A power price prediction method and device

Abstract

The application discloses a power price prediction method and device, which can acquire all electric appliance plans in a block area; generates a total demand load curve corresponding to the block area according to each electric appliance plan, and generates a power supply plan according to the total demand load curve; generates a power price plan according to the total demand load curve and the power supply plan; calculates a predicted electricity charge corresponding to each user based on the power price plan and the electric appliance plan corresponding to each user, and issues the power price plan and each predicted electricity charge to a terminal of the corresponding user; updates the total demand load curve according to the latest uploaded electric appliance plan of one or more users, returns to the step of generating the power supply plan corresponding to the block area according to the total demand load curve until the power price plan converges; it can be seen that the application can combine the energy consumption scheduling game of the demand side and the dynamic economic scheduling game of the supply side, further improve the accuracy of the predicted power price plan, and thus improve the practicability of the power price plan.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and more specifically, to a method and apparatus for predicting electricity prices. Background Technology

[0002] In the power grid, traditional electricity price forecasting methods rely on historical electricity price sequences within a specific area. However, during grid operation, various error scenarios exist, such as significant changes in the electricity consumption behavior of multiple users, leading to substantial price fluctuations. The diversity and high frequency of these error scenarios result in significant deviations between the predicted electricity prices and actual conditions, rendering the predicted prices unreliable. Summary of the Invention

[0003] In view of this, this application provides an electricity price prediction method and apparatus to address the shortcomings of the poor practicality of the predicted electricity prices in the prior art.

[0004] To achieve the above objectives, the following solution is proposed:

[0005] A method for predicting electricity prices, comprising:

[0006] Get the appliance plans for all users in the area;

[0007] Based on the electrical appliance plans, generate the total demand load curve for the area, and generate the power supply plan for the area based on the total demand load curve.

[0008] Based on the total demand load curve and the power supply plan, an electricity price plan is generated;

[0009] Based on the electricity price plan and the appliance plan for each user, the predicted electricity cost for each user is calculated, and the electricity price plan and each predicted electricity cost are sent to the corresponding user's terminal so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan;

[0010] Based on the latest appliance plans uploaded by one or more users, the total demand load curve is updated, and the process returns to the step of generating the power supply plan corresponding to the area based on the total demand load curve, until the electricity price plan converges.

[0011] Optionally, based on each of the aforementioned electrical appliance plans, a total demand load curve corresponding to the area is generated, including:

[0012] For each user, with the goal of minimizing the user's electricity cost, the user's demand load is constrained and compared in each time period based on the user's appliance plan, thus forming the corresponding demand load curve for the user;

[0013] Summarize the demand load curves of each user to form the total demand load curve corresponding to the area.

[0014] Optionally, the step of constraining and comparing the user's demand load for each time period based on the user's electrical appliance plan includes:

[0015] Based on the user's appliance plan, the operating status of multiple appliances for the user in each time period is constrained and compared.

[0016] Optionally, generating the power supply plan corresponding to the area based on the total demand load curve includes:

[0017] With the goal of minimizing electricity costs, the power supply of each generator set at each time period is constrained and compared based on the total demand load curve to form the power supply plan corresponding to the area.

[0018] Optionally, the step of constraining and comparing the power supply of each generator unit in each time period based on the total demand load curve includes:

[0019] Based on the total demand load curve, as well as the power generation range, ramping constraints, and energy storage constraints of each generator set, the power supply of each generator set at each time period is constrained and compared.

[0020] Optionally, the total demand load curve includes the total demand load of the area in each time period; the power supply plan includes the power generation capacity of the area in each time period;

[0021] The step of generating an electricity price plan based on the total demand load curve and the power supply plan includes:

[0022] Based on the power supply plan, determine the power generation cost for each time period;

[0023] Compare total demand load with power generation capacity during the same period;

[0024] For each time period, when the total demand load of that time period is less than the power generation capacity of that time period, the target electricity price for that time period is calculated based on the power generation cost and the power generation capacity of that time period.

[0025] For each time period, if the total demand load in that time period is not less than the power generation capacity in that time period, the target electricity price for that time period is calculated based on the power generation cost and the total demand load in that time period.

[0026] The target electricity prices for each time period are summarized to form an electricity price plan.

[0027] Optionally, updating the total demand load curve based on the latest appliance plans uploaded by one or more users includes:

[0028] Users who upload new appliance plans after the latest electricity price plan is issued will be designated as first users, and the latest appliance plan uploaded by each first user will be used as their corresponding first appliance plan.

[0029] All users in the area other than the first user are designated as the second user;

[0030] For each second user, predict the load adjustment behavior of the second user, and generate a second electrical appliance plan corresponding to the second user based on the load adjustment behavior and the latest electrical appliance plan corresponding to the second user.

[0031] The total demand load curve is updated based on each first electrical appliance plan and each second electrical appliance plan.

