Electric charge reminding method, device and equipment based on power demand prediction

Abstract

The invention is suitable for the technical field of electric power systems, and provides an electric charge reminding method, device and equipment based on electric power demand prediction, and the method comprises the steps: carrying out the electricity consumption prediction according to the historical electric power consumption data set of all electricity users in a transformer area, and obtaining the electricity consumption prediction information of the corresponding electricity users in a current period, establishing an electric power settlement model based on the electric power settlement rule, determining the initial electric power cost required to be settled in the current electricity utilization period of each electricity user based on the electric power settlement model, and correcting the initial electric power cost according to the historical electric power cost data set of each electricity user to obtain the final electric power cost; and based on the final electric power cost and the residual electric power cost in the corresponding electricity user account, determining reminding information to remind the electricity user. According to the invention, the initial electric power cost is obtained by predicting the electricity consumption information of the electricity user, the final electric power cost is obtained through correction, the electricity user is reminded, the accuracy of the final electric power cost is ensured, and the electricity consumption experience of the electricity user is improved.

Description

Technical Field

[0001] This invention belongs to the field of power system technology, and in particular relates to a method, device and equipment for electricity bill reminders based on electricity demand forecasting. Background Technology

[0002] With rapid economic and technological development, residents' living standards are constantly improving, and the impact of global warming on their lives is becoming increasingly apparent. Affected by these factors, residents' electricity consumption is increasing year by year, and correspondingly, electricity bill reminder methods are constantly being adjusted.

[0003] Currently, electricity demand forecasting methods include historical data analysis. This method involves statistically analyzing electricity consumption data from previous years to identify patterns in electricity consumption over time, such as seasonal fluctuations and differences between weekdays and weekends, in order to predict future electricity demand. For example, during the hot summer months, increased air conditioning use typically leads to a significant increase in electricity consumption, while the use of heating equipment in winter creates another peak in electricity demand. However, existing electricity demand forecasting methods still have some shortcomings in terms of accuracy.

[0004] While historical data can provide some trend guidance, it cannot fully account for the impact of specific weather changes. For example, during extreme weather events, historical data may not accurately reflect actual changes in electricity demand, leading to significant forecast inaccuracies. Because of these biases in electricity demand forecasts, the estimated duration of electricity usage cannot be accurately predicted. Summary of the Invention

[0005] This invention provides a method and apparatus for electricity bill reminders based on electricity demand forecasting, in order to solve the problem that the estimated usage time of electricity costs cannot be accurately estimated due to deviations in electricity demand forecasting results.

[0006] This invention is achieved through the following technical solution: In a first aspect, embodiments of the present invention provide a method for electricity bill reminders based on electricity demand forecasting, comprising: Obtain historical power consumption datasets for all electricity users within the distribution area. Based on the historical power consumption datasets and weather forecast data for the current electricity consumption cycle, perform power consumption forecasts to obtain the power consumption forecast information for the relevant electricity users in the current cycle. An electricity settlement model is established based on the electricity settlement rules, and based on the electricity settlement model, the initial electricity cost to be settled for each electricity user in the current electricity consumption cycle is determined. Obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle. Then, based on the electricity cost set, correct the initial electricity cost for the corresponding electricity user to obtain the final electricity cost. Based on the final electricity cost and the remaining electricity cost in the relevant user's account, a reminder will be sent to the relevant user.

[0007] Secondly, embodiments of the present invention provide an electricity bill reminder device based on electricity demand forecasting, comprising: The prediction module is used to obtain the historical power consumption dataset of all electricity users in the transformer area. Based on the historical power consumption dataset and the weather forecast data of the current electricity consumption cycle, it performs power consumption prediction to obtain the power consumption prediction information of the relevant electricity users in the current cycle. The settlement module is used to establish an electricity settlement model based on electricity settlement rules, and based on the electricity settlement model, determine the initial electricity cost that each electricity user needs to settle in the current electricity consumption cycle; The correction module is used to obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle, and correct the initial electricity cost of the corresponding electricity user based on the electricity cost set to obtain the final electricity cost. The reminder module is used to remind relevant electricity users based on the final electricity cost and the remaining electricity cost in their accounts.

