Method and system for dynamically formulating energy-saving and efficiency-improving scheme for residential users

Abstract

The invention discloses a method and a system for dynamically formulating an energy-saving and efficiency-improving scheme for residential users. The method comprises the following steps of: obtaining a user energy consumption mode by adopting a clustering analysis method; respectively acquiring power consumption time sequence data of the related users in the same time period of the previous period in each energy consumption mode, and fitting a power consumption prediction model of the energy consumption mode by adopting an autoregressive differential mobile model; for users in each energy consumption mode, inputting the electricity consumption time sequence data into the electricity consumption prediction model for rolling prediction to obtain electricity consumption prediction data in a prediction duration; and respectively making an energy-saving scheme for each user based on the electricity consumption prediction data of each energy consumption mode in the future prediction duration. According to the method and the system, the energy-saving awareness of residents and the participation degree of the energy-saving behaviors are improved by analyzing the energy consumption behaviors of the users and accurately formulating the personalized energy-saving scheme and combining a scientific incentive mechanism and a dynamic evaluation system, the dynamic adjustment and real-time feedback of the energy-saving scheme are realized, and the continuity of the energy-saving effect is enhanced.

Description

Technical Field

[0001] The present invention relates to a power distribution technology, and in particular to a method and system for dynamically formulating energy-saving and efficiency-improving plans for residential users. Background Art

[0002] In the context of increasingly severe global energy consumption and environmental problems, the analysis and prediction of residents' energy consumption behavior is of great significance in modern energy management. Its scientificity and practicality are particularly important. The existing technology has some shortcomings:

[0003] First, many existing energy-saving solutions usually adopt universal strategies and fail to fully consider factors such as users' historical energy consumption data, real-time energy consumption, seasonal changes, and home appliance usage habits. This one-size-fits-all solution is difficult to effectively meet the actual needs of different users, resulting in unsatisfactory energy-saving effects, and users' acceptance and willingness to implement are also affected.

[0004] Secondly, in the existing technology, energy-saving plans are often static suggestions that cannot be dynamically adjusted according to the user's actual energy consumption. The lack of a real-time feedback system means that users cannot keep up with their energy-saving progress and cannot adjust their behavior based on feedback, resulting in limited effectiveness of energy-saving guidance and reduced user satisfaction.

[0005] In addition, the existing energy-saving effect evaluation system usually only considers a single or a few indicators, resulting in insufficient comprehensiveness and accuracy of the evaluation results, making it difficult to visualize the energy-saving effects and unable to provide strong data support for subsequent energy-saving recommendations and incentives, affecting the sustainability and long-term effects of energy-saving behaviors.

[0006] In summary, existing energy-saving technologies have obvious deficiencies in terms of incentive mechanisms for residential users, the accuracy of personalized solutions, dynamic adjustment and real-time feedback mechanisms, and comprehensive evaluation systems for energy-saving effects. These deficiencies result in limited effectiveness of energy-saving measures in practical applications, making it difficult to effectively stimulate users' enthusiasm for energy conservation, meet users' personalized needs, adjust and feedback energy-saving strategies in a timely manner, and comprehensively and accurately evaluate energy-saving results. Summary of the invention

[0007] In order to solve the problems in the prior art that energy-saving solutions are one-size-fits-all and cannot be dynamically adjusted, the present invention provides a method and system for dynamically formulating energy-saving and efficiency-improving solutions for residential users.

[0008] The technical solution provided by the present invention is:

[0009] Cluster analysis is used to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption patterns;

[0010] For each energy consumption mode, respectively obtain the time series data of power consumption of the relevant users in the same time period of the previous period under each energy consumption mode, and based on the time series data of power consumption in the same time period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration of the time period and the power consumption at the next moment of the characteristic duration of the time period, as the power consumption prediction model of the energy consumption mode;

[0011] For each user of each energy consumption mode, the power consumption time series data is input into the power consumption prediction model for rolling prediction to obtain power consumption prediction data within the prediction time period;

[0012] Formulate energy-saving plans for each user based on the predicted power consumption data for each energy consumption mode within the predicted future duration;

[0013] The characteristic duration includes the durations of multiple moments, and the characteristic duration is shorter than the duration of a period of time before the current moment.

[0014] Preferably, for each energy consumption mode, the power consumption time series data of the relevant users in the same time period of the previous period of time under each energy consumption mode are obtained respectively, and based on the power consumption time series data of the same time period, the corresponding relationship between the power consumption within the characteristic duration of the time period and the power consumption at the next moment of the characteristic duration of the time period is fitted using an autoregressive difference moving model as the power consumption prediction model of the energy consumption mode, including:

[0015] When the power consumption time series data shows a trend or seasonality, the power consumption time series data is processed by a differential operation to obtain stable time series power consumption data;

[0016] Determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data;

[0017] The power consumption prediction model is obtained by fitting the corresponding relationship between the power consumption within the characteristic time length and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order;

[0018] The characteristic duration is the number of moments of the autoregressive order.

[0019] Preferably, the step of determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data includes:

[0020] Determine the moving average order by drawing an autocorrelation diagram of the power consumption time series data;

[0021] Determine the autoregressive order by plotting partial autocorrelations;

[0022] The difference order is obtained by processing the non-stationary time series through the difference operation.

[0023] Preferably, after obtaining the power consumption prediction model by fitting the corresponding relationship between the power consumption within the characteristic duration and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order, the method further includes:

[0024] Check the residual of the electricity consumption prediction model. When the residual has autocorrelation or the residual is not white noise, adjust the autoregressive order, the difference order and the moving average order of the electricity consumption prediction model and calculate the residual of the adjusted electricity consumption prediction model until the residual has no autocorrelation and is white noise.

[0025] Preferably, after formulating energy-saving plans for each user based on the power consumption forecast data within the future forecast duration of each energy consumption mode, the method further includes:

[0026] Based on the pre-built evaluation system, the energy-saving scheme is evaluated by multiple indicators;

[0027] Generate a personalized feedback report for the energy-saving plan at the current moment based on the evaluation results.

