance coefficient K and the annual load factor L are concatenated to form the user characteristic X.

[0023] Non-intrusive monitoring equipment is combined with smart meters and deployed in the user's power consumption environment through the Internet of Things technology to collect accurate user power consumption data. Compared with traditional invasive monitoring methods, non-intrusive equipment will not modify or directly access the user's existing power system, which not only improves the convenience of data collection, but also greatly protects the user's privacy and security, while reducing the cost of equipment maintenance. In addition, the deployment of non-intrusive equipment combined with the Internet of Things technology can remotely monitor large-scale user power consumption data, thereby improving the breadth and real-time nature of data collection. Abnormal data and noise are inevitably present in user power consumption data. Through data cleaning and denoising, the reliability and accuracy of the data can be effectively improved. This processing step is particularly important when the user's power consumption environment is complex and fluctuating. The cleaned and denoised data can eliminate the interference caused by measurement errors or transmission failures, thereby ensuring the robustness of subsequent analysis. This lays a solid foundation for the extraction of user features, so that the subsequent user behavior model can more realistically reflect the user's actual power consumption. By extracting the quarterly imbalance coefficient and the annual load factor, the invention can quantify the user's electricity consumption fluctuation and load utilization efficiency. The quarterly imbalance coefficient can reveal the user's seasonal electricity consumption pattern and help identify the electricity consumption during peak and trough periods, thereby providing a basis for the selection of electric energy alternatives. The annual load factor reflects the uniformity of the user's electricity consumption throughout the year and the overall load level, and helps evaluate whether the user has fully utilized the existing power resources. Through these two key indicators, more targeted alternative energy solutions can be provided to users, and the accuracy and applicability of the evaluation results can be improved. The quarterly imbalance coefficient and the annual load factor are spliced ​​into a user feature vector X. This operation makes the user's electricity consumption pattern specific and standardized. In the subsequent user behavior modeling process, the feature vector X can be used for cluster analysis and machine learning algorithms to identify the electricity consumption habits and behavior patterns of different users. Through this data-driven analysis, users can more accurately select electric energy alternatives that suit them, improve the efficiency of alternative energy use, reduce energy costs, and maximize environmental benefits.

[0024] S2. Perform cluster analysis based on the user's electricity consumption data characteristics to obtain user tags, and use machine learning algorithms to analyze user behavior based on user tags and electricity consumption data characteristics to build a user behavior model; Specifically, cluster analysis is performed based on the user's electricity consumption data characteristics to obtain user tags, and a machine learning algorithm is used to analyze user behavior based on the user tags and electricity consumption data characteristics to build a user behavior model, including setting the number of clusters c and the fuzziness parameter m, randomly generating the membership value of each user feature X belonging to the cluster and performing normalization processing to obtain the initial membership value. Constructing the initial membership matrix , and the sum of all initial memberships is 1; according to the initial membership matrix Calculate the initial cluster center of each cluster : in is the initial membership of the k-th user to the i-th cluster, is the user feature of the kth user, n is the number of users; get the initial cluster center Then, update the membership matrix : in and are the distances between the kth user and the i-th cluster center and the j-th cluster center respectively; The cluster center is updated again through the updated membership matrix, and the cluster center and the membership matrix are updated iteratively until the change of the membership matrix is ​​less than the preset threshold. Cluster labels are added to users according to the clustering results, and the final membership matrix and user cluster labels are output; Use ARIMA model to predict user electricity consumption based on user electricity consumption data The user characteristics and membership matrix are input into the SVM model to analyze the user behavior and predict the user's electricity consumption. , user behavior and user tags to establish a user behavior model.