[0008] This invention provides a method, apparatus, and device for electricity bill reminders based on electricity demand forecasting. It acquires historical electricity consumption datasets and current electricity cycle weather forecast data for all users within a distribution area, and trains a neural network to obtain an electricity consumption forecast model for each user. Further, it obtains electricity consumption forecast information, establishes an electricity settlement model according to electricity settlement rules, determines the initial electricity cost, corrects the initial electricity cost using historical electricity cost datasets to obtain the final electricity cost, compares it with the remaining electricity cost, and reminds users, ensuring the accuracy of the predicted electricity cost. Correcting the initial electricity cost using historical electricity cost datasets to obtain the final electricity cost ensures the accuracy of the electricity cost forecast. Reminding users based on the final electricity cost and the remaining electricity cost allows them to clearly understand their electricity usage, improving their electricity consumption experience. It also considers the impact of weather forecast data, ensuring the accuracy of the forecast results. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating an electricity bill reminder method based on electricity demand forecasting, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of an electricity bill reminder device based on electricity demand forecasting provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0011] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0012] It should be noted that, due to peak and off-peak electricity consumption periods, time-of-use pricing is used to guide electricity users to smooth out peak demand and fill off-peak periods. The electricity cost for the same amount of electricity varies depending on the time period. The time periods defined in this application are related to the time-of-use pricing rules. For example, if the electricity price for industrial users in transformer area A is 'a' from 18:00 to 22:00, 'b' from 1:00 to 4:00, and 'c' for the remaining time periods, then the time periods for transformer area A are divided into three parts: 18:00-22:00, 1:00-4:00, and the remaining time.

[0013] Figure 1 This is a flowchart illustrating an embodiment of the electricity bill reminder method based on electricity demand forecasting provided by the present invention. (Refer to...) Figure 1 The following is a detailed description of the electricity bill reminder method based on electricity demand forecasting: S110: Obtain the historical power consumption dataset of all electricity users in the transformer area. Based on the historical power consumption dataset and the weather forecast data of the current power consumption cycle, perform power consumption forecasting to obtain the power consumption forecast information of the relevant electricity users in the current cycle.

[0014] In this embodiment, each transformer substation corresponds to a historical power consumption dataset. The historical power consumption dataset of each transformer substation includes the power consumption of each user in each time period of each historical power consumption cycle, the historical power settlement rules, and the actual power cost settled by each user in each historical power consumption cycle.

[0015] Optionally, the electricity consumption forecast information for each electricity user includes the user's total electricity consumption in the next electricity cycle and the electricity consumption in each time period.

[0016] In one possible implementation, electricity consumption forecasting is performed based on historical electricity consumption datasets and weather forecast data for the current electricity consumption cycle to obtain electricity consumption forecast information for relevant users in the current cycle, including: Build a neural network model; Data is extracted based on historical electricity consumption datasets to obtain sub-historical electricity consumption datasets for each type of electricity user within the transformer area. The neural network model is trained based on the historical electricity consumption dataset to obtain the initial electricity consumption prediction model for electricity users of the corresponding electricity application type. After each electricity consumption cycle ends, obtain the first electricity consumption dataset for each electricity user during that cycle; For each electricity user, based on the user's first electricity consumption dataset, the initial electricity consumption prediction model for the corresponding electricity application type is optimized to obtain the user's electricity consumption prediction model. Based on the electricity consumption prediction model and the weather prediction data for the current electricity consumption cycle, the electricity consumption prediction information for the corresponding electricity user in the current electricity consumption cycle is obtained.

[0017] The types of electricity use include residential electricity, commercial electricity, industrial electricity, and agricultural electricity.

[0018] Optionally, the sub-historical power consumption dataset is a historical power consumption dataset for a single type of electricity user, with each type of electricity user corresponding to a sub-historical power consumption dataset.

[0019] Each electricity user of a certain electricity consumption type corresponds to an initial electricity consumption prediction model. During the training process, the sub-historical electricity consumption dataset can be divided into a training set and a validation set to improve the accuracy of the initial electricity consumption prediction model.

[0020] In this embodiment, the first electricity consumption dataset for each electricity user refers to the electricity consumption data of that user in the recently concluded electricity consumption cycle. The length of the electricity consumption cycle is not fixed; it can be a month, a week, or a day. For example, if the electricity consumption cycle is one week, electricity settlement will be carried out after Sunday. In this case, the first electricity consumption dataset for each electricity user includes the electricity consumption of that user in each time period from Monday to Sunday of the previous week, the total electricity consumption of the previous week, the electricity settlement rules of the previous week, and the actual electricity cost settled in the previous week.