[0028] Preferably, the multi-index comprehensive evaluation includes:

[0029] Constructing an evaluation matrix according to the score of each indicator of the energy-saving behavior data of each user and standardizing the evaluation matrix;

[0030] Calculating the contribution of each indicator in the user energy-saving behavior data to the evaluation according to the standardized evaluation matrix;

[0031] Calculate the weight of each indicator based on its contribution to the evaluation;

[0032] Based on the score and weight of the index value of each user's energy-saving behavior data, the energy-saving effect of the energy-saving scheme is quantitatively evaluated to obtain a comprehensive evaluation value of each user;

[0033] The indicators of the user energy-saving behavior data include at least one or more of the following: energy saving amount, behavior continuity or user satisfaction.

[0034] Preferably, the contribution of each indicator to the evaluation is calculated as follows:

[0035] d j =1-E j

[0036] Where, d j is the contribution of the jth indicator to the evaluation, E jis the entropy value of the jth indicator;

[0037] The entropy value E of the jth indicator j The calculation formula is as follows:

[0038]

[0039] In the formula, p ij is the entropy value of the i-th user at the j-th indicator;

[0040] The entropy value p of the i-th user at the j-th indicator ij The calculation formula is as follows:

[0041] z ij is an item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator, and n is the number of users.

[0042] Preferably, the weight of each indicator is calculated as follows:

[0043]

[0044] In the formula, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation, and m is the number of energy-saving behavior indicators.

[0045] Preferably, the comprehensive evaluation value is calculated as follows:

[0046]

[0047] In the formula, S i is the comprehensive evaluation value of the i-th user, m is the number of user energy-saving behavior indicators, and w j is the weight of the jth indicator, z ij is the item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator.

[0048] Based on the same inventive concept, the present invention also provides a system for dynamically formulating energy-saving and efficiency-improving plans for residential users, including: an energy consumption mode acquisition module, an electricity consumption prediction model establishment module, a rolling prediction module, and a plan formulation module;

[0049] The energy consumption pattern acquisition module is used to process the user's electricity consumption data for a period of time before the current moment using a cluster analysis method to obtain a number of energy consumption patterns;

[0050] The module for establishing a power consumption prediction model is used to obtain the power consumption time series data of the relevant users in the same period of the previous period under each energy consumption mode for each energy consumption mode, and based on the power consumption time series data of the same period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration of the period and the power consumption at the next moment of the characteristic duration of the period, as the power consumption prediction model of the energy consumption mode;

[0051] The rolling prediction module is used to input the power consumption time series data into the power consumption prediction model for rolling prediction for users of each energy consumption mode, and obtain the power consumption prediction data within the prediction time period;

[0052] The plan making module is used to make energy-saving plans for each user based on the power consumption forecast data within the future forecast period of each energy consumption mode;

[0053] The characteristic duration includes the durations of multiple moments, and the characteristic duration is shorter than the duration of a period of time before the current moment.

[0054] Preferably, the module for establishing a power consumption prediction model is specifically used for:

[0055] When the power consumption time series data shows a trend or seasonality, the power consumption time series data is processed by a differential operation to obtain stable time series power consumption data;

[0056] Determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data;

[0057] The power consumption prediction model is obtained by fitting the corresponding relationship between the power consumption within the characteristic time length and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order;

[0058] The characteristic duration is the number of moments of the autoregressive order.

[0059] Preferably, the power consumption prediction model establishment module determines the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data, including:

[0060] Determine the moving average order by drawing an autocorrelation diagram of the power consumption time series data;

[0061] Determine the autoregressive order by plotting partial autocorrelations;

[0062] The difference order is obtained by processing the non-stationary time series through the difference operation.

[0063] Preferably, the system also includes a checking model module, which is used to check the residual of the electricity consumption prediction model after obtaining the electricity consumption prediction model by fitting the correspondence between the electricity consumption within the characteristic time length and the electricity consumption after the next moment according to the autoregressive order, the differential order and the moving average order. When the residual has autocorrelation or the residual is not white noise, the autoregressive order, the differential order and the moving average order of the electricity consumption prediction model are adjusted and the residual of the adjusted electricity consumption prediction model is calculated until the residual has no autocorrelation and is white noise.

[0064] Preferably, the system also includes a multi-indicator evaluation module and a personalized feedback report generation module. The multi-indicator evaluation module and the personalized feedback report generation module are used to formulate energy-saving plans for each user based on the power consumption forecast data within the future predicted duration of each energy consumption mode, and then perform a multi-indicator evaluation on the energy-saving plan based on a pre-built evaluation system; and generate a personalized feedback report for the energy-saving plan at the current moment according to the evaluation results.

[0065] Preferably, the multi-index evaluation of the multi-index comprehensive evaluation module includes:

[0066] Constructing an evaluation matrix according to the score of each indicator of the energy-saving behavior data of each user and standardizing the evaluation matrix;

[0067] Calculating the contribution of each indicator in the user energy-saving behavior data to the evaluation according to the standardized evaluation matrix;

[0068] Calculate the weight of each indicator based on its contribution to the evaluation;

[0069] Based on the score and weight of the index value of each user's energy-saving behavior data, the energy-saving effect of the energy-saving scheme is quantitatively evaluated to obtain a comprehensive evaluation value of each user;

[0070] The indicators of the user energy-saving behavior data include at least one or more of the following: energy saving amount, behavior continuity or user satisfaction.

[0071] Preferably, the contribution of each indicator of the multi-indicator evaluation module to the evaluation is calculated as follows:

[0072] d j =1-E j

[0073] Where, d j is the contribution of the jth indicator to the evaluation, E j is the entropy value of the jth indicator;

[0074] The entropy value E of the jth indicator jThe calculation formula is as follows:

[0075]

[0076] In the formula, p ij is the entropy value of the i-th user at the j-th indicator;

[0077] The entropy value p of the i-th user at the j-th indicator ij The calculation formula is as follows:

[0078] z ij is an item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator, and n is the number of users.

