Power price intelligent prediction system and method based on data analysis

Abstract

The invention relates to the technical field of electric power data processing, and discloses an electric power price intelligent prediction system and method based on data analysis, and the system comprises a user side electric power price prediction authority management module, a user side electric power price and electricity consumption prediction module, and a user side electric power cost prediction output module. The electric power price increase rate and the electric power consumption increase rate parameters of the user side in the prediction month are scientifically analyzed based on numerical analysis, and the electric power price increase rate and the electric power consumption increase rate parameters of the user side in the prediction month are accurately counted; the electricity price and electricity consumption parameters of the user side in the current month are accurately collected through the electricity management platform; the electricity price and electricity consumption parameters of the prediction month of the user side are scientifically and accurately metered based on numerical analysis, the user side can conveniently and efficiently predict the electricity price and electricity consumption, and the scientificity and quality of electricity consumption management of the user side are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power data processing, and in particular to a system and method for intelligently predicting power prices based on data analysis. Background Art

[0002] Electricity price forecasting refers to the use of mathematical tools to analyze and study historical data, explore the internal connections and development and change laws between things, and predict the future electricity transaction prices in the electricity market under the condition of meeting certain accuracy and speed, taking into account the market supply and demand relationship, the market power of market participants, electricity costs, and the influence of important factors such as the electricity market system structure and social and economic situation. Electricity price is a core indicator that reflects the operation status of the electricity market and evaluates the efficiency of market competition. It is the basis for electricity market decision-making. However, the existing electricity price forecast cannot be applied to the user side to accurately predict the future market electricity price, nor can it accurately predict the future electricity cost based on the user-side predicted electricity price, which reduces the safety and scientificity of electricity use at the user side.

[0003] The Chinese invention patent application with publication number CN114201858A discloses a pricing method for real-time electricity prices of new energy. It mines the relevant factors affecting the real-time electricity prices of new energy through standardized-Euclidean distance, proposes the fitting function relationship between each relevant factor and the real-time electricity prices of new energy, establishes a min-max model and a min-max multi-scenario objective function, and uses the Lagrangian optimization duality theory to transform and solve the model. However, the above technical solutions cannot achieve efficient and accurate prediction of future electricity prices and electricity costs at the power user end. Summary of the invention

[0004] 1. Technical issues to be resolved In order to solve the problem that the above-mentioned existing electricity price forecast cannot be applied to the user side to realize the accurate forecast of future market electricity price at the user side, and cannot accurately predict the future electricity cost based on the predicted electricity price at the user side, which reduces the safety and scientificity of electricity use at the user side, the above purpose is to accurately collect the user side identity information and the user side electricity price forecast demand characteristic information, accurately identify the user side electricity price forecast operation authority, accurately search the user side historical monthly electricity price increase rate parameters and the user side historical monthly electricity consumption increase rate parameters, scientifically count the user side predicted monthly electricity price increase rate parameters and the predicted monthly electricity consumption increase rate parameters, collect the user side current monthly electricity price parameters and the user side current monthly electricity consumption parameters, accurately measure the user side predicted monthly electricity price parameters and the user side predicted monthly electricity consumption parameters, accurately predict the user side electricity cost, and improve the safety and scientificity of electricity use at the user side.

[0005] (II) Technical solution The present invention is implemented by the following technical scheme: an intelligent prediction method for power prices based on data analysis, the method comprising the following steps: S1. Collecting user-side identity text data and user-side power price forecast demand feature text data; S2, performing authority identification processing for the user to perform the power price forecasting operation based on the user-side identity text data and the power price forecasting registration personnel identity text data, and generating user-side power price forecasting operation authority identification data, and when there is no authority, ending the current user-side power price forecasting operation; S3. When the user has the authority, based on the user-side power price forecast demand feature text data, the user-side identity text data, the historical monthly power price increase rate data, and the historical monthly power consumption increase rate data, respectively, the user-side power price increase rate parameters and the power consumption increase rate parameters of the historical months are searched and processed to generate the user-side historical monthly power price increase rate data and the user-side historical monthly power consumption increase rate data; S4, performing numerical statistical processing on the power price increase rate parameters and power consumption increase rate parameters of the user-side predicted month according to the power price increase rate parameters and power consumption increase rate parameters of the user-side historical month, and generating the power price increase rate data and power consumption increase rate data of the user-side predicted month; S5, collecting the current monthly electricity price data and the current monthly electricity consumption data of the user end, and performing numerical measurement processing on the electricity price parameters and electricity consumption parameters of the predicted month of the user end with the predicted monthly electricity price increase rate data and the predicted monthly electricity consumption increase rate data of the user end, to generate the predicted monthly electricity price data and the predicted monthly electricity consumption data of the user end; S6. Perform numerical measurement processing of the power cost of the user-side predicted month based on the power price parameters and power consumption parameters of the user-side predicted month, and generate power cost data of the user-side predicted month; S7. Construct the user-side power price forecast result data and execute the power price forecast result display operation.

[0006] Preferably, the steps of collecting the user-side identity text data and the user-side power price forecast demand feature text data are as follows: S11. The user enters personal or corporate identity text information online through the power management platform and generates user-side identity text data , the user terminal identity text data includes name, ID number or company name, company code; Collect the user-side electricity price forecast demand feature text information online through the power management platform and generate the user-side electricity price forecast demand feature text data The user-side electricity price forecast demand characteristic text data includes the administrative region name information where the user is located, the electricity consumption field information and the historical electricity price record month range parameters required for the user-side electricity price forecast operation. The electricity consumption field includes industrial electricity, commercial electricity, agricultural electricity and residential electricity.

[0007] Preferably, the authority identification processing of the user-side power price forecasting operation is performed based on the user-side identity text data and the power price forecasting registration personnel identity text data, and the power price forecasting operation authority identification data of the user-side is generated. When there is no authority, the operation steps for ending the power price forecasting operation of the user-side are as follows: S21. Establishing a text data set of the identity of the personnel registered for power price forecasting , ;in Indicates The identity text data of the person who registered for electricity price forecasting, Indicates the maximum number of persons registered for power price forecasting, wherein the identity text data of persons registered for power price forecasting indicates the identity information of persons registered for power price forecasting who have been registered and backed up on the power management platform; S22, using the BERT language model algorithm to convert the user end identity text data A text data set of the identity of the person registered with the electricity price forecast The identity text data of the person registered for the electricity price forecast Perform identity text data matching and generate user-side power price forecasting operation authority identification data based on the identity text data matching results ; when and If the identity text data is matched successfully, it means that the user has the authority to perform the power price forecasting operation on the power management platform, and the user's power price forecasting operation authority identification data is output. To have authority; when and If the identity text data is not matched successfully, it means that the user end does not have the authority to perform the power price forecasting operation on the power management platform, then the user end power price forecasting operation authority identification data is output If the user has no authority, the user-side electricity price forecasting operation will be terminated directly.