[0021] In one possible implementation, based on an electricity consumption forecasting model and weather forecast data for the current electricity consumption cycle, electricity consumption forecast information for relevant electricity users within the current electricity consumption cycle is obtained, including: For each electricity user, obtain the weather forecast data and holiday data for the current electricity consumption cycle, and input the weather forecast data and holiday data into the corresponding electricity consumption forecast model for that electricity user to obtain the initial electricity consumption forecast information for that electricity user. The initial electricity consumption forecast information for each electricity user is compared with the first historical electricity consumption information in the first electricity consumption dataset corresponding to the previous electricity consumption cycle, and the initial electricity consumption forecast information is corrected based on the comparison results to obtain the electricity consumption forecast information for the corresponding electricity user.

[0022] Optionally, the initial forecast information for each electricity user refers to the information obtained by using the electricity forecasting model to predict the electricity consumption data of the electricity user, including the total electricity consumption initially predicted for the electricity user and the electricity consumption for each time period.

[0023] The first historical electricity consumption information for each electricity user includes the user's total electricity consumption in the previous electricity cycle and the electricity consumption in each time period.

[0024] The process of making corrections based on the comparison results is as follows: Determine whether the difference in total electricity consumption exceeds the threshold.

[0025] If the threshold is not exceeded, the total electricity consumption and the corresponding amount of electricity consumption for each time period will be determined as the electricity consumption forecast information for that user.

[0026] If the threshold is exceeded, the system will retrieve information on whether there have been significant changes in temperature, humidity, holidays, etc., between the current electricity consumption cycle and the previous electricity consumption cycle.

[0027] If significant changes occur, the thresholds will be updated based on the changed data. For example, if this week's holiday is three days longer than last week's, the electricity consumption will be adjusted accordingly based on the historical daily electricity consumption during the holiday period.

[0028] Determine whether the difference in total electricity consumption exceeds the new threshold. If it does not exceed the threshold, then the predicted total electricity consumption is determined as one of the electricity consumption prediction information.

[0029] If the threshold is exceeded, it is determined whether the difference between the electricity consumption in each time period and the electricity consumption in the corresponding time period of the previous electricity cycle exceeds the corresponding threshold. If neither exceeds the threshold, the predicted total electricity consumption and the electricity consumption in each time period are determined as the electricity consumption prediction information for that user.

[0030] If the difference between the electricity consumption in a certain time period and the electricity consumption in the corresponding time period of the previous electricity cycle exceeds the threshold, the electricity consumption of that user in that time period will be re-predicted.

[0031] By constructing a neural network model and training it with historical electricity consumption datasets, an initial electricity consumption prediction model is obtained for each type of electricity user. Then, using the first electricity consumption data of each user in the previous electricity consumption cycle, the initial electricity consumption prediction model is revised to obtain a final electricity consumption prediction model. This ensures the accuracy of the electricity consumption prediction model for each user and guarantees its suitability for that user. Furthermore, by using weather forecast data, holiday data, and the corresponding first historical electricity consumption information from the previous electricity consumption cycle to revise the initial electricity consumption prediction information, the impact of extreme weather factors can be taken into account, effectively improving the accuracy of the electricity consumption prediction information.

[0032] S120: Establish an electricity settlement model based on electricity settlement rules, and determine the initial electricity cost to be settled for each electricity user in the current electricity consumption cycle based on the electricity settlement model.

[0033] The electricity settlement rules mainly include time-of-use pricing rules, and may also include tiered pricing rules. The electricity settlement model is determined based on the electricity settlement rules.

[0034] Optionally, the electricity billing model needs to incorporate electricity consumption forecast information to obtain the initial electricity cost.

[0035] In one possible implementation, an electricity settlement model is established based on electricity settlement rules, including: Based on the electricity settlement rules, the electricity price information of different types of electricity users within the distribution area is determined, and electricity settlement models for different types of electricity users are established based on the electricity price information.

[0036] Optionally, electricity price information is determined according to electricity settlement rules, and the electricity settlement model is determined based on electricity price information. For example, the distribution area... A The electricity price for industrial users in time period 1 is a Electricity consumption is a’ The electricity price during time period 2 is bElectricity consumption is b’ The electricity price during time period 3 is c Electricity consumption is c’ Meanwhile, the Taiwan area A A phased electricity pricing policy will be adopted, where electricity consumption exceeds... x Afterwards, the electricity price for the excess portion will be increased by 10%, then the substation area... A The total electricity formula in the electricity settlement model is:

[0037] in, For electricity costs, Not exceeding the time period 1 x Part of the electricity consumption, Not exceeding the time period 2 x Part of the electricity consumption, Not exceeding the time period 3 x The amount used for this part.

[0038] The electricity settlement model also includes the electricity cost for each time period of the current time cycle, which will not be listed here.