[0025] Cluster analysis is the key starting point of the entire invention process. Through cluster analysis of user electricity consumption data, users can be divided into groups with similar electricity consumption characteristics. Setting the appropriate number of clusters and fuzziness parameters can help optimize the clustering results and ensure the differences between different user groups and the similarities between users in the same group. By clustering user feature vectors, not only can the differences in users' electricity consumption habits be discovered, but user labels can also be generated based on different electricity consumption behaviors. This process makes subsequent model training more targeted, thus laying the foundation for personalized electricity substitution solutions. By setting the fuzzy average The number of clusters and fuzziness parameters in the value clustering are randomly initialized, and the membership value of each user feature belonging to each clustering cluster is normalized to ensure that the sum of each user's membership to different clusters is 1. This design not only retains the fuzziness of user behavior, but also provides a stable basis for the subsequent calculation of clustering centers. The initial membership matrix is ​​updated iteratively and gradually converges to the optimal result. Based on the analysis of user electricity consumption data, the model is used to predict the user's future electricity consumption. The model can generate accurate future electricity consumption forecasts based on trends, periodic fluctuations and random fluctuations in time series. This step is crucial in the evaluation of the benefits of user electricity substitution. It can provide reliable electricity consumption forecast data for the actual application of alternative solutions and ensure that alternative solutions can meet future electricity demand. Through the model, the user's behavior pattern can be further extracted based on the user's electricity consumption characteristics and clustering analysis results. The model is particularly suitable for processing nonlinear data. By mapping user characteristics to high-dimensional space, the complex relationship in user behavior can be captured more comprehensively. Combined with the user's clustering labels and predicted electricity consumption, the model can generate an accurate user behavior model, which can process multi-dimensional complex data and accurately extract hidden patterns in user behavior. Combined with the model's electricity consumption forecast, the accuracy of the user behavior model is further enhanced. This user behavior model can not only be used for the analysis of current electricity demand, but also provide a behavioral basis for future electricity substitution benefit evaluation. The establishment of the user behavior model provides an accurate user behavior data basis for the alternative solution, ensuring that the alternative solution can maximize its economic benefits, energy efficiency and environmental protection. Through dynamic adjustment and personalized analysis, the user behavior model can help users make more scientific decisions and significantly improve users' acceptance and satisfaction with alternative solutions.

[0026] S3. Establish a library of electric energy alternatives based on the user behavior model, and evaluate the benefits of alternatives to generate an evaluation report; Specifically, establishing an electricity alternative solution library based on the user behavior model means setting the types of alternative energy, obtaining the parameters of each alternative energy including power, energy efficiency ratio and operating cost, and extracting the predicted user electricity consumption from the user behavior model. , calculate the power generation at the predicted time t according to the power and energy efficiency ratio of each alternative energy , and calculate the operating cost at the forecast time t, and the power generation at the forecast time t And predict user electricity consumption For comparison, if the power generation Greater than or equal to power consumption , then the parameters of alternative energy types, power generation and operating costs are used to form an electric energy alternative plan. Less than power consumption , then exclude the alternative energy from the types of alternative energy, and integrate all electric energy alternatives to establish an electric energy alternative solution library.

[0027] By setting different types of alternative energy (such as solar energy, wind energy, natural gas, etc.) and obtaining key parameters of each energy, including power, energy efficiency ratio and operating cost, the purpose of this operation is to ensure that the alternative scheme can reflect the actual power generation capacity and cost-effectiveness of different energy sources, and help users make scientific decisions. Power determines the maximum power output that each alternative energy can provide, while energy efficiency ratio directly affects energy conversion efficiency. Operating cost is the economic factor that ultimately determines the user's choice. By setting the types of alternative energy, the invention can provide a variety of electric energy alternative schemes according to the specific needs of users. This step can flexibly combine the characteristics of multiple alternative energy sources to help users balance power generation, cost and energy efficiency in actual use, and improve the overall efficiency of energy use. At the same time, this step also lays a data foundation for subsequent alternative scheme calculations, so that the calculation results can more accurately reflect the actual energy usage. Based on the user behavior model, the invention extracts the user's power consumption forecast for a period of time in the future. This forecast value is based on the user's historical power consumption data, behavior patterns, seasonal changes and other factors, and is obtained through ARIMA or other time series prediction models. The predicted power consumption provides a clear demand target for the alternative energy scheme, thereby The power generation of the alternative solution can accurately match the user's needs. This step ensures that the design of the alternative solution does not rely on general power demand assumptions, but is customized based on the user's personalized needs, so as to ensure that the power generation can fully meet the user's power demand and avoid the situation of excess or insufficient power generation. This personalized alternative solution improves the accuracy of energy substitution and improves the user's satisfaction with the alternative energy solution. Through accurate power generation calculation, the invention can ensure that the alternative energy can maximize the energy utilization efficiency while meeting the user's needs. Moreover, by evaluating the operating cost of each alternative energy, the user can choose the most appropriate alternative solution based on economic efficiency, which not only improves the scientific nature of the user's decision-making, but also helps the user to reduce the overall energy cost while saving energy. The establishment of the electric energy alternative solution library provides users with clear and comprehensive energy alternative options. Compared with a single energy solution, users can view the power generation capacity, economic benefits and energy efficiency ratio of different alternative energy sources in the solution library. Through this multi-dimensional comparison, users can more scientifically and reasonably choose the most appropriate energy alternative solution. At the same time, this process greatly improves the decision-making efficiency, reduces the user's blind choice in energy substitution, and optimizes the energy usage pattern.