[0008] Preferably, when the user has the authority, the user-side electricity price forecast demand feature text data, the user-side identity text data and the historical monthly electricity price increase rate data, the historical monthly electricity consumption increase rate data are respectively searched and processed for the user-side electricity price increase rate parameters and the electricity consumption increase rate parameters, and the operation steps of generating the user-side historical monthly electricity price increase rate data and the user-side historical monthly electricity consumption increase rate data are as follows: S31, when the user-side power price forecasting operation authority identification data If authorized, establish a historical monthly electricity price increase rate data set , ;in Indicates The historical monthly electricity price increase rate data corresponding to the combination type of electricity price forecast demand characteristics, Indicates the maximum number of power price forecast demand feature combination types. The power price forecast demand feature combination type indicates the power price forecast demand type mainly composed of the name information of the administrative region where the user-side power price forecast is located, the power consumption field information where the user-side power price forecast is located, and the monthly range parameters of the historical power price records required for the user-side power price forecast; Establish a historical monthly electricity consumption increase rate data set , ;in Indicates the user's The data of the increase rate of electricity consumption in the past months, Indicates the maximum number of historical months on the user side; S32, the user-side power price forecast demand feature text data The data set of the historical monthly electricity price increase rate The historical monthly electricity price increase rate data mentioned in According to the keyword matching of power price forecast demand characteristics, the user-side power price forecast demand characteristics text data is searched out The corresponding historical monthly electricity price increase rate data , and generate a data set of the user-side historical monthly electricity price increase rate , execute to generate the user-side historical monthly electricity price increase rate data set The specific steps are as follows: S321, initialization, in the historical monthly electricity price increase rate data set The electricity price increase rate is randomly updated in the search space to search for the location of the Tasmanian devil population. The electricity price increase rate search for the location of the Tasmanian devil is updated with the following formula: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals exist The position of the dimensional search space, that is, the increase rate of electricity price searches for Tasmanian devil individuals In the spatial dimension The historical monthly electricity price increase rate data set The position in the search space, , Respectively represent the historical monthly electricity price increase rate data set The lower and upper boundaries in the search space, Represents a random number in the interval [0,1]; S322, exploration phase, the power price increase rate searches for the Tasmanian devil in the historical monthly power price increase rate data set Search the search space to find out the text data related to the user-side power price forecast demand characteristics Matching the historical monthly electricity price increase rate data Targeting carrion for food, searching for Tasmanian devils in the historical monthly electricity price increase rate data set The search space scans the habitat area to identify the text data with the demand characteristics of the user-side electricity price prediction Matching the historical monthly electricity price increase rate data The behavior of the decay is similar to the algorithm search in the problem space with the user-side electricity price forecast demand feature text data Matching the historical monthly electricity price increase rate data The process of increasing the electricity price is as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month Search the search space for the position of the selected target carrion, Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals in the historical month electricity price increase rate data set Select target carrion in the search space location, ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The maximum number of carrion to search; Based on the selected target carrion, the electricity price increase rate searches for Tasmanian devils in the historical monthly electricity price increase rate data set The new position in the search space is calculated, and the rate of increase in electricity price is used to search for the new position of the Tasmanian devil as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month The position before the update in the search space; Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month The updated position in the search space; and Respectively represent the data set of the increase rate of electricity price in the historical month The rate of increase in electricity price in the search space searches for carrion quality parameters of the location coordinates of Tasmanian devil individuals before and after the location update; S323, in the development stage, the power price increase rate searches for the Tasmanian devil in the historical monthly power price increase rate data set Search the search space to find out the text data related to the user-side power price forecast demand characteristics Matching the historical monthly electricity price increase rate data The behavior of the Tasmanian devil in the process of attacking the target prey has two stages. In the first stage, the Tasmanian devil searches for the target prey by scanning the historical monthly data set. Search the search space to find out the text data related to the user-side power price forecast demand characteristics Matching the historical monthly electricity price increase rate data Target prey, select the historical monthly electricity price increase rate data Target and attack the historical monthly electricity price increase rate data Target prey; in the second stage, close to the historical monthly electricity price increase rate data After the target prey, the power price increase rate search Tasmanian devil chasing the historical monthly power price increase rate data Target prey and prey on the historical monthly electricity price increase rate data Target prey; Electricity price increase rate Searching Tasmanian devils to identify selected target prey behavior simulation formula is as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month Search the search space for the location of the selected target prey, Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals in the historical month electricity price increase rate data set Target prey selected in search space location, ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The maximum number of target prey to be searched; Based on the selected target prey, the Tasmanian devil was searched in the historical monthly data set. The new position in the search space is calculated, and the rate of increase in electricity price is used to search for the new position of the Tasmanian devil as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month The position before the update in the search space; Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The data collection of the increase rate of electricity price in the historical month The updated position in the search space; and Respectively represent the data set of the increase rate of electricity price in the historical month The rate of increase in electricity price in the search space is the target prey quality parameter for the position coordinates of the Tasmanian devil individuals before and after the position update; S324: When the algorithm meets the maximum number of iterations, the text data corresponding to the user-side power price forecast demand characteristics is output. Match all the historical monthly electricity price increase rate data ; S325: All the historical monthly electricity price increase rate data output in step S324 are Generate a data set of the user's historical monthly electricity price increase rate through data identification ,in Indicates The historical monthly electricity price increase rate data of each user, Indicates Historical monthly electricity price increase rate data for each user; Similarly, the intelligent recognition algorithm in steps S321 to S325 is used to identify the user end identity text data. and the user-side electricity price forecast demand characteristic text data The data set of the increase rate of electricity consumption in the historical month The historical monthly electricity consumption increase rate data mentioned in According to the identity characteristics and the power price forecast demand characteristics keyword matching, search out the user end identity text data and the user-side electricity price forecast demand characteristic text data The corresponding historical monthly electricity consumption increase rate data , and generate a data set of the user's historical monthly electricity consumption increase rate ,in Indicates The historical monthly electricity consumption increase rate data of each user, Indicates Historical monthly electricity consumption increase rate data for each user.