[0039] In one possible implementation, the initial electricity cost to be settled for each electricity user in the current electricity cycle is determined based on an electricity billing model, including: Based on the electricity consumption forecast information of each electricity user and the corresponding electricity settlement model, the first set of predicted electricity costs for the corresponding electricity user in the current electricity cycle is determined. Based on historical electricity consumption datasets, the first historical average electricity cost for each electricity user in each electricity consumption cycle and the second historical average electricity cost for each electricity user in each time period are determined. For each electricity user, based on the user's first historical average electricity cost and second historical average electricity cost, the user's first predicted electricity cost set is corrected to obtain the user's second predicted electricity cost set. Based on the second predicted electricity cost set for each electricity user, the initial electricity cost that the corresponding electricity user needs to settle in the current electricity cycle is determined.

[0040] Optionally, the first predicted electricity cost set includes the electricity cost for each user in each time period and the total electricity cost within the current electricity consumption cycle.

[0041] In this embodiment, the first historical average electricity cost refers to the average total electricity cost for each electricity user in each electricity consumption cycle within the historical electricity consumption dataset. For example, for each electricity user... H The historical electricity consumption dataset includes electricity cost information for the past 10 electricity consumption cycles, with the average total electricity cost being [value missing].h Then the first historical average electricity cost for this user is h .

[0042] In this embodiment, the second historical average electricity cost refers to the average electricity cost consumed by each electricity user in each time period in the historical electricity consumption dataset. For example, a user H The historical electricity consumption dataset includes electricity cost information for the past 10 electricity consumption cycles. The average electricity cost for time period 1 is [data missing]. h 1. The average electricity cost for time period 2 is: h 2. The average electricity cost for time period 3 is h 3. Then, the second historical average electricity cost for this user in time period 1 is: h 1. The second historical average electricity cost in time period 2 is h 2. The second historical average electricity cost in time period 3 is h 3.

[0043] The first historical average electricity cost is used to correct the total electricity cost in the first predicted electricity cost set, while the second historical average electricity cost is used to correct the electricity cost for each response time period in the first predicted electricity cost set. The corrected total electricity cost is the initial electricity cost. The correction method can be determined by the difference. For example, if the difference between the first historical average electricity cost and the total electricity cost is within 5%, it falls within the normal fluctuation range and no correction is needed. If the difference is between 5% and 10%, it falls within the larger fluctuation range and requires appropriate adjustment of the electricity cost for each time period based on the second historical average electricity cost before determining whether the difference between the first historical average electricity cost and the total electricity cost is within 5%. The specific adjustment method is not limited here. For example, the predicted electricity cost for each time period can be averaged with the corresponding second historical average electricity cost, and the average value can be used to replace the predicted electricity cost.

[0044] Electricity price information for different types of electricity users is determined by electricity settlement rules, and an electricity settlement model is established. Then, combined with electricity consumption forecast information, the first predicted electricity cost set for the current electricity cycle is determined. Then, through historical electricity consumption datasets, the first historical average electricity cost and the second historical average electricity cost for each electricity user are determined. The first predicted electricity cost set is then corrected to obtain the second predicted electricity cost set, which further determines the initial electricity cost. This approach takes into account the electricity consumption habits of users and improves the accuracy of the initial electricity cost forecast.

[0045] S130: Obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle, and correct the initial electricity cost of the corresponding electricity user based on the electricity cost set to obtain the final electricity cost.

[0046] Optionally, the historical electricity cost dataset is extracted from the historical electricity consumption dataset. The historical electricity cost dataset for each electricity user includes the total electricity cost used by the user in each historical electricity consumption cycle and the historical electricity cost used in each time period.

[0047] In one possible implementation, the historical electricity cost dataset for each electricity user is obtained, including: Data is extracted from historical electricity consumption datasets to obtain historical electricity cost datasets for each electricity user. The historical electricity cost dataset for each electricity user includes the sub-historical electricity cost actually settled for each time period, as well as the historical electricity cost actually settled for each electricity consumption cycle.

[0048] The historical electricity consumption dataset includes the electricity consumption of each user in each time period of each electricity cycle, as well as the total electricity consumption of each user in each electricity cycle. Therefore, data extraction is required to obtain the historical electricity cost dataset for each user.