[0032] Optionally, predicting the load adjustment behavior of the second user includes:

[0033] Determine the user type of the second user and obtain the load adjustment model that matches the user type;

[0034] The latest electricity price plan and the latest appliance plan of the second user are input into the load adjustment model to obtain the load adjustment behavior corresponding to the second user output by the load adjustment model.

[0035] Optionally, obtaining the load adjustment model matching the user type includes:

[0036] Build the initial model;

[0037] Multiple users belonging to this user type will be used as training users respectively;

[0038] Multiple historical load adjustment behaviors of each training user are obtained, and samples corresponding to each historical load adjustment behavior are determined. Each sample includes the historical electricity price plan, the first historical appliance plan, and the second historical appliance plan corresponding to the historical load adjustment behavior. The first historical appliance plan is adjusted by the corresponding historical load adjustment behavior to form the second historical appliance plan.

[0039] The initial model is trained sequentially using each sample and its corresponding historical load adjustment behavior until the initial model meets the preset training stopping condition. The final initial model is then used as the load adjustment model matching the user type.

[0040] An electricity price forecasting device, comprising:

[0041] The appliance planning acquisition module is used to acquire the appliance plans corresponding to all users in the area;

[0042] The curve generation module is used to generate the total demand load curve corresponding to the area based on each of the electrical appliance plans.

[0043] The power supply plan generation module is used to generate a power supply plan corresponding to the area based on the total demand load curve.

[0044] The electricity price plan generation module is used to generate an electricity price plan based on the total demand load curve and the power supply plan;

[0045] The predicted electricity cost calculation module is used to calculate the predicted electricity cost for each user based on the electricity price plan and the appliance plan corresponding to each user, and to send the electricity price plan and each predicted electricity cost to the terminal of the corresponding user so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan;

[0046] The electricity price plan update module is used to update the total demand load curve based on the latest appliance plans uploaded by one or more users, and then call the power supply plan generation module and its subsequent modules until the electricity price plan converges.

[0047] As can be seen from the above technical solution, the electricity price forecasting method provided in this application can obtain the appliance plans corresponding to all users in a region; generate the total demand load curve corresponding to the region based on each appliance plan, and generate the power supply plan corresponding to the region based on the total demand load curve; thus, this application can generate an electricity price plan based on the appliance plans on the demand side and the power supply plan on the supply side; subsequently, based on the electricity price plan and the appliance plans corresponding to each user, the predicted electricity cost for each user can be calculated, and the electricity price plan and each predicted electricity cost can be sent to the terminal of the corresponding user so that the user can use the predicted electricity cost. The application adjusts the appliance planning based on the electricity price plan; updates the total demand load curve based on the latest appliance planning uploaded by one or more users, and returns to the step of generating the power supply plan corresponding to the area based on the total demand load curve, until the electricity price plan converges. Thus, this application completes the prediction of the electricity price plan through the interaction of the electricity price plan and the appliance planning, combined with the energy consumption scheduling game on the demand side and the dynamic economic scheduling game on the supply side. Simultaneously, the appliance planning used in this application is obtained through adjustments by users, which can further improve the reliability of the appliance planning, thereby ensuring the reliability and practicality of the electricity price plan proposed in this application. It is evident that this application can combine the energy consumption scheduling game on the demand side and the dynamic economic scheduling game on the supply side to further improve the accuracy of the predicted electricity price plan, thereby improving the practicality of the electricity price plan proposed in this application. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0049] Figure 1 This is a flowchart of an electricity price forecasting method disclosed in an embodiment of this application;

[0050] Figure 2 This is a structural block diagram of an electricity price forecasting device disclosed in an embodiment of this application;

[0051] Figure 3 This is a hardware structure block diagram of an electricity price forecasting device disclosed in an embodiment of this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] Next, combine Figure 1 The electricity price forecasting method described in this application is detailed, including the following steps:

[0054] Step S1: Obtain the appliance plans for all users in the area.

[0055] Specifically, each appliance plan can include the usage time periods of multiple appliances for the corresponding user and the appliance type of each appliance, and may also include the indoor temperature range.

[0056] The type of an appliance can indicate whether it can be charged and used, and whether its operating status can be adjusted. For example, there are generally four types of appliances: one type is an appliance whose operating status cannot be adjusted but can store energy; another type is an appliance whose operating status can be adjusted but cannot store energy, such as an air conditioner; another type is an appliance whose operating status cannot be adjusted and cannot store energy; and yet another type is an appliance whose operating status can be adjusted and can store energy.

[0057] It can receive appliance planning data uploaded by each smart meter in the area. Each smart meter can determine the energy consumption of the corresponding user at different times, so as to determine the operating status of each appliance at each time period.

[0058] With user authorization, it can interact with the smart meter via fiber optic wireless or high-speed local area network.

[0059] Step S2: Generate the total demand load curve corresponding to the area based on each of the electrical appliance plans.

[0060] Specifically, based on the various electrical appliance plans, the total demand load corresponding to each time period can be determined, and the total demand load of each time period forms the total demand load curve.