[0079] Preferably, the weight of each indicator of the multi-indicator evaluation module is calculated as follows:

[0080]

[0081] In the formula, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation, and m is the number of energy-saving behavior indicators.

[0082] Preferably, the comprehensive evaluation value of the multi-index evaluation module is calculated as follows:

[0083]

[0084] In the formula, S i is the comprehensive evaluation value of the i-th user, m is the number of user energy-saving behavior indicators, and w j is the weight of the jth indicator, z ij is the item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator.

[0085] Based on the same inventive concept, the present invention also provides a computer device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0086] The memory is used to store one or more programs;

[0087] When the one or more programs are executed by the at least one processor, the above-mentioned method for dynamically formulating energy-saving and efficiency-improving plans for residential users is implemented.

[0088] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which an execution program is stored. When the execution program is executed, the above-mentioned method for dynamically formulating energy-saving and efficiency-improving plans for residential users is implemented.

[0089] Compared with the prior art, the present invention has the following beneficial effects:

[0090] The present invention provides a method for dynamically formulating energy-saving and efficiency-improving schemes for residential users, using cluster analysis to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption patterns; for each energy consumption pattern, respectively obtain the time series data of electricity consumption of the relevant users in the same period of the previous period under each energy consumption pattern, and based on the time series data of electricity consumption in the same period, use the autoregressive difference moving model to fit the corresponding relationship between the electricity consumption in the characteristic duration of the period and the electricity consumption at the next moment of the characteristic duration of the period, as the electricity consumption prediction model of the energy consumption pattern; for each user of each energy consumption pattern, input the electricity consumption time series data into the electricity consumption prediction model for rolling prediction, and obtain the electricity consumption prediction data within the prediction duration; based on the electricity consumption prediction data within the future prediction duration of each energy consumption pattern, respectively formulate energy-saving schemes for each user. The present invention distinguishes the typical energy consumption patterns of different users through the application of cluster analysis and prediction models of historical data, and can also predict the energy consumption trend of users in a specific time period, formulates a dynamically adjustable personalized energy-saving scheme for each user, ensures the continuous effectiveness of the energy-saving scheme, and improves residents' energy-saving awareness and participation in energy-saving behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 A flow chart of a method for dynamically formulating energy-saving and efficiency-enhancing plans for residential users according to the present invention;

[0092] Figure 2 A schematic diagram of a method for dynamically formulating energy-saving and efficiency-enhancing plans for residential users according to the present invention;

[0093] Figure 3 A schematic diagram of the effectiveness evaluation system of the method for dynamically formulating energy-saving and efficiency-improving plans for residential users according to the present invention;

[0094] Figure 4 A schematic diagram of a system for dynamically formulating energy-saving and efficiency-enhancing plans for residential users according to the present invention;

[0095] Figure 5 A schematic diagram of a computer device dynamically formulating an energy-saving and efficiency-enhancing solution for residential users according to the present invention. DETAILED DESCRIPTION

[0096] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings.

[0097] Example 1

[0098] The present invention provides a method for dynamically formulating energy-saving and efficiency-enhancing plans for residential users, the flow chart of which is as follows: Figure 1 As shown, including:

[0099] S1. Use cluster analysis to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption patterns.

[0100] S2. For each energy consumption mode, respectively obtain the time series data of electricity consumption of the relevant users in the same time period of the previous period under each energy consumption mode, and based on the time series data of electricity consumption in the same time period, use the autoregressive difference moving model to fit the corresponding relationship between the electricity consumption within the characteristic duration of the time period and the electricity consumption at the next moment of the characteristic duration of the time period as the electricity consumption prediction model for the energy consumption mode.

[0101] S3. For each user of each energy consumption mode, the power consumption time series data is input into the power consumption prediction model for rolling prediction to obtain power consumption prediction data within the prediction period.

[0102] S4. Formulate energy-saving plans for each user based on the predicted power consumption data within the future predicted time period of each energy consumption mode.

[0103] Step S1 uses cluster analysis to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption patterns, including:

[0104] Smart metering devices are used to collect users' historical energy consumption data, and cluster analysis and time series analysis methods are used to identify users' energy consumption patterns.

[0105] Cluster analysis is a commonly used unsupervised learning algorithm, which is particularly suitable for fast and efficient cluster analysis of large-scale data sets. It is favored because of its simplicity, high computational efficiency, applicability to a variety of data types, and good interpretability of results. The algorithm can process multidimensional data and performs well in practical applications, especially in the fields of market segmentation, user behavior analysis, and image processing. At the same time, cluster analysis has good scalability, and many variants such as K-means++ and small batch gradient descent can further improve its performance. Although there are limitations such as sensitivity to initial conditions and the possibility of falling into local optimal solutions, these problems can be effectively solved through algorithm improvement and data preprocessing, making cluster analysis still have wide application value in large-scale data analysis. In the analysis of residential electricity consumption behavior, cluster analysis is widely used to identify the electricity consumption patterns of different users, thereby realizing personalized energy management and energy-saving strategy formulation. The process of cluster analysis mainly includes the following steps: first, randomly select K data points as the initial cluster centroids; then, assign each data point to the nearest cluster based on its distance from the centroid of each cluster; then, recalculate the centroid of each cluster, that is, take the average value of all data points in the cluster as the new centroid; repeat the above assignment and update steps until a certain termination condition is met (such as the cluster centroid no longer changes significantly or reaches a preset number of iterations).