[0049] In one possible implementation, based on historical electricity cost datasets, the electricity cost set for each electricity user in the previous electricity cycle is obtained. The initial electricity cost for the relevant electricity user is then corrected based on this electricity cost set to obtain the final electricity cost, including: The predicted difference is obtained by comparing the actual historical electricity cost settled in the previous electricity consumption cycle with the initial electricity cost of the corresponding electricity user in the historical electricity cost data. If the predicted difference does not exceed the threshold, the electricity cost that needs to be settled in the current period will be determined as the predicted electricity cost. If the prediction difference exceeds the threshold, the electricity cost set of the relevant electricity user in the previous electricity consumption cycle is obtained based on the historical electricity cost dataset. The initial electricity cost of the relevant electricity user is then corrected based on the electricity cost set of the previous electricity consumption cycle and the second predicted electricity cost set to obtain the final electricity cost.

[0050] In this embodiment, the historical electricity cost actually settled in the previous electricity consumption cycle refers to the electricity cost actually spent in the previous electricity consumption cycle.

[0051] Optionally, projected electricity costs refer to the total electricity costs expected to be incurred during the current electricity consumption cycle.

[0052] The electricity cost set of the electricity user in the previous electricity cycle includes the electricity cost of the user in each time period of the previous electricity cycle and the total electricity cost of the user in the previous electricity cycle.

[0053] It should be noted that the final electricity cost can be obtained based on the electricity cost set of the previous electricity consumption cycle, the second predicted electricity cost set, and the electricity cost correction formula. The electricity cost correction formula is as follows:

[0054] in, To predict electricity costs for electricity users, The initial electricity cost for the user is [value], and the time period is [number]. For the first A time period For the first Predicted electricity consumption for a given time period For the first The historical electricity consumption in the previous electricity consumption cycle for a given time period. For the first The unit price of electricity consumption during the current electricity consumption cycle for a given time period. For the first The unit price of electricity consumption in the previous electricity cycle for a given time period For the first Correction coefficients for each time period.

[0055] In this embodiment, the correction factor for each electricity user is different for each time period. The correction factor for each time period is obtained based on the electricity user's electricity consumption habits. For example, the electricity user... H In the historical electricity cost dataset, the electricity consumption of this user in time period 1 accounts for about 40% of the total electricity consumption, and the electricity consumption stability in time period 1 is about 80% in each electricity cycle. Therefore, the correction factor for this user in time period 1 is 40% × 80% = 0.32.

[0056] The actual electricity cost of the previous electricity cycle is obtained by acquiring historical electricity cost datasets and comparing it with the user's initial electricity cost to obtain the predicted difference. The predicted difference is then compared with a threshold and corrected. During the correction process, the user's electricity consumption habits are taken into account, as well as different correction coefficients for each time period and fluctuations in electricity price and consumption. Finally, the final electricity cost for the current electricity cycle is obtained, ensuring that the final electricity cost is closely aligned with the user's electricity consumption habits and further guaranteeing the accuracy of the final electricity cost prediction.

[0057] S140, reminds the relevant electricity user based on the final electricity cost and the remaining electricity cost in the relevant electricity user's account.

[0058] Reminders can take many forms, including SMS reminders, phone reminders, and online message reminders.

[0059] In one possible implementation, electricity users are reminded based on the final electricity cost and the remaining electricity cost in their accounts, including: Obtain the remaining electricity cost in each electricity user's account and compare the remaining electricity cost with the predicted electricity cost for the corresponding electricity user; If the remaining electricity cost exceeds a preset multiple of the predicted electricity cost, no reminder message will be issued; If the remaining electricity cost exceeds the predicted electricity cost, but does not exceed a preset multiple of the predicted electricity cost, a weak reminder message will be sent to both the account that paid the electricity cost last time and the account linked to the electricity user. If the remaining electricity cost does not exceed the predicted electricity cost, the power outage time will be estimated, and a strong reminder message with the estimated power outage time will be sent to the account that paid the electricity cost last time and the account linked to the relevant electricity user.

[0060] Optionally, the account that last paid the electricity bill can be obtained from the power system's registration information database through information filtering.

[0061] Optionally, the preset multiplier can be ≥1. The preset multiplier can be set based on the user's credit rating; the higher the credit rating, the smaller the preset multiplier. For example, if there are five credit ratings, and user 1 has a credit rating of level 5, user 2 has a credit rating of level 3, and user 3 has a credit rating of level 1, then the preset multiplier for user 1 could be 1.1, for user 2 it could be 1.5, and for user 3 it could be 2. Other methods can also be used to determine the multiplier; this scheme does not impose any limitations on this.

[0062] In this embodiment, the estimated power outage time can be determined based on the electricity user's electricity usage habits. Based on the electricity user's electricity usage habits, the remaining balance in the electricity user's account is divided into several parts according to time periods, the available time of each part is determined, and the earliest time is taken as the estimated power outage time.