[0061] Step S3: Generate the power supply plan corresponding to the area based on the total demand load curve.

[0062] Specifically, the power required for a region in each time period can be determined based on the total demand load curve, and the power required in each time period forms a power supply plan.

[0063] The power supply plan may include the power output of each generator set in the area at each time period, or it may include the power output of other areas that need to be accessed.

[0064] Step S4: Generate an electricity price plan based on the total demand load curve and the power supply plan.

[0065] Specifically, an electricity price plan can be generated based on the total demand load for each time period in the total demand load curve and the power supply for each time period in the power supply plan.

[0066] Step S5: Based on the electricity price plan and the appliance plan corresponding to each user, calculate the predicted electricity cost for each user, and send the electricity price plan and each predicted electricity cost to the corresponding user's terminal.

[0067] Specifically, the projected electricity cost for each user can be calculated based on the target electricity price for each time period in the electricity pricing plan and the planning for each appliance.

[0068] The corresponding predicted electricity costs and electricity price plans can be sent to the smart meters of the corresponding users so that the users can adjust their appliance plans based on the predicted electricity costs and electricity price plans.

[0069] Step S6: Update the total demand load curve based on the latest appliance plans uploaded by one or more users, and return to step S3 until the electricity price plan converges.

[0070] Specifically, some time after the electricity price plan is issued, the total demand load curve can be updated based on the latest plans for each appliance, and the process can return to step S3 to update the electricity price plan until the electricity price plan converges.

[0071] As can be seen from the above technical solutions, the electricity price forecasting method provided in this application can obtain the appliance plans corresponding to all users in a region; generate a total demand load curve corresponding to the region based on each appliance plan, and generate a power supply plan corresponding to the region based on the total demand load curve; thus, this application can generate a supply-side power supply plan based on the demand-side appliance plans; generate an electricity price plan based on the total demand load curve and the power supply plan; thus, this application can generate an electricity price plan based on the demand-side appliance plans and the supply-side power supply plan; calculate the predicted electricity cost for each user based on the electricity price plan and the appliance plans corresponding to each user, and combine the electricity price plan and the predicted electricity cost for each user. Electricity charges are distributed to the corresponding user's terminal so that the user can adjust their appliance planning based on the predicted electricity charges and electricity price plan. Based on the latest appliance planning uploaded by one or more users, the total demand load curve is updated, and the process returns to generate the corresponding power supply plan for the area based on the total demand load curve, continuing until the electricity price plan converges. Thus, this application, through the interaction of the electricity price plan and appliance planning, combined with demand-side energy consumption scheduling game theory and supply-side dynamic economic scheduling game theory, completes the prediction of the electricity price plan. Simultaneously, the appliance planning used in this application is obtained through user adjustments, which further improves the reliability of the appliance planning, thereby ensuring the reliability and practicality of the proposed electricity price plan. Therefore, this application can combine demand-side energy consumption scheduling game theory and supply-side dynamic economic scheduling game theory to further improve the accuracy of the predicted electricity price plan, thereby improving the practicality of the electricity price plan proposed in this application.

[0072] In addition, the predicted electricity charges for each user in this application are only sent to the corresponding user, thus ensuring the information security of each user.

[0073] In some embodiments of this application, the process of step S2, generating the total demand load curve corresponding to the area based on each of the electrical appliance plans, is described in detail below:

[0074] S20. For each user, with the goal of minimizing the user's electricity cost, constrain and compare the user's demand load for each time period based on the user's appliance plan to form the corresponding demand load curve for the user.

[0075] Specifically, in the process of calculating the demand load curve for each user, the goal can be to minimize the user's electricity cost. Based on the corresponding appliance plan, the user's demand load for each time period is constrained and compared. The demand load for each time period corresponding to the minimum electricity cost forms the user's demand load curve.

[0076] S21. Summarize the demand load curves of each user to form the total demand load curve corresponding to the area.

[0077] Specifically, the demand load of each user in the same time period can be added together to obtain the total demand load for each time period, and the total demand load for each time period forms the total demand load curve.

[0078] As can be seen from the above technical solution, this embodiment provides an optional method for generating a total demand load curve. This method can further reduce the electricity costs for individual users and improve the practicality of electricity pricing plans.

[0079] In some embodiments of this application, step S20, which involves constraining and comparing the user's demand load for each time period based on the user's electrical appliance plan with the goal of minimizing the user's electricity cost, and forming the corresponding demand load curve for that user, is described in detail below:

[0080] S200. For each user, with the goal of minimizing the user's electricity cost, based on the user's corresponding appliance plan, the operating status of multiple appliances of the user in each time period is constrained and compared to form the user's corresponding demand load curve.

[0081] Specifically, each appliance can have multiple different operating states. At the same time, the same appliance can only have one operating state. Different appliances have different operating states, and the operating state can represent the energy consumption of the corresponding appliance at the corresponding time period.