[0106] The principle of cluster analysis in the present invention is as follows:

[0107] First, collect residential electricity consumption data and perform feature selection. These data usually include daily, weekly or monthly electricity consumption, electricity consumption time distribution, seasonal changes, and electrical equipment usage. For these data, select key features as inputs for cluster analysis, such as: Total electricity consumption: total electricity consumption per day, week or month. Time distribution of electricity consumption: such as the proportion of electricity consumption during peak hours in the morning and evening. Seasonal changes: changes in electricity consumption in different seasons. Appliance usage pattern: electricity consumption of specific appliances (such as air conditioners, lighting equipment). These features will form a multidimensional vector and be input into the cluster analysis method for cluster analysis.

[0108] After the data features are prepared, the specific steps are as follows:

[0109] Initialize cluster centers: Select K initial cluster centers, which can be determined by random selection. The cluster centers may represent different power consumption patterns at the beginning, such as peak power consumption, low load power consumption, etc.

[0110] Assign data points: Assign each resident’s electricity consumption behavior data to the cluster center closest to it. For each resident’s electricity consumption feature vector x i, calculate its Euclidean distance to all cluster centers, and assign it to the cluster with the closest distance. In this way, each resident is classified into a specific electricity consumption pattern group.

[0111]

[0112] Where x is the data point, c i is the i-th cluster center, d is the dimension of the data, x j and c ij are x and c respectively i The value in the jth dimension.

[0113] Update cluster center: Recalculate the center of each cluster based on the average value of the residential electricity consumption data in each cluster. This new cluster center reflects the typical electricity consumption pattern of this type of user.

[0114]

[0115] Where x is the data point, S i is the set of data points of the ith cluster, |S i | is the number of data points in the set.

[0116] Repeated iteration: Repeat the allocation of data points and the update of cluster centers until the cluster centers no longer change significantly or the preset maximum number of iterations is reached. The final cluster centers will represent different residential electricity consumption patterns, and the residents in each cluster will show similar electricity consumption behaviors.

[0117] Clustering results and behavior analysis: Through cluster analysis, residents can be divided into several different electricity consumption behavior categories, such as: Peak electricity consumption type: The electricity consumption of these residents is concentrated in the peak hours in the morning and evening, and they may use a large number of household appliances. Balanced electricity consumption type: The electricity consumption of these residents is relatively balanced throughout the day, without obvious peaks or troughs. Low-load electricity consumption type: The overall electricity consumption of these residents is low, and they may mainly use basic living appliances. Seasonal electricity consumption type: The electricity consumption of these residents has obvious seasonal changes, such as significantly higher electricity consumption in summer or winter than in other seasons.

[0118] Step S2 obtains the time series data of power consumption of the relevant users in the same time period of the previous period for each energy consumption mode, and based on the time series data of power consumption in the same time period, uses the autoregressive difference moving model to fit the corresponding relationship between the power consumption in the characteristic duration of the time period and the power consumption at the next moment of the characteristic duration of the time period as the power consumption prediction model of the energy consumption mode, which specifically includes:

[0119] After cluster analysis of residents, an autoregressive difference moving average model was established, and the principle is as follows:

[0120] Data preparation: After clustering the residents, several different user groups are obtained. For each group, representative time series data of the group needs to be extracted. Usually, this data is based on time (such as daily, weekly) electricity consumption records.

[0121] Determine time series data: Extract time series data from each cluster group, which usually includes the date and the corresponding electricity consumption.

[0122] Stationarity check: The time series must be stationary, that is, the mean and variance are constant. If the time series shows trend or seasonality, it needs to be converted to a stationary series through differencing or other methods.

[0123] Model identification: Before using the autoregressive difference moving average model, three key parameters of the model need to be determined: the autoregressive order p, the difference order d, and the moving average order q. This is usually done by the following steps:

[0124] Autocorrelation function and partial autocorrelation function analysis: By drawing the autocorrelation graph and partial autocorrelation graph of the time series, the values ​​of p and q can be preliminarily determined. The autocorrelation graph is used to determine the q value, and the partial autocorrelation graph is used to determine the p value. Difference operation: The non-stationary series is processed by difference operation, usually by first-order difference or second-order difference to eliminate the trend component, so as to obtain a stationary series, and then determine the difference order d.

[0125] Model parameter estimation: After determining the p, d, and q parameters, these parameters can be used to fit the autoregressive difference moving average model. This step includes:

[0126] Fitting the model:

[0127] Using the determined p, d, and q parameters, the power consumption prediction model is obtained by fitting the sequence data of a period of time before the current moment (for example, the daily peak power consumption period 18:00-22:00 or the trough period 0:00-6:00) to fit the corresponding relationship between the power consumption within the characteristic time period and the power consumption at the next moment of the characteristic time period.

[0128] At the same time, the characteristic duration includes the duration of the autoregressive order moments, and the characteristic duration is smaller than the duration of a period before the current moment.

[0129] Estimate the coefficients of the model: Estimate the parameters of the autoregressive difference moving average model through methods such as maximum likelihood estimation. These coefficients will be used to predict future time series values.

[0130] After fitting the model, the model needs to be diagnosed to ensure its accuracy and effectiveness. The diagnostic steps include:

[0131] Residual analysis: Check the model residuals (the difference between the actual value and the predicted value). Ideally, the residuals should appear to be white, that is, random errors with zero mean and no autocorrelation. If the residuals have autocorrelation, the model parameters may need to be adjusted.

[0132] White noise test: Further test whether the residual is white noise. This test can help determine whether the model is suitable for the data.

[0133] Step S3, for each user of each energy consumption mode, inputting the power consumption time series data into the power consumption prediction model for rolling prediction, and obtaining power consumption prediction data within the prediction time, specifically including:

[0134] After the model passes the diagnosis, the autoregressive difference moving average model can be used to predict future electricity consumption. The prediction steps include:

[0135] Generate future forecasts: Based on the fitted autoregressive difference moving average model, predict the electricity consumption for a period of time in the future. The forecast time span can be days, weeks or months, depending on the frequency of the time series and the forecast requirements.