[0028] Further, evaluating the benefits of alternative solutions to generate an evaluation report refers to extracting user labels and user behaviors in the user behavior model as user input; Construct a convolutional neural network, define the input as user input and electric energy alternatives, and the output as the benefits of the electric energy alternatives. Use the training set to iteratively train the convolutional neural network, and set the cross entropy loss function and Adam optimizer to iteratively optimize the convolutional neural network parameters. The user input and each electricity alternative are input into the convolutional neural network to obtain the benefits of each electricity alternative for the user, and the benefits are sorted from high to low to generate an evaluation report.

[0029] Through personalized user labels and behavior input, the invention can more accurately identify user preferences and needs during the evaluation of alternative solutions. Compared with traditional general evaluation methods, input based on user behavior models greatly improves the accuracy and scientificity of the evaluation, and provides users with more targeted alternative energy recommendations. Compared with traditional linear models or simple machine learning algorithms, CNN can better capture the complex nonlinear relationship between users and energy solutions, especially in the case of large data volumes or high dimensions. Through the feature extraction capabilities of CNN, the invention can ensure that the benefit evaluation of alternative solutions has higher accuracy and interpretability. The use of cross-entropy loss function and Adam optimizer significantly improves the efficiency and accuracy of model training. Through these two optimization strategies, CNN can converge to the optimal solution faster, reduce training time, and avoid the problem of the model falling into local optimality. This is particularly critical when processing large amounts of user data and complex energy solutions, ensuring the real-time and accuracy of the benefit evaluation of alternative solutions. By processing user input and alternative solution parameters through a convolutional neural network, the invention can provide users with accurate alternative energy benefit evaluations. This process greatly improves the matching degree of alternative solutions, allowing users to make the best choice based on scientific evaluation results. Compared with traditional manual evaluation methods, the benefit evaluation based on CNN is faster and more accurate, which improves the user's decision-making efficiency. By sorting the benefits of alternative solutions, users can quickly find the energy alternative that best meets their needs. The evaluation report provides users with a comprehensive and intuitive comparison basis, avoiding the trouble of users blindly choosing among many alternative solutions. In addition, the evaluation report can be further adjusted in combination with the user's personalized needs to ensure that each user can obtain the best alternative energy solution.

[0030] S4. Obtain the evaluation report for display and store it in the database; Specifically, obtaining the evaluation report for display means obtaining a benefit evaluation report of the electric energy alternatives and displaying it to the user using visual charts, recommending the electric energy alternatives to the user based on the evaluation report, the user selecting the electric energy alternative based on the evaluation report, and recording the electric energy alternative selected by the user.