[0082] For each user, with the goal of minimizing the user's electricity cost, the operating status of multiple appliances for each user in each time period is constrained and compared based on the usage time of each appliance in the user's appliance plan, the appliance type of each appliance, the load demand of each appliance in each operating state, the charging and discharging efficiency of each rechargeable appliance, and the indoor temperature requirements, thus forming the user's corresponding demand load curve.

[0083] One approach is to use a demand load curve adjustment model to minimize the user's electricity costs. This model involves constraining and comparing the operating states of multiple appliances for the user in each time period based on the user's appliance plan, the appliance type, the load demand of each appliance in each operating state, the charging and discharging efficiency of rechargeable appliances, and the indoor temperature requirements. This results in the formation of the user's corresponding demand load curve.

[0084] Demand load adjustment models can include the following functions:

[0085]

[0086]

[0087]

[0088]

[0089]

[0090]

[0091]

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099] Among them, C h Forecasted electricity charges for the corresponding users; C t P represents the target electricity price at time t. t net Net energy consumption; Δt is the time slot duration; A UI All electrical appliances involved in the electrical appliance planning; 'a' represents the electrical appliances used by the corresponding user; x a,t P represents the operating state of appliance a at time t. t c P is the charging power at time t; t d Power supply for energy storage; P a,t P represents the energy consumption of appliance a at time t. t local The photovoltaic power supply capacity of the area; Γ={1,2,3,4,...,...T} represents the different time periods within a day; v a,t For the usage period of appliance a in the electrical appliance planning; z a The usage duration of appliance a in the electrical appliance planning; s a,t P is a decision variable used to maintain the operating state of appliance a and prevent appliance a from operating more than once during the scheduling period; t d The discharge power at time t; SOC t State of charge at time t; SOC t-1 The charging state at time t-1; ηc For charging efficiency; E ESS η is the maximum capacity of the energy storage unit. d For discharge efficiency; SOC min Minimum charging power; SOC max R is the maximum charging power. c For charging rate; U t R represents the total voltage of the user at time t; d Discharge rate; PDT t This represents the demand load threshold; Γ AC For each time period involved in the corresponding electrical appliance planning; T min The minimum indoor temperature in the electrical appliance planning; T max P represents the maximum indoor temperature in the electrical appliance design; t local,av P represents the maximum power generation capacity of the new energy generating units in the area. a max T represents the maximum energy consumption of appliance a; t in Let be the indoor temperature at time t; P is the indoor temperature at time t-1; t fixed The energy consumption of electrical appliances whose operating status cannot be adjusted and which cannot store energy; P a Let φ be the energy consumption of appliance a; φ and ψ are environmental parameters representing indoor temperature conditions. Let A be the predicted outdoor temperature at time t-1; r A collection of electrical appliances whose operating status can be adjusted.

[0100] As can be seen from the above technical solution, this application provides an optional method for adjusting the demand load curve of each user. Through the above method, the demand load curve can be constrained by electricity costs and appliance planning, so as to minimize the user's electricity costs while meeting the appliance planning requirements. This can further improve the practicality of this application and meet user needs.

[0101] In some embodiments of this application, the process of step S3, generating a power supply plan corresponding to the area based on the total demand load curve, is described in detail as follows:

[0102] S30. With the goal of minimizing electricity costs, constrain and compare the power supply of each generator set at each time period based on the total demand load curve to form the power supply plan corresponding to the area.

[0103] Specifically, in the process of generating a power supply plan, with the goal of minimizing electricity costs, the power supply power for each time period is constrained and compared based on the total demand load for each time period to obtain the power supply power for each time period, and the power supply power for each time period forms the power supply plan.

[0104] As can be seen from the above technical solution, this embodiment provides an optional way to generate power supply plans. By using the above method, the power cost can be reduced while meeting the demand load of each time period as much as possible, thus providing economic benefits to the power grid.

[0105] In some embodiments of this application, the process of step S30, which aims to minimize electricity costs by constraining and comparing the power supply of each generator set at each time period based on the total demand load curve to form a power supply plan for the corresponding area, is described in detail below:

[0106] S300. With the goal of minimizing electricity costs, the power supply of each generator set at each time period is constrained and compared based on the total demand load curve, the power generation range of each generator set, ramping constraints, and energy storage constraints, to form the power supply plan corresponding to the area.

[0107] Specifically, generator sets can include thermal power units and new energy units. Different types of generator sets may have different power generation ranges, ramping constraints, landslide constraints, and energy storage constraints. New energy units are more affected by the environment, and their power generation range can be obtained based on historical environmental sequences and historical power generation sequences.

[0108] The power cost adjustment model can be used to minimize power costs. Based on the total demand load curve, as well as the power generation range, ramping constraints, and energy storage constraints of each generator set, the power supply power of each generator set in each time period is constrained and compared to form the power supply plan corresponding to the area.