[0136] Prediction interval estimation: While providing the prediction value, the autoregressive difference moving average model usually also provides a prediction interval, which indicates the uncertainty range of the prediction value. This is very important for evaluating the reliability of the prediction. Interpretation and application of prediction results: For each cluster group, the autoregressive difference moving average model is used to predict the power consumption trend in the future. These prediction results can help power companies or energy management systems understand the changes in power demand of different user groups in advance, so as to carry out reasonable power dispatch and resource allocation. For example: For peak power users, the prediction results can be used to adjust the electricity price strategy to encourage users to avoid peak power consumption; for seasonal power users, seasonal energy-saving measures can be promoted in advance according to the predicted seasonal power consumption changes, such as strengthening insulation and using energy-saving equipment; for low-load power users, although their power consumption is low, the prediction results can still be used to identify potential power consumption anomalies to help users further optimize their power consumption behavior.

[0137] Step S4, based on the power consumption forecast data of each energy consumption mode within the future forecast period, an energy saving plan is formulated for each user, specifically including:

[0138] Based on the accurate analysis of the user's energy consumption behavior, the present invention tailors a personalized energy-saving plan for each user. The plan not only takes into account the user's historical energy consumption data, but also combines factors such as real-time energy consumption, seasonal changes, and household appliance usage habits. The formulation of personalized energy-saving plans mainly includes two aspects: energy-saving target setting and energy-saving measure recommendation. The point and reward mechanism design includes the point and reward mechanism. The overall process is as follows: Figure 2 .

[0139] After the plan is formulated, the energy-saving behavior data of users after the implementation of the plan is evaluated, including:

[0140] like Figure 3 As shown in the figure, the feedback and cycle process of energy-saving solutions based on the multi-dimensional data analysis model is described. First, the system obtains the user's energy consumption data and inputs it into the multi-dimensional data analysis model for analysis. The analysis process includes multiple dimensions such as entropy weight allocation, energy evaluation, economic benefit calculation, behavior continuity analysis and user satisfaction evaluation. Through these evaluations, the system conducts quantitative evaluation and generates personalized feedback reports. Based on the feedback report, the system dynamically adjusts the energy-saving plan and feeds back the adjusted plan to the user. Users continue to optimize their energy-saving behavior based on the feedback, forming a continuous feedback and improvement cycle, thereby continuously improving the overall energy-saving effect, including:

[0141] In order to conduct a multi-index comprehensive evaluation of the energy-saving behavior of users, the entropy weight method is combined to allocate weights to ensure the objectivity and accuracy of the evaluation. The entropy weight method is an objective weighting method, which is mainly used to determine the weights of each indicator in the multi-index comprehensive evaluation. Its principle is based on the concept of information entropy. The larger the information entropy, the higher the information uncertainty of the indicator, which means that its contribution to the comprehensive evaluation is lower and the weight is smaller; conversely, the smaller the information entropy, the greater the weight. The entropy weight method uses information entropy to measure the differences of each indicator. Information entropy is a concept in information theory that is used to quantify the degree of chaos in the system. In the multi-index evaluation, the smaller the information entropy of a certain indicator, the greater the variability of the indicator among all evaluation objects, and the greater the weight and influence.

[0142] The principle of entropy weight method is as follows: Assume that n' samples, m' indicators, x i’j’ is the value of the j'th indicator of the i'th sample, forming the original data matrix X' as follows:

[0143]

[0144] Standardize the original data to eliminate the impact of dimension. The commonly used standardization method is range transformation, which converts the data to the [0,1] interval:

[0145]

[0146] Among them, z i’j’ is the item of the standardized matrix, and then the entropy value E of each indicator is calculated based on the standardized data j ':

[0147]

[0148] The entropy value p of the i'th user at the j'th indicator ij The calculation formula of ′ is as follows:

[0149]

[0150] Where n' is the number of samples. Generally speaking, 0≤E j '≤1.

[0151] Information utility value d j ', is the supplementary amount of entropy value, reflecting the contribution of the indicator to the evaluation:

[0152] d j’ =1-E j’

[0153] The final weight w j ' is the normalized result of the indicator information utility value:

[0154]

[0155] Finally, according to the calculated weight w j ', perform weighted summation on the indicators of each evaluation object to obtain a comprehensive evaluation value:

[0156]

[0157] In this method, first, the energy-saving behavior data of users is collected, involving multiple dimensions, such as energy saving, behavior continuity, user satisfaction, etc. Assuming there are n users, each user has m evaluation indicators, and the evaluation matrix X is constructed:

[0158]

[0159] Among them, x ij represents the score of the i-th user on the j-th indicator, i = 1, 2, ..., n, j = 1, 2, ..., m.

[0160] To ensure the comparability between different energy-saving indicators, the data of indicators such as energy saving, behavior continuity, and user satisfaction are standardized so that they are all on the same scale, thereby fairly comparing the energy-saving behaviors of different users.

[0161]

[0162] Among them, z ij is the entry of the normalized matrix.

[0163] Calculate the entropy value p of each energy-saving behavior indicator ij , determine its information uncertainty E jThrough this process, the impact of each indicator on the overall energy saving effect can be quantified, and a basis can be provided for subsequent weight allocation.

[0164]

[0165] The weights of various energy-saving indicators are calculated based on the entropy value to identify which indicators (such as energy saving or behavior continuity) have the greatest impact on the user's overall energy-saving behavior. This step ensures the objectivity of the evaluation and highlights the most important energy-saving factors.

[0166] d j =1-E j

[0167]

[0168] Among them, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation.

[0169] The energy-saving behaviors of users are weighted and summed to comprehensively evaluate the overall energy-saving effect of each user. This score reflects the comprehensive performance of users in terms of energy saving, behavior continuity, and satisfaction.