[0031] The generation of the evaluation report is data-driven, taking into account multiple dimensions to ensure the scientificity and rationality of the alternatives. Users can clearly see the advantages and disadvantages of each alternative energy source and make more informed choices. Compared with traditional manual analysis, the systematically generated evaluation report avoids human errors and greatly improves the accuracy and objectivity of the evaluation. Visual charts enhance the user experience and make complex technical reports easier to understand, which not only shortens the user's decision-making time, but also helps users better understand the relationship between data and make data-based choices. The visual presentation method can also enhance the user's sense of participation and increase the user's trust in the system's recommendations. The recommendation function of the electric energy alternative greatly simplifies the user's selection process and avoids the situation where users have difficulty making decisions due to information overload. Through personalized recommendations, the system can better meet the needs of different users. The report can meet the specific needs of users and improve the pertinence and feasibility of alternative solutions. The recommendation function ensures that users can quickly find the best solution among many solutions and optimizes the decision-making process. The user's independent choice enhances the actual application effect of the alternative solutions. With the support of scientific data in the report, users can more clearly understand the advantages and disadvantages of each alternative solution and ensure that their decisions are based on comprehensive and objective information. This process effectively reduces the uncertainty in user selection and improves the acceptance of alternative solutions and user satisfaction. The recording and feedback optimization function of user selection improves the learning ability of the system, enabling the system to continuously improve the evaluation and recommendation process of alternative solutions. Through the data-driven feedback mechanism, the system can more accurately predict user needs and improve the accuracy of subsequent recommendations of alternative solutions. This continuous optimization mechanism ensures the long-term benefits of the system and the continuous improvement of user experience.

[0032] Furthermore, storing in a database means that the evaluation report and the electric energy alternative selected by the user are stored in a local database, and each time storage is performed, the data stored in the local database is checked for vulnerabilities and integrity, and the stored data is synchronously and regularly uploaded to the blockchain for backup.

[0033] Through the storage of local databases, the user's operating efficiency and data access speed are significantly improved. In addition, the user data stored locally has a high degree of privacy, avoiding the exposure of sensitive data on the network and improving the security of user data. Vulnerability detection and integrity detection significantly enhance the security and reliability of data. Vulnerability detection can prevent malicious attacks and data leakage. Integrity detection ensures the accuracy of data during transmission and storage, and prevents data from being tampered with or lost. This provides users with a safe and reliable operating environment to ensure the accuracy of assessment reports and alternatives. By uploading data to the blockchain for backup, the present invention provides users with a highly secure and traceable data protection mechanism. The distributed storage of the blockchain ensures that the backup of data will not be lost due to damage to a single node. At the same time, its tamper-proof nature ensures the integrity and credibility of the data. The user's data can be safely stored for a long time under multiple guarantees. The data synchronization function ensures the consistency of local storage and blockchain backup data, avoiding problems caused by data asynchrony. This mechanism not only improves the efficiency of data management, but also ensures that users can obtain the latest and complete copy of the data when data recovery is required. Example

[0034] Reference Figure 2 , which is a second embodiment of the present invention, and which is different from the previous embodiment, provides an electric energy substitution benefit evaluation system, which includes: The data acquisition module is used to deploy load monitoring equipment to collect user power consumption data for preprocessing and extract user characteristics; The behavior analysis module is used to perform cluster analysis on user characteristics to obtain user tags, and use machine learning algorithms to analyze user behavior and establish a user behavior model; The scheme evaluation module is used to establish a library of electric energy alternative schemes based on the user behavior model, and to evaluate the benefits of the electric energy alternative schemes and generate an evaluation report to recommend to users; The display storage module is used to display and store backup of the assessment report.

[0035] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0036] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0037] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0038] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0039] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the benefits of electric energy substitution, characterized in that: include, Deploy non-intrusive monitoring equipment to collect user electricity consumption data for pre-processing and extract user electricity consumption data features; Perform cluster analysis based on the user's electricity consumption data characteristics to obtain user tags, and use machine learning algorithms to analyze user behavior based on user tags and electricity consumption data characteristics to build a user behavior model; Establish a library of electricity alternatives based on user behavior models, and evaluate the benefits of alternatives to generate evaluation reports; Obtain the assessment report for display and store it in the database.

2. The method for evaluating the benefits of electric energy substitution according to claim 1, characterized in that: The non-intrusive monitoring equipment is deployed to collect user electricity consumption data for pre-processing, and the user electricity consumption data features are extracted. The non-intrusive load monitoring equipment is deployed in the user's electricity consumption environment to collect user electricity consumption data in combination with smart meters and the Internet of Things, and the user electricity consumption data is cleaned, denoised and standardized, and the quarterly imbalance coefficient K and annual load factor L of the standardized user electricity consumption data are extracted: , ;in is the maximum load in the ith month, is the annual maximum load, is the electricity consumption in the ith month, is the total number of hours in a year; the quarterly imbalance coefficient K and the annual load factor L are concatenated to form the user characteristic X.