[0009] Preferably, the steps of performing numerical statistical processing on the power price increase rate parameters and power consumption increase rate parameters of the predicted month on the user side according to the power price increase rate parameters and power consumption increase rate parameters of the historical months on the user side to generate the power price increase rate data of the predicted month on the user side and the power consumption increase rate data of the predicted month on the user side are as follows: S41, collecting the historical monthly electricity price increase rate data of the user side The historical monthly electricity price increase rate data of the user side mentioned in to Combine the mean formula to measure the average increase rate of the user's historical monthly electricity price and generate the user's predicted monthly electricity price increase rate data. ,in ; Similarly, the user-side historical monthly electricity consumption increase rate data set The historical monthly electricity consumption increase rate data of the user side mentioned in to Combined with the mean formula, the average measurement of the historical monthly electricity consumption increase rate at the user end is processed to generate the user end predicted monthly electricity consumption increase rate data ,in .

[0010] Preferably, the steps of collecting the current monthly electricity price data and the current monthly electricity consumption data of the user end and performing numerical measurement processing of the electricity price parameters and electricity consumption parameters of the predicted month of the user end with the predicted monthly electricity price increase rate data and the predicted monthly electricity consumption increase rate data of the user end to generate the predicted monthly electricity price data and the predicted monthly electricity consumption data of the user end are as follows: S51, collect the electricity price parameters of the current month at the user end online through the power management platform and generate the electricity price data of the current month at the user end ,in The unit is yuan per kilowatt-hour; The power management platform collects the power consumption parameters of the user end in the current month online and generates the power consumption data of the user end in the current month ,in The unit is kilowatt-hour; S52: the current monthly electricity price data of the user terminal The monthly electricity price increase rate data predicted by the user side Perform numerical integral measurement processing to generate user-side predicted monthly electricity price data ,in , The unit is yuan per kilowatt-hour; The current monthly electricity consumption data of the user end The predicted monthly electricity consumption increase rate data of the user side Perform numerical integral measurement processing to generate user-side predicted monthly power consumption data ,in , The unit is kilowatt-hour.

[0011] Preferably, the steps of performing numerical measurement processing of the power cost of the user-side predicted month based on the power price parameters and power consumption parameters of the user-side predicted month to generate the power cost data of the user-side predicted month are as follows: S61, the user-side predicted monthly electricity price data The user-side predicted monthly electricity consumption data Combined with the price formula, the total price of electricity consumption in the user's predicted month is processed by product measurement to generate the user's predicted monthly electricity cost data. ,in , The unit is yuan.

[0012] Preferably, the steps of constructing the user-side power price forecast result data and performing the power price forecast result display operation are as follows: S71, the user-side power price forecast demand feature text data , the user-side predicted monthly electricity price data and the user-side predicted monthly electricity cost data Combine data to construct user-side electricity price forecast result data ; S72: the user-side power price prediction result data Feedback is pushed to the power management platform through the IoT communication network and displayed on the display screen.

[0013] An intelligent power price prediction system based on data analysis, used to implement the intelligent power price prediction method based on data analysis, the system includes a user-side power price prediction authority management module, a user-side power price and power consumption prediction module, and a user-side power cost prediction output module; The user-side power price prediction authority management module includes a user-side identity information collection unit, a user-side power price prediction demand feature information collection unit, a power price prediction registered personnel identity information storage unit, and a user-side power price prediction operation authority identification unit; The user-side identity information collection unit collects user-side identity text data through the power management platform; the user-side power price forecast demand feature information collection unit collects user-side power price forecast demand feature text data through the power management platform; the power price forecast registered personnel identity information storage unit is used to store the power price forecast registered personnel identity text data; the user-side power price forecast operation authority identification unit performs the user-side power price forecast operation authority identification processing based on the user-side identity text data and the power price forecast registered personnel identity text data, and generates the user-side power price forecast operation authority identification data; The user-side electricity price and electricity consumption prediction module includes a historical monthly electricity price increase rate information storage unit, a user-side historical monthly electricity price increase rate search unit, a historical monthly electricity consumption increase rate information storage unit, a user-side historical monthly electricity consumption increase rate search unit, a user-side predicted monthly electricity price increase rate metering unit, a user-side predicted monthly electricity consumption increase rate metering unit, a user-side current monthly electricity price collection unit, a user-side current monthly electricity consumption collection unit, a user-side predicted monthly electricity price metering unit, and a user-side predicted monthly electricity consumption metering unit; The historical monthly electricity price increase rate information storage unit is used to store historical monthly electricity price increase rate data; the user-side historical monthly electricity price increase rate search unit performs a user-side historical monthly electricity price increase rate parameter search process based on the user-side electricity price forecast demand feature text data and the historical monthly electricity price increase rate data to generate the user-side historical monthly electricity price increase rate data; the historical monthly electricity consumption increase rate information storage unit is used to store historical monthly electricity consumption increase rate data; the user-side historical monthly electricity consumption increase rate search unit performs a user-side historical monthly electricity consumption increase rate parameter search process based on the user-side electricity price forecast demand feature text data, the user-side identity text data and the historical monthly electricity consumption increase rate data to generate the user-side historical monthly electricity consumption increase rate data; the user-side predicted monthly electricity price increase rate metering unit performs a user-side predicted monthly electricity price increase rate parameter numerical statistical processing based on the user-side historical monthly electricity price increase rate parameters to generate the user-side predicted monthly electricity price Increase rate data; the user-side predicted monthly electricity consumption increase rate metering unit performs numerical statistical processing on the parameters of the electricity price increase rate of the user-side predicted month according to the parameters of the electricity consumption increase rate of the user-side historical months, and generates the user-side predicted monthly electricity consumption increase rate data; the user-side current month electricity price collection unit collects the user-side current month electricity price data through the power management platform; the user-side current month electricity consumption collection unit collects the user-side current month electricity consumption data through the power management platform; the user-side predicted monthly electricity price metering unit performs numerical metering processing on the electricity price parameters of the user-side predicted month according to the user-side current month electricity price data and the user-side predicted monthly electricity price increase rate data, and generates the user-side predicted monthly electricity price data; the user-side predicted monthly electricity consumption metering unit performs numerical metering processing on the electricity consumption parameters of the user-side predicted month according to the user-side current month electricity consumption data and the user-side predicted monthly electricity consumption increase rate data, and generates the user-side predicted monthly electricity consumption data; The user-side power price and power consumption prediction module includes a user-side predicted monthly power cost metering unit and a user-side power price prediction result information display unit; The user-side predicted monthly electricity cost metering unit performs numerical metering processing on the user-side predicted monthly electricity cost based on the user-side predicted monthly electricity price parameters and electricity consumption parameters to generate user-side predicted monthly electricity cost data; the user-side electricity price forecast result information display unit is used to construct the user-side electricity price forecast result data and perform the electricity price forecast result display operation.