[0170]

[0171] In deriving the comprehensive score S i After analyzing the specific performance of each dimension, a personalized energy-saving effect feedback report is generated. Based on the feedback report, the system dynamically adjusts the energy-saving plan and feeds back the adjusted plan to the user. The user continues to optimize his energy-saving behavior based on the feedback, forming a continuous feedback and improvement cycle, thereby continuously improving the overall energy-saving effect. According to the user's performance in dimensions such as energy saving, behavior continuity, and user satisfaction shown in the feedback report, the contribution of key dimensions to the comprehensive score is analyzed in combination with weights, and specific improvement suggestions are provided for dimensions with lower scores. For example, if the behavior continuity score is low, the user can be advised to improve the continuity of energy-saving behavior by using smart devices or making plans.

[0172] Comprehensively evaluate users' energy-saving behaviors and analyze the effectiveness of multiple aspects such as energy saving, economic benefits, and behavior sustainability. This evaluation system not only ensures the visualization of energy-saving effects, but also provides data support for subsequent energy-saving recommendations and incentives, thereby ensuring the sustainability and long-term nature of energy-saving effects.

[0173] Example 2

[0174] Based on the same inventive concept, the present invention also provides a system for dynamically formulating energy-saving and efficiency-enhancing plans for residential users, such as Figure 4As shown, it includes: an energy consumption mode acquisition module, an electricity consumption prediction model establishment module, a rolling prediction module and a plan formulation module;

[0175] The energy consumption pattern acquisition module is used to process the user's electricity consumption data for a period of time before the current moment using a cluster analysis method to obtain a number of energy consumption patterns;

[0176] The module for establishing a power consumption prediction model is used to obtain the power consumption time series data of the relevant users in the same period of the previous period under each energy consumption mode for each energy consumption mode, and based on the power consumption time series data of the same period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration of the period and the power consumption at the next moment of the characteristic duration of the period, as the power consumption prediction model of the energy consumption mode;

[0177] The rolling prediction module is used to input the power consumption time series data into the power consumption prediction model for rolling prediction for users of each energy consumption mode, and obtain the power consumption prediction data within the prediction time period;

[0178] The plan making module is used to make energy-saving plans for each user based on the power consumption forecast data within the future forecast period of each energy consumption mode;

[0179] The characteristic duration includes the durations of multiple moments, and the characteristic duration is shorter than the duration of a period of time before the current moment.

[0180] Preferably, the module for establishing a power consumption prediction model is specifically used for:

[0181] When the power consumption time series data shows a trend or seasonality, the power consumption time series data is processed by a differential operation to obtain stable time series power consumption data;

[0182] Determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data;

[0183] The power consumption prediction model is obtained by fitting the corresponding relationship between the power consumption within the characteristic time length and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order;

[0184] The characteristic duration is the number of moments of the autoregressive order.

[0185] Preferably, the power consumption prediction model establishment module determines the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data, including:

[0186] Determine the moving average order by drawing an autocorrelation diagram of the power consumption time series data;

[0187] Determine the autoregressive order by plotting partial autocorrelations;

[0188] The difference order is obtained by processing the non-stationary time series through the difference operation.

[0189] Preferably, the system also includes a checking model module, which is used to check the residual of the electricity consumption prediction model after obtaining the electricity consumption prediction model by fitting the correspondence between the electricity consumption within the characteristic time length and the electricity consumption after the next moment according to the autoregressive order, the differential order and the moving average order. When the residual has autocorrelation or the residual is not white noise, the autoregressive order, the differential order and the moving average order of the electricity consumption prediction model are adjusted and the residual of the adjusted electricity consumption prediction model is calculated until the residual has no autocorrelation and is white noise.

[0190] Preferably, the system also includes a multi-indicator evaluation module and a personalized feedback report generation module. The multi-indicator evaluation module and the personalized feedback report generation module are used to formulate energy-saving plans for each user based on the power consumption forecast data within the future predicted duration of each energy consumption mode, and then perform a multi-indicator evaluation on the energy-saving plan based on a pre-built evaluation system; and generate a personalized feedback report for the energy-saving plan at the current moment according to the evaluation results.

[0191] Preferably, the multi-index evaluation of the multi-index comprehensive evaluation module includes:

[0192] Constructing an evaluation matrix according to the score of each indicator of the energy-saving behavior data of each user and standardizing the evaluation matrix;

[0193] Calculating the contribution of each indicator in the user energy-saving behavior data to the evaluation according to the standardized evaluation matrix;

[0194] Calculate the weight of each indicator based on its contribution to the evaluation;

[0195] Based on the score and weight of the index value of each user's energy-saving behavior data, the energy-saving effect of the energy-saving scheme is quantitatively evaluated to obtain a comprehensive evaluation value of each user;

[0196] The indicators of the user energy-saving behavior data include at least one or more of the following: energy saving amount, behavior continuity or user satisfaction.

[0197] Preferably, the contribution of each indicator of the multi-indicator evaluation module to the evaluation is calculated as follows:

[0198] d j=1-E j

[0199] Where, d j is the contribution of the jth indicator to the evaluation, E j is the entropy value of the jth indicator;

[0200] The entropy value E of the jth indicator j The calculation formula is as follows:

[0201]

[0202] In the formula, p ij is the entropy value of the i-th user at the j-th indicator;

[0203] The entropy value p of the i-th user at the j-th indicator ij The calculation formula is as follows:

[0204] z ij is an item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator, and n is the number of users.

[0205] Preferably, the weight of each indicator of the multi-indicator evaluation module is calculated as follows:

[0206]

[0207] In the formula, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation, and m is the number of energy-saving behavior indicators.

[0208] Preferably, the comprehensive evaluation value of the multi-index evaluation module is calculated as follows:

[0209]

[0210] In the formula, S i is the comprehensive evaluation value of the i-th user, m is the number of user energy-saving behavior indicators, and w j is the weight of the jth indicator, z ij is the item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator.

[0211] Example 3

[0212] like Figure 5As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0213] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement corresponding method flows or corresponding functions, so as to implement the steps of a method for dynamically formulating energy-saving and efficiency-improving plans for residential users in the above-mentioned embodiment.