[0109] The electricity cost adjustment model can include the following functions:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116] In the formula, C SS For power generation cost; g is the thermal power unit; G is all the generator units included in the area; a g b g and c g P is the cost coefficient for thermal power unit g; g,t P is the power generation capacity of thermal power unit g at time t; t so P represents the power generation capacity of the new energy unit at time t. t so,av Let t be the maximum power output of the new energy generating unit. Let t be the total demand load; This represents the minimum power generation limit for thermal power unit g; P represents the maximum power generation limit of thermal power unit g; g,t-1 Let g be the power generation capacity of thermal power unit g at time t-1; For the ramping constraint of thermal power unit g; Let h be the landslide constraint for thermal power unit g; h be a single user; and H be the set of all users.

[0117] New energy units can include photovoltaic (PV) generator sets, and a PV model can be shown below:

[0118]

[0119]

[0120]

[0121] In the formula, P t (solar,local),av is the maximum power generation limit of the photovoltaic generator; K is the normalization constant; f(d) is used to calculate available solar energy based on geographical location; g(t) is used to calculate available solar energy based on sunrise and sunset times; Latitude; θ is the tilt angle; θ is the equatorial angle; t0 is the midpoint time; t sunset For sunset time or tsunami impact time; t sunrise d represents sunrise time or tsunami rise time; d represents day d; D represents the set of days; F d,t Let be the cloud cover rate at time t on day d; σ is a constant.

[0122] As can be seen from the above technical solution, this embodiment provides an optional method for generating electricity price plans while ensuring the minimum electricity cost. The above method can ensure that the total demand load in each time period is met as much as possible while reducing electricity costs.

[0123] In some embodiments of this application, the process of generating an electricity price plan based on the total demand load curve and the power supply plan is described in detail, and the steps are as follows:

[0124] S40. Determine the power generation cost for each time period according to the power supply plan.

[0125] Specifically, the power generation cost for each time period can be calculated based on the power generation capacity of each generator unit in each time period of the power supply plan.

[0126] S41. Compare the total demand load with the power generation capacity during the same period.

[0127] Specifically, for each time period, the total demand load of that time period can be compared with the power generation of that time period. If the total demand load of that time period is less than the power generation of that time period, step S42 is executed. If the total demand load of that time period is not less than the power generation of that time period, step S43 is executed.

[0128] S42. For each time period, when the total demand load of that time period is less than the power generation of that time period, calculate the target electricity price for that time period based on the power generation cost and the power generation of that time period.

[0129] Specifically, when the total demand load during a given period is less than the power generation during that period, the target electricity price can be the product of the profit coefficients, where the first ratio can be the ratio between the power generation cost and the power generation during that period.

[0130] S43. For each time period, if the total demand load of that time period is not less than the power generation capacity of that time period, calculate the target electricity price for that time period based on the power generation cost and the total demand load of that time period.

[0131] Specifically, when the total demand load during a given period is not less than the power generation capacity during that period, the target electricity price can be the product of a second ratio and a profitability coefficient, where the second ratio can be the ratio between the power generation cost during that period and the total demand load during that period.

[0132] S44. Summarize the target electricity prices for each time period to form an electricity price plan.

[0133] Specifically, the target electricity prices for each time period can be aggregated to form an electricity price plan.

[0134] Considering only the power generation cost of thermal power units, the target electricity price for each time period can be easily calculated using the following function:

[0135]

[0136]

[0137] In the formula, M t Let be the target electricity price at time t; α be the profit coefficient; β be a preset adjustment coefficient used to increase the profit range; C SS C represents the total cost of electricity generation. t SS Let C be the cost of generating electricity at time t; t The operating cost at time t; d t Let t be the total demand load at time t.

[0138] As can be seen from the above technical solution, this embodiment provides an optional method for calculating electricity price plans. Through the above method, electricity price calculation can be completed by comprehensively considering power generation costs, power supply plans and total demand load, which further improves the reliability of the electricity price plan of this application.

[0139] In some embodiments of this application, the process of updating the total demand load curve based on the latest appliance plans uploaded by one or more users is described in detail, and the steps are as follows:

[0140] S60. After the latest electricity price plan is issued, users who upload new appliance plans are identified as first users, and the latest appliance plan uploaded by each first user is taken as their corresponding first appliance plan.

[0141] Specifically, after the latest electricity price plan is issued, multiple users' appliance plans can be received; after a preset time, the user who responds to the latest electricity price plan can be identified as the first user, and the appliance plan uploaded by the first user in response to the latest electricity price plan can be identified as the first appliance plan corresponding to the first user.

[0142] S61. Identify all users in the area other than the first user as the second user.

[0143] Specifically, all users other than the first user can be designated as the second user.

[0144] S62. For each second user, predict the load adjustment behavior of the second user, and generate a second electrical appliance plan corresponding to the second user based on the load adjustment behavior and the latest electrical appliance plan corresponding to the second user.

[0145] Specifically, the load adjustment behavior corresponding to each second user can be predicted, and the latest electrical appliance plan for the corresponding second user can be adjusted according to each load adjustment behavior to form the second electrical appliance plan for that second user.