3. The method for evaluating the benefits of electric energy substitution according to claim 2, characterized in that: The method of obtaining user tags by clustering analysis based on the user's electricity consumption data characteristics and constructing a user behavior model by analyzing user behaviors using a machine learning algorithm based on the user tags and electricity consumption data characteristics includes: Set the number of clusters c and the fuzziness parameter m, randomly generate the membership value of each user feature X belonging to the cluster and perform normalization to obtain the initial membership value Constructing the initial membership matrix , and the sum of all initial memberships is 1; according to the initial membership matrix Calculate the initial cluster center of each cluster : in is the initial membership of the k-th user to the i-th cluster, is the user feature of the kth user, n is the number of users; Get the initial cluster center Then, update the membership matrix : in and The distances between the kth user and the ith cluster center and the jth cluster center are calculated respectively; the cluster center is updated again through the updated membership matrix, and the cluster center and the membership matrix are updated iteratively until the change of the membership matrix is ​​less than the preset threshold. Cluster labels are added to users according to the clustering results, and the final membership matrix and user cluster labels are output; Use ARIMA model to predict user electricity consumption based on user electricity consumption data The user characteristics and membership matrix are input into the SVM model to analyze the user behavior and predict the user's electricity consumption. , user behavior and user tags to establish a user behavior model.

4. The method for evaluating the benefits of electric energy substitution according to claim 3, characterized in that: The establishment of an electric energy alternative solution library based on the user behavior model refers to setting the types of alternative energy, obtaining the parameters of each alternative energy including power, energy efficiency ratio and operating cost, and extracting the predicted user power consumption from the user behavior model. , calculate the power generation at the predicted time t according to the power and energy efficiency ratio of each alternative energy , and calculate the operating cost at the forecast time t, and the power generation at the forecast time t And predict user electricity consumption For comparison, if the power generation Greater than or equal to power consumption , then the parameters of alternative energy types, power generation and operating costs are used to form an electric energy alternative plan. Less than power consumption , then exclude the alternative energy from the types of alternative energy, and integrate all electric energy alternatives to establish an electric energy alternative solution library.

5. The method for evaluating the benefits of electric energy substitution according to claim 4, characterized in that: The evaluating the benefits of the alternative solutions to generate an evaluation report refers to extracting user tags and user behaviors in the user behavior model as user input; Construct a convolutional neural network, define the input as user input and electric energy alternatives, and the output as the benefits of the electric energy alternatives. Use the training set to iteratively train the convolutional neural network, and set the cross entropy loss function and Adam optimizer to iteratively optimize the convolutional neural network parameters. The user input and each electricity alternative are input into the convolutional neural network to obtain the benefits of each electricity alternative for the user, and the benefits are sorted from high to low to generate an evaluation report.

6. The method for evaluating the benefits of electric energy substitution according to claim 5, characterized in that: The obtaining of the evaluation report for display refers to obtaining a benefit evaluation report of the electric energy alternatives and displaying it to the user using a visual chart, recommending the electric energy alternatives to the user based on the evaluation report, the user selecting the electric energy alternative based on the evaluation report, and recording the electric energy alternative selected by the user.

7. The method for evaluating the benefits of electric energy substitution according to claim 6, characterized in that: The storage in the database means that the evaluation report and the electric energy alternative selected by the user are stored in the local database, and each time the storage is performed, the data stored in the local database is checked for vulnerabilities and integrity, and the stored data is uploaded to the blockchain for backup at regular intervals.

8. An electric energy substitution benefit evaluation system according to any one of claims 1 to 7, characterized in that: include, The data acquisition module is used to deploy load monitoring equipment to collect user power consumption data for preprocessing and extract user characteristics; The behavior analysis module is used to perform cluster analysis on user characteristics to obtain user tags, and use machine learning algorithms to analyze user behaviors and establish user behavior models; The scheme evaluation module is used to establish an electric energy alternative scheme library based on the user behavior model, and to evaluate the benefits of the electric energy alternative schemes and generate an evaluation report to recommend to users; The display storage module is used to display and store backup of the assessment report.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the electric energy substitution benefit evaluation method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the benefits of electric energy substitution described in any one of claims 1 to 7 are implemented.

Images