[0014] (III) Beneficial effects The present invention provides an intelligent prediction system and method for power prices based on data analysis, which has the following beneficial effects: 1. Accurately collect user-side identity information and user-side electricity price forecast demand information through the power management platform to provide reliable data support for accurately judging the user-side electricity price forecast operation authority and accurately predicting electricity prices; scientifically store the identity text parameters of electricity price forecast registered personnel and combine intelligent search algorithms with user-side identity information to intelligently identify the authority of the user to execute electricity price forecast operations, thereby improving the security of electricity price forecast operations on the user side.

[0015] 2. Through standard storage of historical monthly electricity price increase rate parameters, combined with intelligent recognition algorithm and user-side electricity price forecast demand characteristic text parameters, accurate search of user-side historical monthly electricity price increase rate parameters is performed to achieve efficient and accurate acquisition of user-side historical electricity price change rate parameters; accurate storage of historical monthly electricity consumption increase rate parameters, combined with intelligent recognition algorithm and user-side electricity price forecast demand characteristic text parameters and user-side identity text parameters, accurate search of user-side historical monthly electricity consumption increase rate parameters is performed to achieve efficient and accurate acquisition of user-side historical electricity consumption change rate parameters; based on numerical analysis, scientific analysis of the user-side forecast month electricity price increase rate and electricity consumption increase rate parameters is performed to achieve accurate statistics of the user-side forecast month electricity price increase rate and electricity consumption increase rate parameters; through the power management platform, accurate collection of the user-side electricity price and electricity consumption parameters of the current month provides real data support for scientific prediction of the user-side electricity price and electricity consumption parameters; based on numerical analysis, scientifically and accurately measure the user-side forecast month electricity price and electricity consumption parameters to achieve convenient and efficient prediction of electricity price and electricity consumption at the user end, improving the scientificity and quality of power consumption management at the user end.

[0016] 3. Through the scientific measurement of the monthly electricity cost parameters of the user side based on the monthly electricity price parameters and electricity consumption parameters of the user side in combination with numerical analysis, the electricity cost parameters of the user side can be predicted intuitively and accurately, and the intelligent power consumption management of the user side can be realized; based on the user side's electricity price forecast demand information, electricity price forecast results, electricity consumption forecast results, and electricity cost forecast, the user side electricity price forecast result information is scientifically constructed, and at the same time, in conjunction with the Internet of Things communication network, timely and efficiently transmits feedback to the power management platform, and in conjunction with the display screen for intuitive visual feedback, efficient and clear output of electricity price forecast result information is achieved, which improves the intuitiveness and convenience of power consumption management at the user side. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the modules of the intelligent prediction system for power prices based on data analysis provided by the present invention; Figure 2 A flow chart of the method for intelligent prediction of electricity prices based on data analysis provided by the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The embodiments of the power price intelligent prediction system and method based on data analysis are as follows: Example

[0020] See also Figure 1 - Figure 2 , an intelligent prediction method for power prices based on data analysis, the method comprises the following steps: S1. Collecting user-side identity text data and user-side power price forecast demand feature text data; S2. Performing authority identification processing for the user to perform the power price forecasting operation based on the user's identity text data and the power price forecasting registration personnel's identity text data, and generating user's power price forecasting operation authority identification data. If there is no authority, the power price forecasting operation of the user is terminated; S3. When the user has the authority, based on the user-side electricity price forecast demand feature text data, the user-side identity text data, the historical monthly electricity price increase rate data, and the historical monthly electricity consumption increase rate data, the user-side historical monthly electricity price increase rate parameters and the electricity consumption increase rate parameters are searched and processed to generate the user-side historical monthly electricity price increase rate data and the user-side historical monthly electricity consumption increase rate data; S4, performing numerical statistical processing on the power price increase rate parameters and power consumption increase rate parameters of the user-side predicted month according to the power price increase rate parameters and power consumption increase rate parameters of the user-side historical month, and generating the power price increase rate data and power consumption increase rate data of the user-side predicted month; S5, collecting the current monthly electricity price data and the current monthly electricity consumption data of the user end, and performing numerical measurement processing on the electricity price parameters and electricity consumption parameters of the predicted month of the user end with the electricity price increase rate data and the electricity consumption increase rate data of the predicted month of the user end, to generate the electricity price data and the electricity consumption data of the predicted month of the user end; S6. Perform numerical measurement processing of the power cost of the user-side predicted month based on the power price parameters and power consumption parameters of the user-side predicted month, and generate power cost data of the user-side predicted month; S7. Construct the user-side power price forecast result data and execute the power price forecast result display operation.

[0021] For further information, see Figure 1 - Figure 2 ,The operation steps for collecting the user end identity text data and the user end electricity price forecast demand feature text data are as follows: S11. The user enters personal or corporate identity text information online through the power management platform and generates user-side identity text data ,The user end identity text data includes name, ID number or company name, company code; Collect the user-side electricity price forecast demand feature text information online through the power management platform and generate the user-side electricity price forecast demand feature text data The user-side electricity price forecast demand characteristic text data includes the administrative region name information where the user is located, the electricity consumption field information and the historical electricity price record month range parameters required for the user-side electricity price forecast operation. The electricity consumption field includes industrial electricity, commercial electricity, agricultural electricity and residential electricity.