[0146] Furthermore, there is a possibility that the second user may not adjust the latest electrical appliance plan. In this case, the load adjustment behavior can be to not adjust the latest electrical appliance plan, and the latest electrical appliance plan can be directly used as the second user's second electrical appliance plan.

[0147] S63. Update the total demand load curve based on each first electrical appliance plan and each second electrical appliance plan.

[0148] Specifically, for each first user, with the goal of minimizing the first user's electricity cost, the demand load of the first user in each time period is constrained and compared according to the first user's first appliance plan, and a new demand load curve corresponding to the first user is formed.

[0149] For each second user, with the goal of minimizing the second user's electricity cost, the demand load of the second user in each time period is constrained and compared according to the second user's second appliance plan, forming a new demand load curve for the second user;

[0150] The various new demand load curves are then combined to form a new aggregate demand load curve.

[0151] As can be seen from the above technical solution, this embodiment provides an optional method for updating the total demand load curve. By using the above method, waiting time can be reduced and the efficiency of this application can be further improved.

[0152] In some embodiments of this application, the process of predicting the load adjustment behavior of the second user in step S62 is described in detail, and the steps are as follows:

[0153] S620. Determine the user type of the second user and obtain the load adjustment model that matches the user type.

[0154] Specifically, users in the area can be pre-classified to form multiple user types, and a load adjustment model matching each user type can be established.

[0155] You can call or train a load adjustment model that matches the user type.

[0156] S621. Input the latest electricity price plan and the latest electrical appliance plan of the second user into the load adjustment model to obtain the load adjustment behavior corresponding to the second user output by the load adjustment model.

[0157] Specifically, the latest electricity price plan and the latest appliance plan can be input into the load adjustment model. Based on the appliance plan and the electricity price plan, the load adjustment model can calculate the predicted electricity cost and determine the load adjustment behavior corresponding to the second user based on the predicted electricity cost and appliance plan.

[0158] As can be seen from the above technical solution, this embodiment provides an optional method for determining load adjustment behavior, which can further improve the reliability of this application.

[0159] In some embodiments of this application, the process of obtaining the load adjustment model matching the user type in step S620 is described in detail, and the steps are as follows:

[0160] S6200, Build the initial model.

[0161] Specifically, it is possible to obtain a pre-trained initial model.

[0162] S6201. Select multiple users belonging to this user type as training users respectively.

[0163] Specifically, multiple users corresponding to this user type can be selected and used as training users.

[0164] S6202. Obtain multiple historical load adjustment behaviors for each training user and determine the sample corresponding to each historical load adjustment behavior. Each sample includes the historical electricity price plan, the first historical appliance plan, and the second historical appliance plan corresponding to the historical load adjustment behavior. The first historical appliance plan is adjusted by the corresponding historical load adjustment behavior to form the second historical appliance plan.

[0165] Specifically, it is possible to obtain multiple historical load adjustment behaviors for each training user and multiple samples corresponding to each load adjustment behavior.

[0166] Each sample may include the historical electricity price plan, the first historical appliance plan, and the second historical appliance plan corresponding to the historical load adjustment behavior.

[0167] The historical electricity price plan is calculated based on the first historical load planning. The first historical load planning is adjusted according to the corresponding historical load adjustment behavior to form the second historical load planning.

[0168] S6203. Train the initial model sequentially using each sample and its corresponding historical load adjustment behavior until the initial model meets the preset training stopping condition. Use the final initial model as the load adjustment model matching the user type.

[0169] Specifically, the initial model can be trained using each sample and its corresponding historical load adjustment behavior until the initial model converges, and the final initial model can be used as the load adjustment model for matching the user type.

[0170] As can be seen from the above technical solution, this embodiment provides an optional method for training a load adjustment model for each user type. Through the above method, the reliability of this application can be further improved.

[0171] Next, we will combine Figure 2 The electricity price forecasting device provided in this application is described in detail. The electricity price forecasting device described below can be compared with the electricity price forecasting method described above.

[0172] See Figure 2 It can be observed that the electricity price forecasting device may include:

[0173] Appliance planning acquisition module 10 is used to acquire appliance plans for all users in the area.

[0174] The curve generation module 20 is used to generate the total demand load curve corresponding to the area based on each of the electrical appliance plans.

[0175] The power supply plan generation module 30 is used to generate a power supply plan corresponding to the area based on the total demand load curve.

[0176] The electricity price plan generation module 40 is used to generate an electricity price plan based on the total demand load curve and the power supply plan;

[0177] The predicted electricity cost calculation module 50 is used to calculate the predicted electricity cost for each user based on the electricity price plan and the appliance plan corresponding to each user, and to send the electricity price plan and each predicted electricity cost to the terminal of the corresponding user so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan;

[0178] The electricity price plan update module 60 is used to update the total demand load curve based on the latest appliance plans uploaded by one or more users, and then call the power supply plan generation module and its subsequent modules until the electricity price plan converges.