[0063] Optionally, the weak reminder message can be an SMS reminder. The weak reminder message can be sent when the remaining electricity cost exceeds the predicted electricity cost but does not exceed a preset multiple, or it can be sent every other electricity consumption cycle in daily life, so as to make it convenient for electricity users to know the remaining electricity cost in their account.

[0064] Strong reminders can be sent via telephone, where the estimated power outage time can be announced to the user via voice over the phone.

[0065] By comparing the remaining electricity cost in each user's account with the predicted electricity cost for the corresponding user, and determining the corresponding reminder method based on the comparison result, reminder messages and estimated power outage times are sent to the user's linked account and the account that last paid the electricity bill. This avoids situations where the linked account and the payer are inconsistent, which would affect the user's understanding of their electricity usage. It ensures that users can know their remaining electricity cost in a timely manner, helping them to avoid power outages due to insufficient electricity funds, and effectively improving the user's electricity experience.

[0066] First, a neural network model is trained using electricity consumption data from users with similar usage patterns in a historical electricity consumption dataset. The training results are then optimized using electricity consumption data from the previous electricity cycle for each user, resulting in an electricity consumption prediction model that ensures the accuracy of both the model and the prediction information. An electricity billing model is established and combined with the electricity consumption prediction information to obtain the initial electricity cost. This initial cost is then corrected based on historical electricity cost datasets, improving the alignment between the final electricity cost and the user's usage habits. The final electricity cost is compared with the remaining electricity cost, and a reminder message is sent, allowing users to understand their electricity usage with minimal disruption, thus improving their electricity experience. Furthermore, the impact of weather changes is considered using weather forecast data, ensuring the accuracy of the prediction results.

[0067] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0068] Corresponding to the electricity bill reminder method based on electricity demand forecasting in the above embodiment, Figure 2 The diagram shows a schematic of an electricity bill reminder device based on electricity demand forecasting provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown.

[0069] See Figure 2 The electricity bill reminder device 2 based on electricity demand forecasting in this embodiment of the invention may include: Prediction module 21 is used to obtain the historical power consumption dataset of all electricity users in the transformer area, and based on the historical power consumption dataset and the weather forecast data of the current power consumption cycle, to perform power consumption forecast to obtain the power consumption forecast information of the relevant electricity users in the current cycle. Settlement module 22 is used to establish an electricity settlement model based on electricity settlement rules, and based on the electricity settlement model, determine the initial electricity cost that each electricity user needs to settle in the current electricity consumption cycle; The correction module 23 is used to obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle, and correct the initial electricity cost of the corresponding electricity user based on the electricity cost set to obtain the final electricity cost. The reminder module 24 is used to remind relevant electricity users based on the final electricity cost and the remaining electricity cost in the relevant electricity user's account.

[0070] In one possible implementation, the prediction module 21 is specifically used for: Build a neural network model; Data is extracted based on historical electricity consumption datasets to obtain sub-historical electricity consumption datasets for each type of electricity user within the transformer area. The neural network model is trained based on the sub-historical electricity consumption dataset to obtain the initial electricity consumption prediction model for electricity users of the corresponding electricity application type. After each electricity consumption cycle ends, obtain the first electricity consumption dataset for each electricity user during that cycle; For each electricity user, based on the user's first electricity consumption dataset, the initial electricity consumption prediction model for the corresponding electricity application type is optimized to obtain the user's electricity consumption prediction model. Based on the electricity consumption prediction model and the weather prediction data for the current electricity consumption cycle, the electricity consumption prediction information for the corresponding electricity user in the current electricity consumption cycle is obtained.

[0071] In one possible implementation, the prediction module 21 is further configured to: For each electricity user, obtain the weather forecast data and holiday data for the current electricity consumption cycle, and input the weather forecast data and holiday data into the corresponding electricity consumption forecast model for that electricity user to obtain the initial electricity consumption forecast information for that electricity user. The initial electricity consumption forecast information of each electricity user is compared with the first historical electricity consumption information in the first electricity consumption dataset of the previous electricity consumption cycle, and the initial electricity consumption forecast information is corrected according to the comparison results to obtain the electricity consumption forecast information of the corresponding electricity user.