[0022] The authority identification processing of the user-side power price forecasting operation is performed based on the user-side identity text data and the identity text data of the power price forecasting registration personnel, and the power price forecasting operation authority identification data of the user-side is generated. If there is no authority, the operation steps to end the power price forecasting operation of the user-side are as follows: S21. Establishing a text data set of the identity of the personnel registered for power price forecasting , ;in Indicates The identity text data of the person who registered for electricity price forecasting, Indicates the maximum number of persons registered for power price forecasting. The identity text data of persons registered for power price forecasting indicates the identity information of persons registered for power price forecasting who have been registered and backed up on the power management platform. S22. Use the BERT language model algorithm to convert the user's identity text data A collection of text data on the identities of people registered for electricity price prediction China Power Electricity Price Forecasting Registration Personnel Identity Text Data Perform identity text data matching and generate user-side power price forecasting operation authority identification data based on the identity text data matching results ; when and If the identity text data is matched successfully, it means that the user has the authority to perform the power price forecasting operation on the power management platform, and the user's power price forecasting operation authority identification data is output. To have authority; when and If the identity text data is not matched successfully, it means that the user end does not have the authority to perform the power price forecasting operation on the power management platform, then the user end power price forecasting operation authority identification data is output If the user has no authority, the user-side electricity price forecasting operation will be terminated directly.

[0023] Through the cooperation between the user-side identity information collection unit and the user-side electricity price forecast demand feature information collection unit, the power management platform is used to accurately collect the user-side identity information and the user-side electricity price forecast demand information, so as to provide reliable data support for accurately judging the user-side electricity price forecast operation authority and accurately predicting electricity prices; the electricity price forecast registered personnel identity information storage unit and the user-side electricity price forecast operation authority identification unit cooperate with each other, scientifically store the electricity price forecast registered personnel identity text parameters, combine the intelligent search algorithm with the user-side identity information, and intelligently identify the authority of the user-side to execute the electricity price forecast operation, so as to improve the security of the user-side electricity price forecast operation.

[0024] For further information, see Figure 1 - Figure 2 When the user has the authority, the user's historical monthly electricity price increase rate parameters and electricity consumption increase rate parameters are searched and processed based on the user's electricity price forecast demand feature text data, the user's identity text data, the historical monthly electricity price increase rate data, and the historical monthly electricity consumption increase rate data. The operation steps for generating the user's historical monthly electricity price increase rate data and the user's historical monthly electricity consumption increase rate data are as follows: S31, when the user-side power price forecasting operation authority identification data If authorized, establish a historical monthly electricity price increase rate data set , ;in Indicates The historical monthly electricity price increase rate data corresponding to the combination type of electricity price forecast demand characteristics, Indicates the maximum number of power price forecast demand feature combination types. The power price forecast demand feature combination type indicates the power price forecast demand type mainly composed of the name information of the administrative region where the user-side power price forecast is located, the power consumption field information where the user-side power price forecast is located, and the monthly range parameters of the historical power price records required for the user-side power price forecast; Establish a historical monthly electricity consumption increase rate data set , ;in Indicates the user's The data of the increase rate of electricity consumption in the past months, Indicates the maximum number of historical months on the user side; S32, user-side electricity price forecast demand characteristic text data Data collection of historical monthly electricity price increase rates Historical monthly electricity price increase rate data According to the keyword matching of power price forecast demand characteristics, search for the user-side power price forecast demand characteristics text data Corresponding historical monthly electricity price increase rate data , and generate a data set of the user-side historical monthly electricity price increase rate , execute to generate the user-side historical monthly electricity price increase rate data set The specific steps are as follows: S321, initialization, in the historical monthly electricity price increase rate data collection The electricity price increase rate is randomly updated in the search space to search for the location of the Tasmanian devil population. The electricity price increase rate search for the location of the Tasmanian devil is updated with the following formula: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals exist The position of the dimensional search space, that is, the increase rate of electricity price searches for Tasmanian devil individuals In the spatial dimension Historical monthly electricity price increase rate data collection The position in the search space, , Represents the historical monthly electricity price increase rate data set The lower and upper boundaries in the search space, Represents a random number in the interval [0,1]; S322, exploration phase, electricity price increase rate search Tasmanian devil in the historical monthly electricity price increase rate data set Search the search space to find the text data related to the demand characteristics of user-side electricity price forecast Matching historical monthly electricity price increase rate data Target carrion, electricity price increase rate search Tasmanian devil in the historical monthly electricity price increase rate data set Search space scans habitat areas to identify demand characteristics related to user-side electricity price forecasting text data Matching historical monthly electricity price increase rate data The behavior of rotting meat is similar to the algorithm search in the problem-solving space and the user-side electricity price forecast demand feature text data Matching historical monthly electricity price increase rate data The process of increasing the electricity price is as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months Search the search space for the position of the selected target carrion, Represents the rate of increase in electricity prices. Search for Tasmanian devil individuals in the historical monthly electricity price increase rate data set Select target carrion in the search space location, ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The maximum number of carrion to search; Based on the selected target carrion, the electricity price increase rate searches for Tasmanian devils in the historical monthly electricity price increase rate data set The new position in the search space is calculated, and the rate of increase in electricity price is used to search for the new position of the Tasmanian devil as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months The position before the update in the search space; Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months The updated position in the search space; and Respectively represent the data set of the increase rate of electricity price in the historical month The rate of increase in electricity price in the search space searches for carrion quality parameters of the location coordinates of Tasmanian devil individuals before and after the location update; S323, development stage, electricity price increase rate search Tasmanian devil in the historical monthly electricity price increase rate data set Search the search space to find the text data related to the demand characteristics of user-side electricity price forecast Matching historical monthly electricity price increase rate data The behavior of Tasmanian devils in attacking target prey has two stages. In the first stage, the Tasmanian devil searches for prey by scanning the historical monthly data set. Search the search space to find the text data related to the demand characteristics of user-side electricity price forecast Matching historical monthly electricity price increase rate data Target prey, select historical monthly electricity price increase rate data Target prey and attack historical monthly electricity price increase rate data Target prey; in the second stage, close to the historical monthly electricity price increase rate data After the target prey, the electricity price increase rate search Tasmanian devil chasing historical monthly electricity price increase rate data Target prey and prey Historical monthly electricity price increase rate data Target prey; Electricity price increase rate Searching Tasmanian devils to identify selected target prey behavior simulation formula is as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months Search the search space for the location of the selected target prey, Represents the rate of increase in electricity prices. Search for Tasmanian devil individuals in the historical monthly electricity price increase rate data set Target prey selected in search space location, ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals The maximum number of target prey to be searched; Based on the selected target prey, the Tasmanian devil is searched in the historical monthly electricity price increase rate data set. The new position in the search space is calculated, and the rate of increase in electricity price is used to search for the new position of the Tasmanian devil as follows: ,in Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months The position before the update in the search space; Indicates the rate of increase in electricity prices. Search for Tasmanian devil individuals Data collection on the increase rate of electricity prices in historical months The updated position in the search space; and Respectively represent the data set of the increase rate of electricity price in the historical month The rate of increase in electricity price in the search space is the target prey quality parameter for the position coordinates of the Tasmanian devil individuals before and after the position update; S324. When the algorithm meets the maximum number of iterations, the output is the text data of the power price forecast demand characteristics of the user end. All historical monthly electricity price increase rate data matched ; S325: All the historical monthly electricity price increase rate data output in step S324 are Generate a data set of the user's historical monthly electricity price increase rate through data identification ,in Indicates The historical monthly electricity price increase rate data of each user, Indicates Historical monthly electricity price increase rate data for each user; Similarly, the intelligent recognition algorithm in steps S321 to S325 is used to identify the user's identity text data. and user-side electricity price forecast demand characteristics text data Data collection of historical monthly electricity consumption increase rate Data on the monthly increase in electricity consumption in the past few years Search for user-side identity text data by matching identity features with keywords of power price forecast demand features and user-side electricity price forecast demand characteristics text data Corresponding historical monthly electricity consumption increase rate data , and generate a data set of the user's historical monthly electricity consumption increase rate ,in Indicates The historical monthly electricity consumption increase rate data of each user, Indicates Historical monthly electricity consumption increase rate data for each user.