[0179] Furthermore, the curve generation module may include:

[0180] The demand load curve generation unit is used to constrain and compare the demand load of each user in different time periods, with the goal of minimizing the user's electricity cost, based on the user's electrical appliance plan, and to generate the corresponding demand load curve for the user.

[0181] The demand load curve aggregation unit is used to aggregate the demand load curves of each user to form the total demand load curve corresponding to the area.

[0182] Furthermore, the demand load curve generation unit may include:

[0183] The operation status constraint subunit is used to constrain and compare the operation status of multiple appliances of the user in each time period according to the user's corresponding appliance plan.

[0184] Furthermore, the power supply plan generation module may include:

[0185] The power supply constraint unit is used to constrain and compare the power supply of each generator set at each time period based on the total demand load curve with the goal of minimizing electricity costs, so as to form the power supply plan corresponding to the area.

[0186] Furthermore, the power supply constraint unit may include:

[0187] The power generation range constraint subunit is used to constrain and compare the power supply of each generator set at each time period based on the total demand load curve, as well as the power generation range, ramping constraint and energy storage constraint of each generator set.

[0188] Furthermore, the electricity price plan generation module may include:

[0189] The first electricity price plan generation unit is used to determine the power generation cost for each time period based on the power supply plan;

[0190] The second electricity price planning unit is used to compare the total demand load with the power generation capacity for the same period.

[0191] The third electricity price planning unit is used to calculate the target electricity price for each time period when the total demand load of the time period is less than the power generation capacity of the time period, based on the power generation cost and the power generation capacity of the time period.

[0192] The fourth electricity price planning unit is used to calculate the target electricity price for each time period, based on the generation cost and total demand load of that time period, provided that the total demand load of that time period is not less than the generation capacity of that time period.

[0193] The fifth electricity price planning unit is used to summarize the target electricity prices for each time period to form an electricity price plan.

[0194] Furthermore, the electricity price plan update module may include:

[0195] The first user determination unit is used to determine the users who upload new appliance plans after the latest electricity price plan is issued as first users, and to take the latest appliance plan uploaded by each first user as its corresponding first appliance plan.

[0196] The second user unit is used to identify all users in the area other than the first user as the second user;

[0197] The load adjustment behavior prediction unit is used to predict the load adjustment behavior of each second user, and generate a second electrical appliance plan corresponding to the second user based on the load adjustment behavior and the latest electrical appliance plan corresponding to the second user.

[0198] The load curve update unit is used to update the total demand load curve based on each first electrical appliance plan and each second electrical appliance plan.

[0199] Furthermore, the load adjustment behavior prediction unit may include:

[0200] The load adjustment model acquisition sub-unit is used to determine the user type of the second user and acquire the load adjustment model that matches the user type;

[0201] The load adjustment model utilization unit is used to input the latest electricity price plan and the latest electrical appliance plan of the second user into the load adjustment model to obtain the load adjustment behavior corresponding to the second user output by the load adjustment model.

[0202] Furthermore, the load adjustment model can acquire sub-units that include:

[0203] The first load adjustment model obtains sub-units for constructing the initial model;

[0204] The second load adjustment model obtains a sub-unit, which is used to take multiple users belonging to this user type as training users respectively;

[0205] The third load adjustment model acquisition subunit is used to acquire multiple historical load adjustment behaviors of each training user and determine the sample corresponding to each historical load adjustment behavior. Each sample includes the historical electricity price plan, the first historical appliance plan and the second historical appliance plan corresponding to the historical load adjustment behavior. The first historical appliance plan is adjusted by the corresponding historical load adjustment behavior to form the second historical appliance plan.

[0206] The fourth load adjustment model acquisition sub-unit is used to train the initial model by using each sample and its corresponding historical load adjustment behavior in turn until the initial model meets the preset training stopping condition. The final initial model is then used as the load adjustment model matching the user type.

[0207] The electricity price forecasting device provided in this application embodiment can be applied to electricity price forecasting equipment, such as PC terminals, cloud platforms, servers, and server clusters. Optionally, Figure 3 The hardware structure block diagram of the electricity price forecasting device is shown below. Figure 3 The hardware structure of the electricity price forecasting device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0208] In this embodiment of the application, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4;

[0209] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0210] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0211] The memory stores a program, which the processor can call. The program is used for:

[0212] Get the appliance plans for all users in the area;

[0213] Based on the electrical appliance plans, generate the total demand load curve for the area, and generate the power supply plan for the area based on the total demand load curve.

[0214] Based on the total demand load curve and the power supply plan, an electricity price plan is generated;

[0215] Based on the electricity price plan and the appliance plan for each user, the predicted electricity cost for each user is calculated, and the electricity price plan and each predicted electricity cost are sent to the corresponding user's terminal so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan;

[0216] Based on the latest appliance plans uploaded by one or more users, the total demand load curve is updated, and the process returns to the step of generating the power supply plan corresponding to the area based on the total demand load curve, until the electricity price plan converges.

[0217] Optionally, the refined and extended functions of the program can be referred to the above description.