[0214] Example 4

[0215] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space that stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a method for dynamically formulating an energy-saving and efficiency-enhancing scheme in the above embodiment.

[0216] Example 5

[0217] In a typical urban residential community, the method of the present invention collects the electricity consumption data of each household in real time through intelligent metering equipment, analyzes the user's electricity consumption pattern, seasonal changes and peak and trough periods, and formulates a personalized energy-saving plan for each household. The system recommends that users use high-energy-consuming equipment during non-peak hours, adopt physical cooling measures to reduce the frequency of air-conditioning use, and dynamically monitor electricity consumption during implementation, and adjust energy-saving suggestions in real time. Users can view energy-saving results and points through mobile applications, and points can be exchanged for physical rewards. After the energy-saving cycle is over, the system conducts a comprehensive evaluation of the energy-saving effect based on dimensions such as energy saving and economic benefits, generates a personalized feedback report, and further optimizes energy-saving measures. Through the method of the present invention, residents can not only reduce electricity bills, but also get benefits through point rewards, which significantly improves energy-saving awareness and enthusiasm. At the same time, the overall energy consumption of the community is greatly reduced, which helps to achieve the city's energy-saving and emission reduction goals and has high social and economic benefits.

[0218] In summary, the present invention provides a method for dynamically formulating energy-saving and efficiency-improving plans for residential users, including: using a cluster analysis method to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption modes; for each energy consumption mode, respectively obtain the time series data of electricity consumption of the relevant users in each energy consumption mode in the same period of the previous period, and based on the time series data of electricity consumption in the same period, use the autoregressive difference moving model to fit the corresponding relationship between the electricity consumption in the characteristic duration of the period and the electricity consumption at the next moment of the characteristic duration of the period, as the electricity consumption prediction model of the energy consumption mode; for users of each energy consumption mode, input the electricity consumption time series data into the electricity consumption prediction model for rolling prediction to obtain the electricity consumption prediction data within the prediction duration; based on the electricity consumption prediction data within the future prediction duration of each energy consumption mode, formulate energy-saving plans for each user. The present invention improves residents' energy-saving awareness and participation in energy-saving behavior through the analysis of user energy consumption behavior and the precise formulation of personalized energy-saving plans, combined with scientific incentive mechanisms and dynamic evaluation systems, realizes dynamic adjustment and real-time feedback of energy-saving plans, and enhances the sustainability of energy-saving effects.

[0219] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0220] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0221] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0222] Finally, 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for dynamically formulating energy-saving and efficiency-improving plans for residential users, characterized in that: include: Cluster analysis is used to process the user's electricity consumption data for a period of time before the current moment to obtain several energy consumption patterns; For each energy consumption mode, respectively obtain the time series data of power consumption of the relevant users in the same time period of the previous period under each energy consumption mode, and based on the time series data of power consumption in the same time period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration in the same time period and the power consumption at the next moment of the characteristic duration in the same time period, as the power consumption prediction model of the energy consumption mode; For each user of each energy consumption mode, the power consumption time series data is input into the power consumption prediction model for rolling prediction to obtain power consumption prediction data within the prediction time period; Formulate energy-saving plans for each user based on the predicted power consumption data for each energy consumption mode within the predicted future duration; The characteristic duration includes the durations of multiple moments, and the characteristic duration is shorter than the duration of a period of time before the current moment.

2. The method according to claim 1, characterized in that For each energy consumption mode, respectively obtain the time series data of power consumption of the relevant users in the same time period of the previous period under each energy consumption mode, and based on the time series data of power consumption in the same time period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration of the time period and the power consumption at the next moment of the characteristic duration of the time period as the power consumption prediction model of the energy consumption mode, including: When the power consumption time series data shows a trend or seasonality, the power consumption time series data is processed by a differential operation to obtain stable time series power consumption data; Determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data; The power consumption prediction model is obtained by fitting the corresponding relationship between the power consumption within the characteristic time length and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order; The characteristic duration is the number of moments of the autoregressive order.

3. The method according to claim 2, characterized in that The step of determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data includes: Determine the moving average order by drawing an autocorrelation diagram of the power consumption time series data; Determine the autoregressive order by plotting partial autocorrelations; The difference order is obtained by processing the non-stationary time series through the difference operation.

4. The method according to claim 3, characterized in that After obtaining the power consumption prediction model by fitting the corresponding relationship between the power consumption within the characteristic duration and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order, the method further includes: Check the residual of the electricity consumption prediction model. When the residual has autocorrelation or the residual is not white noise, adjust the autoregressive order, the difference order and the moving average order of the electricity consumption prediction model and calculate the residual of the adjusted electricity consumption prediction model until the residual has no autocorrelation and is white noise.

5. The method according to claim 1, characterized in that After formulating energy-saving plans for each user based on the power consumption forecast data within the future forecast period of each energy consumption mode, it also includes: Based on the pre-built evaluation system, the energy-saving scheme is evaluated by multiple indicators; Generate a personalized feedback report for the energy-saving scheme at the current moment according to the evaluation results.

6. The method according to claim 5, characterized in that The multi-index comprehensive evaluation includes: Constructing an evaluation matrix according to the score of each indicator of the energy-saving behavior data of each user and standardizing the evaluation matrix; Calculating the contribution of each indicator in the user energy-saving behavior data to the evaluation according to the standardized evaluation matrix; Calculate the weight of each indicator based on its contribution to the evaluation; Based on the score and weight of the index value of each user's energy-saving behavior data, the energy-saving effect of the energy-saving scheme is quantitatively evaluated to obtain a comprehensive evaluation value of each user; The indicators of the user energy-saving behavior data include at least one or more of the following: energy saving amount, behavior continuity or user satisfaction.