[0072] In one possible implementation, the correction module 23 is specifically used for: The predicted difference is obtained by comparing the actual historical electricity cost settled in the previous electricity consumption cycle with the initial electricity cost of the corresponding electricity user in the historical electricity cost data. If the predicted difference does not exceed the threshold, the electricity cost that needs to be settled in the current period will be determined as the predicted electricity cost. If the prediction difference exceeds the threshold, the electricity cost set of the relevant electricity user in the previous electricity consumption cycle is obtained based on the historical electricity cost dataset. The initial electricity cost of the relevant electricity user is then corrected based on the electricity cost set of the previous electricity consumption cycle and the second predicted electricity cost set to obtain the final electricity cost.

[0073] In one possible implementation, the settlement module 22 is specifically used for: Based on the electricity settlement rules, the electricity price information of different types of electricity users within the distribution area is determined, and electricity settlement models for different types of electricity users are established based on the electricity price information.

[0074] In one possible implementation, the settlement module 22 is further used for: Based on the electricity consumption forecast information of each electricity user and the corresponding electricity settlement model, the first set of predicted electricity costs for the corresponding electricity user in the current electricity cycle is determined. Based on historical electricity consumption datasets, the first historical average electricity cost for each electricity user in each electricity consumption cycle and the second historical average electricity cost for each electricity user in each time period are determined. For each electricity user, based on the user's first historical average electricity cost and second historical average electricity cost, the user's first predicted electricity cost set is corrected to obtain the user's second predicted electricity cost set. Based on the second predicted electricity cost set for each electricity user, the initial electricity cost that the corresponding electricity user needs to settle in the current electricity cycle is determined.

[0075] In one possible implementation, the correction module 23 is also used for: Data is extracted from historical electricity consumption datasets to obtain historical electricity cost datasets for each electricity user. The historical electricity cost dataset for each electricity user includes the sub-historical electricity cost actually settled for each time period, as well as the historical electricity cost actually settled for each electricity consumption cycle.

[0076] In one possible implementation, the reminder module 24 is specifically used for: Obtain the remaining electricity cost in each electricity user's account and compare the remaining electricity cost with the predicted electricity cost for the corresponding electricity user; If the remaining electricity cost exceeds a preset multiple of the predicted electricity cost, no reminder message will be issued; If the remaining electricity cost exceeds the predicted electricity cost, but does not exceed a preset multiple of the predicted electricity cost, a weak reminder message will be sent to both the account that paid the electricity cost last time and the account linked to the electricity user. If the remaining electricity cost does not exceed the predicted electricity cost, the power outage time will be estimated, and a strong reminder message with the estimated power outage time will be sent to the account that paid the electricity cost last time and the account linked to the relevant electricity user.

[0077] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.

[0078] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.

[0079] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.

[0080] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0081] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0082] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for electricity bill reminders based on electricity demand forecasting, characterized in that, include: Obtain historical power consumption datasets for all electricity users within the distribution area. Based on the historical power consumption datasets and weather forecast data for the current electricity consumption cycle, perform electricity consumption forecasts to obtain electricity consumption forecast information for the relevant electricity users in the current cycle. An electricity settlement model is established based on the electricity settlement rules, and based on the electricity settlement model, the initial electricity cost to be settled for each electricity user in the current electricity consumption cycle is determined. Obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle, and correct the initial electricity cost of the corresponding electricity user based on the electricity cost set to obtain the final electricity cost. Based on the final electricity cost and the remaining electricity cost in the relevant user's account, a reminder will be sent to the relevant user.

2. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, The electricity consumption forecast is performed based on the historical electricity consumption dataset and the weather forecast data for the current electricity consumption cycle to obtain the electricity consumption forecast information for relevant electricity users in the current cycle, including: Construct a neural network model; Data is extracted based on the historical power consumption dataset to obtain sub-historical power consumption datasets for each type of electricity user within the transformer area. The neural network model is trained based on the aforementioned historical electricity consumption dataset to obtain an initial electricity consumption prediction model for electricity users of the corresponding electricity application type. After each electricity consumption cycle ends, obtain the first electricity consumption dataset for each electricity user during that cycle; For each electricity user, based on the user's first electricity consumption dataset, the initial electricity consumption prediction model for the corresponding electricity application type is optimized to obtain the user's electricity consumption prediction model. Based on the electricity consumption prediction model and the weather prediction data for the current electricity consumption cycle, the electricity consumption prediction information for the corresponding electricity user in the current electricity consumption cycle is obtained.