[0025] The operation steps for performing numerical statistical processing of the power price increase rate parameters and power consumption increase rate parameters of the user-side forecast month according to the power price increase rate parameters and power consumption increase rate parameters of the user-side historical month to generate the power price increase rate data and power consumption increase rate data of the user-side forecast month are as follows: S41. Collect the historical monthly electricity price increase rate data of the user end Historical monthly electricity price increase rate data for medium-sized and large-scale users to Combine the mean formula to measure the average increase rate of the user's historical monthly electricity price and generate the user's predicted monthly electricity price increase rate data. ,in ; Similarly, the user-side historical monthly electricity consumption increase rate data is collected Historical monthly electricity consumption increase rate data for medium-sized users to Combined with the mean formula, the average measurement of the historical monthly electricity consumption increase rate at the user end is processed to generate the user end predicted monthly electricity consumption increase rate data ,in .

[0026] The current monthly electricity price data and the current monthly electricity consumption data of the user end are collected and the predicted monthly electricity price increase rate data and the predicted monthly electricity consumption increase rate data of the user end are used to perform numerical measurement processing on the electricity price parameters and electricity consumption parameters of the predicted month of the user end. The operation steps for generating the predicted monthly electricity price data and the predicted monthly electricity consumption data of the user end are as follows: S51, collect the electricity price parameters of the current month at the user end online through the power management platform and generate the electricity price data of the current month at the user end ,in The unit is yuan per kilowatt-hour; The power management platform collects the power consumption parameters of the user end in the current month online and generates the power consumption data of the user end in the current month ,in The unit is kilowatt-hour; S52, the current monthly electricity price data of the user end Monthly electricity price increase rate data predicted by the user side Perform numerical integral measurement processing to generate user-side predicted monthly electricity price data ,in , The unit is yuan per kilowatt-hour; The user's current monthly electricity consumption data Monthly electricity consumption increase rate data predicted by the user Perform numerical integral measurement processing to generate user-side predicted monthly power consumption data ,in , The unit is kilowatt-hour.

[0027] Through the cooperation of the historical monthly electricity price increase rate information storage unit and the user-side historical monthly electricity price increase rate search unit, the standard storage of historical monthly electricity price increase rate parameters is combined with the intelligent recognition algorithm and the user-side electricity price forecast demand feature text parameters to accurately search the user-side historical monthly electricity price increase rate parameters, so as to achieve efficient and accurate acquisition of the user-side historical electricity price change rate parameters; the historical monthly electricity consumption increase rate information storage unit and the user-side historical monthly electricity consumption increase rate search unit cooperate with each other to accurately store the historical monthly electricity consumption increase rate parameters and combine the intelligent recognition algorithm with the user-side electricity price forecast demand feature text parameters and the user-side identity text parameters to accurately search the user-side historical monthly electricity consumption increase rate parameters, so as to achieve efficient and accurate acquisition of the user-side historical electricity consumption change rate parameters; the user-side predicted monthly electricity price increase rate metering unit and the user-side predicted The monthly electricity consumption increase rate metering units cooperate with each other to scientifically analyze the user-side predicted monthly electricity price increase rate and electricity consumption increase rate parameters based on numerical analysis, and realize accurate statistics of the user-side predicted monthly electricity price increase rate and electricity consumption increase rate parameters; the user-side current month electricity price collection unit and the user-side current month electricity consumption collection unit cooperate with each other to accurately collect the user-side current month electricity price and electricity consumption parameters through the power management platform, and provide real data support for the scientific prediction of the user-side electricity price and electricity consumption parameters; the user-side predicted monthly electricity price metering unit and the user-side predicted monthly electricity consumption metering unit scientifically and accurately measure the user-side predicted monthly electricity price and electricity consumption parameters based on numerical analysis, realize convenient and efficient prediction of electricity price and electricity consumption at the user end, and improve the scientificity and quality of power consumption management at the user end.

[0028] For further information, see Figure 1 - Figure 2 , the electricity cost numerical measurement processing of the user-side forecast month is performed based on the electricity price parameters and electricity consumption parameters of the user-side forecast month, and the operation steps for generating the user-side forecast month electricity cost data are as follows: S61, forecast monthly electricity price data at the user end Forecast monthly electricity consumption data with the user side Combined with the price formula, the total price of electricity consumption in the user's predicted month is processed by product measurement to generate the user's predicted monthly electricity cost data. ,in , The unit is yuan.

[0029] The steps to construct the user-side power price forecast result data and perform the power price forecast result display operation are as follows: S71, user-side electricity price forecast demand characteristic text data , User-side forecast monthly electricity price data and user-side forecasted monthly electricity cost data Combine data to construct user-side electricity price forecast result data ; S72, the user-side power price forecast result data Feedback is pushed to the power management platform through the IoT communication network and displayed on the display screen.