7. The method according to claim 6, characterized in that The contribution of each indicator to the evaluation is calculated as follows: d j =1-E j Where, d j is the contribution of the jth indicator to the evaluation, E j is the entropy value of the jth indicator; The entropy value E of the jth indicator j The calculation formula is as follows: In the formula, p ij is the entropy value of the i-th user at the j-th indicator; The entropy value p of the i-th user at the j-th indicator ij The calculation formula is as follows: z ij is an item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator, and n is the number of users.

8. The method according to claim 6, characterized in that The weight of each indicator is calculated as follows: In the formula, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation, and m is the number of energy-saving behavior indicators.

9. The method according to claim 6, characterized in that The comprehensive evaluation value is calculated as follows: In the formula, S i is the comprehensive evaluation value of the i-th user, m is the number of user energy-saving behavior indicators, and w j is the weight of the jth indicator, z ij is the item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator.

10. A system for dynamically formulating energy-saving and efficiency-improvement plans for residential users, characterized in that: include: Obtain energy consumption pattern module, establish power consumption forecast model module, rolling forecast module and plan formulation module; The energy consumption pattern acquisition module is used to process the user's electricity consumption data for a period of time before the current moment using a cluster analysis method to obtain a number of energy consumption patterns; The module for establishing a power consumption prediction model is used to obtain the power consumption time series data of the relevant users in the same period of the previous period under each energy consumption mode, and based on the power consumption time series data of the same period, use the autoregressive difference moving model to fit the corresponding relationship between the power consumption within the characteristic duration of the same period and the power consumption at the next moment of the characteristic duration of the same period, as the power consumption prediction model of the energy consumption mode; The rolling prediction module is used to input the power consumption time series data into the power consumption prediction model for rolling prediction for users of each energy consumption mode, and obtain the power consumption prediction data within the prediction time period; The plan making module is used to make energy-saving plans for each user based on the power consumption forecast data within the future forecast period of each energy consumption mode; The characteristic duration includes the durations of multiple moments, and the characteristic duration is shorter than the duration of a period of time before the current moment.

11. The system according to claim 10, characterized in that The module for establishing a power consumption prediction model is specifically used for: When the power consumption time series data shows a trend or seasonality, the power consumption time series data is processed by a differential operation to obtain stable time series power consumption data; Determining the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data; The power consumption prediction model is obtained by fitting the corresponding relationship between the power consumption within the characteristic time length and the power consumption after the next moment according to the autoregressive order, the differential order and the moving average order; The characteristic duration is the number of moments of the autoregressive order.

12. The system according to claim 11, characterized in that The power consumption prediction model establishment module determines the autoregressive order, differential order and moving average order of the power consumption prediction model of each energy consumption mode according to the stable power consumption time series data, including: Determine the moving average order by drawing an autocorrelation diagram of the power consumption time series data; Determine the autoregressive order by plotting partial autocorrelations; The difference order is obtained by processing the non-stationary time series through the difference operation.

13. The system according to claim 11, characterized in that The system also includes a checking model module, which is used to check the residual of the electricity consumption prediction model after obtaining the electricity consumption prediction model by fitting the correspondence between the electricity consumption within the characteristic time length and the electricity consumption after the next moment according to the autoregressive order, the differential order and the moving average order. When the residual has autocorrelation or the residual is not white noise, the autoregressive order, the differential order and the moving average order of the electricity consumption prediction model are adjusted and the residual of the adjusted electricity consumption prediction model is calculated until the residual has no autocorrelation and is white noise.

14. The system according to claim 10, characterized in that The system also includes a multi-index evaluation module and a personalized feedback report generation module, which are used to perform a multi-index evaluation on the energy-saving plan based on a pre-built evaluation system after formulating an energy-saving plan for each user based on the power consumption forecast data within the future forecast period of each energy consumption mode; Generate a personalized feedback report for the energy-saving plan at the current moment based on the evaluation results.

15. The system of claim 14, wherein: The multi-index evaluation of the multi-index comprehensive evaluation module includes: Constructing an evaluation matrix according to the score of each indicator of the energy-saving behavior data of each user and standardizing the evaluation matrix; Calculating the contribution of each indicator in the user energy-saving behavior data to the evaluation according to the standardized evaluation matrix; Calculate the weight of each indicator based on its contribution to the evaluation; Based on the score and weight of the index value of each user's energy-saving behavior data, the energy-saving effect of the energy-saving scheme is quantitatively evaluated to obtain a comprehensive evaluation value of each user; The indicators of the user energy-saving behavior data include at least one or more of the following: energy saving amount, behavior continuity or user satisfaction.

16. The system of claim 15, wherein: The contribution of each indicator of the multi-indicator evaluation module to the evaluation is calculated as follows: d j =1-E j Where, d j is the contribution of the jth indicator to the evaluation, E j is the entropy value of the jth indicator; The entropy value E of the jth indicator j The calculation formula is as follows: In the formula, p ij is the entropy value of the i-th user at the j-th indicator; The entropy value p of the i-th user at the j-th indicator ij The calculation formula is as follows: z ij is an item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator, and n is the number of users.

17. The system of claim 15, wherein: The weight of each indicator in the multi-indicator evaluation module is calculated as follows: In the formula, w j is the weight of the jth indicator, d j is the contribution of the jth indicator to the evaluation, and m is the number of energy-saving behavior indicators.

18. The system of claim 15, wherein: The comprehensive evaluation value of the multi-index evaluation module is calculated as follows: In the formula, S i is the comprehensive evaluation value of the i-th user, m is the number of user energy-saving behavior indicators, and w j is the weight of the jth indicator, z ij is the item in the standardized evaluation matrix, which represents the normalized value of the score of the i-th user on the j-th indicator.

19. A computer device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the method for dynamically formulating energy-saving and efficiency-improving plans for residential users as described in any one of claims 1 to 9 is implemented.

20. A computer-readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, a method for dynamically formulating energy-saving and efficiency-improving plans for residential users as described in any one of claims 1 to 9 is implemented.

Images