3. The electricity bill reminder method based on electricity demand forecasting as described in claim 2, characterized in that, The electricity consumption forecast information for relevant electricity users within the current electricity consumption cycle is obtained based on the electricity consumption forecast model and weather forecast data for the current electricity consumption cycle, including: For each electricity user, obtain the weather forecast data and holiday data for the current electricity consumption cycle, and input the weather forecast data and holiday data into the corresponding electricity consumption forecast model of the electricity user to obtain the initial electricity consumption forecast information of the electricity user. The initial electricity consumption forecast information of each electricity user is compared with the first historical electricity consumption information in the first electricity consumption dataset corresponding to the previous electricity consumption cycle, and the initial electricity consumption forecast information is corrected according to the comparison results to obtain the electricity consumption forecast information of the corresponding electricity user.

4. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, The process involves obtaining the electricity cost set for each user in the previous electricity cycle based on the historical electricity cost dataset, and then correcting the initial electricity cost for the relevant user based on the electricity cost set to obtain the final electricity cost, including: The historical electricity cost data is compared with the actual historical electricity cost settled in the previous electricity consumption cycle and the initial electricity cost of the corresponding electricity user to obtain the predicted difference. If the predicted difference does not exceed the preset threshold, the electricity cost to be settled in the current period is determined as the predicted electricity cost. If the predicted difference exceeds the preset threshold, the electricity cost set of the relevant electricity user in the previous electricity consumption cycle is obtained based on the historical electricity cost dataset. Based on the electricity cost set of the previous electricity consumption cycle and the second predicted electricity cost set, the initial electricity cost of the relevant electricity user is corrected to obtain the final electricity cost.

5. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, Establish an electricity settlement model based on electricity settlement rules, including: Based on the electricity settlement rules, the electricity price information of different types of electricity users in the distribution area is determined, and the electricity settlement model of different types of electricity users is established based on the electricity price information.

6. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, The determination of the initial electricity cost to be settled for each electricity user in the current electricity cycle based on the electricity settlement model includes: Based on the electricity consumption forecast information of each electricity user and the corresponding electricity settlement model, the first set of predicted electricity costs for the corresponding electricity user in the current electricity cycle is determined. Based on historical electricity consumption datasets, the first historical average electricity cost for each electricity user in each electricity consumption cycle and the second historical average electricity cost for each electricity user in each time period are determined. For each electricity user, based on the user's first historical average electricity cost and second historical average electricity cost, the user's first predicted electricity cost set is corrected to obtain the user's second predicted electricity cost set. Based on the second predicted electricity cost set for each electricity user, the initial electricity cost that the corresponding electricity user needs to settle in the current electricity cycle is determined.

7. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, The process of obtaining historical electricity cost datasets for each electricity user includes... Data is extracted from the historical electricity consumption dataset to obtain the historical electricity cost dataset for each electricity user. The historical electricity cost dataset for each electricity user includes the sub-historical electricity cost actually settled for each time period, as well as the historical electricity cost actually settled for each electricity consumption cycle.

8. The electricity bill reminder method based on electricity demand forecasting as described in claim 1, characterized in that, The reminder to relevant electricity users based on the final electricity cost and the remaining electricity cost in the relevant electricity user's account includes: Obtain the remaining electricity cost in each electricity user's account and compare the remaining electricity cost with the predicted electricity cost for the corresponding electricity user; If the remaining electricity cost exceeds a preset multiple of the predicted electricity cost, no reminder message will be issued; If the remaining electricity cost exceeds the predicted electricity cost, but does not exceed a preset multiple of the predicted electricity cost, a weak reminder message will be sent to both the account that paid the electricity cost last time and the account bound to the electricity user. If the remaining electricity cost does not exceed the predicted electricity cost, the power outage time will be estimated, and a strong reminder message with the estimated power outage time will be sent to the account that paid the electricity cost last time and the account linked to the relevant electricity user.

9. An electricity bill reminder device based on electricity demand forecasting, characterized in that, include: The prediction module is used to obtain the historical power consumption dataset of all electricity users in the transformer area, and based on the historical power consumption dataset and the weather forecast data of the current power consumption cycle, to make power consumption predictions and obtain the power consumption prediction information of the relevant electricity users in the current cycle. The settlement module is used to establish an electricity settlement model based on electricity settlement rules, and based on the electricity settlement model, determine the initial electricity cost that each electricity user needs to settle in the current electricity consumption cycle; The correction module is used to obtain the historical electricity cost dataset for each electricity user, and based on the historical electricity cost dataset, obtain the electricity cost set for each electricity user in the previous electricity cycle, and based on the electricity cost set, correct the initial electricity cost of the relevant electricity user to obtain the final electricity cost. The reminder module is used to remind relevant electricity users based on the final electricity cost and the remaining electricity cost in the relevant electricity user's account.

10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.

Images