[0030] Through the user-side predicted monthly electricity cost metering unit, the user-side predicted monthly electricity cost parameters are scientifically measured based on the user-side predicted monthly electricity price parameters, electricity consumption parameters and numerical analysis, so as to achieve intuitive and accurate prediction of the user-side electricity cost parameters and realize intelligent power consumption management at the user end; the user-side electricity price forecast result information display unit scientifically constructs the user-side electricity price forecast result information based on the user-side electricity price forecast demand information, electricity price forecast results, electricity consumption forecast results and electricity cost forecast, and cooperates with the Internet of Things communication network to transmit and feedback to the power management platform in a timely and efficient manner, and cooperates with the display screen for intuitive and visual feedback, so as to achieve efficient and clear output of electricity price forecast result information, and improve the intuitiveness and convenience of power consumption management at the user end. Example

[0031] See also Figure 1 - Figure 2 , an intelligent prediction system for electric power prices based on data analysis, used to implement an intelligent prediction method for electric power prices based on data analysis, the system includes a user-side electric power price prediction authority management module, a user-side electric power price and power consumption prediction module, and a user-side electric power cost prediction output module; The user-side power price forecasting authority management module includes a user-side identity information collection unit, a user-side power price forecasting demand characteristic information collection unit, a power price forecasting registered personnel identity information storage unit, and a user-side power price forecasting operation authority identification unit; The user-side identity information collection unit collects user-side identity text data through the power management platform; the user-side power price forecast demand feature information collection unit collects user-side power price forecast demand feature text data through the power management platform; the power price forecast registration personnel identity information storage unit is used to store the power price forecast registration personnel identity text data; the user-side power price forecast operation authority identification unit performs the power price forecast operation authority identification processing on the user side according to the user-side identity text data and the power price forecast registration personnel identity text data, and generates the user-side power price forecast operation authority identification data; The user-side electricity price and electricity consumption prediction module includes a historical monthly electricity price increase rate information storage unit, a user-side historical monthly electricity price increase rate search unit, a historical monthly electricity consumption increase rate information storage unit, a user-side historical monthly electricity consumption increase rate search unit, a user-side predicted monthly electricity price increase rate metering unit, a user-side predicted monthly electricity consumption increase rate metering unit, a user-side current monthly electricity price collection unit, a user-side current monthly electricity consumption collection unit, a user-side predicted monthly electricity price metering unit, and a user-side predicted monthly electricity consumption metering unit; The historical monthly electricity price increase rate information storage unit is used to store the historical monthly electricity price increase rate data; the user-side historical monthly electricity price increase rate search unit performs a user-side historical monthly electricity price increase rate parameter search process based on the user-side electricity price forecast demand feature text data and the historical monthly electricity price increase rate data to generate the user-side historical monthly electricity price increase rate data; the historical monthly electricity consumption increase rate information storage unit is used to store the historical monthly electricity consumption increase rate data; the user-side historical monthly electricity consumption increase rate search unit performs a user-side historical monthly electricity consumption increase rate parameter search process based on the user-side electricity price forecast demand feature text data, the user-side identity text data and the historical monthly electricity consumption increase rate data to generate the user-side historical monthly electricity consumption increase rate data; the user-side predicted monthly electricity price increase rate metering unit performs a user-side predicted monthly electricity price increase rate parameter numerical statistical processing based on the user-side historical monthly electricity price increase rate parameters to generate the user-side predicted monthly electricity price increase rate data. Price increase rate data; the user-side predicted monthly electricity consumption increase rate metering unit performs numerical statistical processing on the parameters of the electricity price increase rate of the user-side predicted month according to the parameters of the electricity consumption increase rate of the user-side historical months, and generates the user-side predicted monthly electricity consumption increase rate data; the user-side current month electricity price collection unit collects the user-side current month electricity price data through the power management platform; the user-side current month electricity consumption collection unit collects the user-side current month electricity consumption data through the power management platform; the user-side predicted monthly electricity price metering unit performs numerical metering processing on the electricity price parameters of the user-side predicted month according to the user-side current month electricity price data and the user-side predicted monthly electricity price increase rate data, and generates the user-side predicted monthly electricity price data; the user-side predicted monthly electricity consumption metering unit performs numerical metering processing on the electricity consumption parameters of the user-side predicted month according to the user-side current month electricity consumption data and the user-side predicted monthly electricity consumption increase rate data, and generates the user-side predicted monthly electricity consumption data; The user-side electricity price and electricity consumption prediction module includes a user-side predicted monthly electricity cost metering unit and a user-side electricity price prediction result information display unit; The user-side predicted monthly electricity cost metering unit performs numerical metering processing of the user-side predicted monthly electricity cost based on the user-side predicted monthly electricity price parameters and electricity consumption parameters, and generates the user-side predicted monthly electricity cost data; the user-side electricity price forecast result information display unit is used to construct the user-side electricity price forecast result data and perform the electricity price forecast result display operation.

[0032] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent prediction method for power prices based on data analysis, characterized in that: The method comprises the following steps: S1. Collecting user-side identity text data and user-side power price forecast demand feature text data; S2, performing authority identification processing for the user to perform the power price forecasting operation based on the user-side identity text data and the power price forecasting registration personnel identity text data, and generating user-side power price forecasting operation authority identification data, and when there is no authority, ending the current user-side power price forecasting operation; S3. When the user has the authority, based on the user-side power price forecast demand feature text data, the user-side identity text data, the historical monthly power price increase rate data, and the historical monthly power consumption increase rate data, respectively, the user-side power price increase rate parameters and the power consumption increase rate parameters of the historical months are searched and processed to generate the user-side historical monthly power price increase rate data and the user-side historical monthly power consumption increase rate data; S4, performing numerical statistical processing on the power price increase rate parameters and power consumption increase rate parameters of the user-side predicted month according to the power price increase rate parameters and power consumption increase rate parameters of the user-side historical month, and generating the power price increase rate data and power consumption increase rate data of the user-side predicted month; S5, collecting the current monthly electricity price data and the current monthly electricity consumption data of the user end, and performing numerical measurement processing on the electricity price parameters and electricity consumption parameters of the predicted month of the user end with the predicted monthly electricity price increase rate data and the predicted monthly electricity consumption increase rate data of the user end, to generate the predicted monthly electricity price data and the predicted monthly electricity consumption data of the user end; S6. Perform numerical measurement processing of the power cost of the user-side predicted month based on the power price parameters and power consumption parameters of the user-side predicted month, and generate power cost data of the user-side predicted month; S7. Construct the user-side power price forecast result data and execute the power price forecast result display operation.

2. The method for intelligent prediction of electric power prices based on data analysis according to claim 1 is characterized in that: The S1 comprises the following steps: S11. The user enters personal or corporate identity text information online through the power management platform and generates user-side identity text data Collect the user-side electricity price forecast demand feature text information online through the power management platform and generate the user-side electricity price forecast demand feature text data .

3. The method for intelligent prediction of electric power prices based on data analysis according to claim 2 is characterized in that: The S2 comprises the following steps: S21. Establishing a text data set of the identity of the personnel registered for power price forecasting , ;in Indicates The identity text data of the person who registered for electricity price forecasting, Indicates the maximum number of persons registered for power price forecasting, wherein the identity text data of persons registered for power price forecasting indicates the identity information of persons registered for power price forecasting who have been registered and backed up on the power management platform; S22, using the BERT language model algorithm to With the As stated in Perform identity text data matching and generate user-side power price forecasting operation authority identification data based on the identity text data matching results ; when and If the identity text data is matched successfully, the user-side power price forecasting operation authority identification data will be output. To have authority; when and If the identity text data is not matched successfully, the user-side power price forecasting operation authority identification data is output. If the user has no authority, the user-side electricity price forecasting operation will be terminated directly.

4. The method for intelligent prediction of electric power prices based on data analysis according to claim 3 is characterized in that: The S3 comprises the following steps: S31, when the user-side power price forecasting operation authority identification data If authorized, establish a historical monthly electricity price increase rate data set , ;in Indicates The historical monthly electricity price increase rate data corresponding to the combination type of electricity price forecast demand characteristics, Indicates the maximum number of combination types of demand characteristics for power price forecasting; Establish a historical monthly electricity consumption increase rate data set , ;in Indicates the user's The data of the increase rate of electricity consumption in the past months, Indicates the maximum number of historical months on the user side; S32, the With the As stated in According to the power price forecast demand characteristics keyword matching, search for the The corresponding , and generate a data set of the user-side historical monthly electricity price increase rate , execute to generate the user-side historical monthly electricity price increase rate data set The specific steps are as follows: S321, initialization, in the Randomly update the rate of increase in electricity prices in the search space to search for the location of the Tasmanian devil population; S322, exploration phase, the power price increase rate searches for Tasmanian devils in the Search the search space for Matching the Targeting carrion for food, electricity prices increase the rate of search for Tasmanian devils in the Search space scans habitat areas to identify areas that are consistent with the Matching the The behavior of the decaying meat is similar to the algorithmic search in the problem space and the Matching the process; based on the selected target carrion, the electricity price increases the rate of search for Tasmanian devils in the The new position in the search space of is calculated; S323, development stage, the rate of increase in electricity price, search for Tasmanian devil in the Search the search space for Matching the The behavior of the Tasmanian devil in the process of attacking the target prey has two stages. In the first stage, the Tasmanian devil searches for the target prey by scanning the Search the search space for Matching the Target prey, select the Target prey and attack the target prey; in the second stage, approaching the After targeting prey, electricity prices increase the rate of search for Tasmanian devils chasing the Target prey and prey on the Target prey; Based on the selected target prey, the power price increases the rate of searching for Tasmanian devils in the The new position in the search space of is calculated; S324, when the algorithm meets the maximum number of iterations, the output is the same as the Matches all of the ; S325: All the historical monthly electricity price increase rate data output in step S324 are Generate a data set of the user's historical monthly electricity price increase rate through data identification ,in Indicates The historical monthly electricity price increase rate data of each user, Indicates Historical monthly electricity price increase rate data for each user; Similarly, the intelligent recognition algorithm in steps S321 to S325 is used to and stated With the As stated in According to the identity characteristics and power price forecast demand characteristics keyword matching, search for the and stated The corresponding , and generate a data set of the user's historical monthly electricity consumption increase rate ,in Indicates The historical monthly electricity consumption increase rate data of each user, Indicates Historical monthly electricity consumption increase rate data for each user.

5. The method for intelligent prediction of electric power prices based on data analysis according to claim 4 is characterized in that: The S4 comprises the following steps: S41, the As stated in to Combine the mean formula to measure the average increase rate of the user's historical monthly electricity price and generate the user's predicted monthly electricity price increase rate data. ; Similarly, As stated in to Combined with the mean formula, the average measurement of the historical monthly electricity consumption increase rate at the user end is processed to generate the user end predicted monthly electricity consumption increase rate data .

6. The method for intelligent prediction of electric power prices based on data analysis according to claim 5 is characterized by: The S5 comprises the following steps: S51, collect the electricity price parameters of the current month at the user end online through the power management platform and generate the electricity price data of the current month at the user end ,in The unit is yuan per kilowatt-hour; The power management platform collects the power consumption parameters of the user end in the current month online and generates the power consumption data of the user end in the current month ,in The unit is kilowatt-hour; S52, the With the Perform numerical integral measurement processing to generate user-side predicted monthly electricity price data , The unit is yuan per kilowatt-hour; The With the Perform numerical integral measurement processing to generate user-side predicted monthly power consumption data , The unit is kilowatt-hour.

7. The method for intelligent prediction of electric power prices based on data analysis according to claim 6 is characterized by: The S6 comprises the following steps: S61, the With the Combined with the price formula, the total price of electricity consumption in the user's predicted month is processed by product measurement to generate the user's predicted monthly electricity cost data. ,in The unit is yuan.

8. The method for intelligent prediction of electric power prices based on data analysis according to claim 7 is characterized in that: The S7 comprises the following steps: S71, the , and stated Combine data to construct user-side electricity price forecast result data ; S72, the Feedback is pushed to the power management platform through the IoT communication network and displayed on the display screen.

9. An intelligent prediction system for electric power prices based on data analysis, used to implement the intelligent prediction method for electric power prices based on data analysis as claimed in any one of claims 1 to 8, characterized in that: The system comprises a user-side power price prediction authority management module, a user-side power price and power consumption prediction module, and a user-side power cost prediction output module.

Images