[0218] This application embodiment also provides a readable storage medium that can store a program suitable for execution by a processor, the program being used for:

[0219] Get the appliance plans for all users in the area;

[0220] Based on the electrical appliance plans, generate the total demand load curve for the area, and generate the power supply plan for the area based on the total demand load curve.

[0221] Based on the total demand load curve and the power supply plan, an electricity price plan is generated;

[0222] Based on the electricity price plan and the appliance plan for each user, the predicted electricity cost for each user is calculated, and the electricity price plan and each predicted electricity cost are sent to the corresponding user's terminal so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan;

[0223] Based on the latest appliance plans uploaded by one or more users, the total demand load curve is updated, and the process returns to the step of generating the power supply plan corresponding to the area based on the total demand load curve, until the electricity price plan converges.

[0224] Optionally, the refined and extended functions of the program can be referred to the above description.

[0225] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0226] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0227] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. The various embodiments of this application can be combined with each other. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting electricity prices, characterized in that, include: Get the appliance plans for all users in the area; Based on the electrical appliance plans, generate the total demand load curve for the area, and generate the power supply plan for the area based on the total demand load curve. Based on the total demand load curve and the power supply plan, an electricity price plan is generated; Based on the electricity price plan and the appliance plan for each user, the predicted electricity cost for each user is calculated, and the electricity price plan and each predicted electricity cost are sent to the corresponding user's terminal so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan; Users who upload new appliance plans after the latest electricity price plan is issued will be designated as first users, and the latest appliance plan uploaded by each first user will be used as their corresponding first appliance plan. All users in the area other than the first user are designated as the second user; For each second user, determine the user type of that second user and build an initial model; Multiple users belonging to this user type will be used as training users respectively; Multiple historical load adjustment behaviors of each training user are obtained, and samples corresponding to each historical load adjustment behavior are determined. Each sample includes the historical electricity price plan, the first historical appliance plan, and the second historical appliance plan corresponding to the historical load adjustment behavior. The first historical appliance plan is adjusted by the corresponding historical load adjustment behavior to form the second historical appliance plan. The initial model is trained sequentially using each sample and its corresponding historical load adjustment behavior until the initial model meets the preset training stopping condition. The final initial model is used as the load adjustment model matching the user type. The latest electricity price plan and the latest appliance plan of the second user are input into the load adjustment model to obtain the load adjustment behavior corresponding to the second user output by the load adjustment model. Based on the load adjustment behavior and the latest appliance plan corresponding to the second user, the second appliance plan corresponding to the second user is generated. Based on each first electrical appliance plan and each second electrical appliance plan, the total demand load curve is updated, and the process returns to the step of generating the power supply plan corresponding to the area based on the total demand load curve, until the electricity price plan converges.

2. The electricity price forecasting method according to claim 1, characterized in that, Based on the respective appliance plans, generate the total demand load curve for the corresponding area, including: For each user, with the goal of minimizing the user's electricity cost, the user's demand load is constrained and compared in each time period based on the user's appliance plan, thus forming the corresponding demand load curve for the user; Summarize the demand load curves of each user to form the total demand load curve corresponding to the area.

3. The electricity price forecasting method according to claim 2, characterized in that, The constraint and comparison of the user's demand load in different time periods based on the user's electrical appliance plan includes: Based on the user's appliance plan, the operating status of multiple appliances for the user in each time period is constrained and compared.

4. The electricity price forecasting method according to claim 1, characterized in that, The step of generating a power supply plan for the area based on the total demand load curve includes: With the goal of minimizing electricity costs, the power supply of each generator set at each time period is constrained and compared based on the total demand load curve to form the power supply plan corresponding to the area.

5. The electricity price forecasting method according to claim 4, characterized in that, The constraint and comparison of the power supply of each generator set in each time period based on the total demand load curve includes: Based on the total demand load curve, as well as the power generation range, ramping constraints, and energy storage constraints of each generator set, the power supply of each generator set at each time period is constrained and compared.

6. The electricity price forecasting method according to claim 1, characterized in that, The total demand load curve includes the total demand load of the area in each time period; the power supply plan includes the power generation capacity of the area in each time period; The step of generating an electricity price plan based on the total demand load curve and the power supply plan includes: Based on the power supply plan, determine the power generation cost for each time period; Compare total demand load with power generation capacity during the same period; For each time period, when the total demand load of that time period is less than the power generation capacity of that time period, the target electricity price for that time period is calculated based on the power generation cost and the power generation capacity of that time period. For each time period, if the total demand load in that time period is not less than the power generation capacity in that time period, the target electricity price for that time period is calculated based on the power generation cost and the total demand load in that time period. The target electricity prices for each time period are summarized to form an electricity price plan.

7. An electricity price forecasting device, characterized in that, include: The appliance planning acquisition module is used to acquire the appliance plans corresponding to all users in the area; The curve generation module is used to generate the total demand load curve corresponding to the area based on each of the electrical appliance plans. The power supply plan generation module is used to generate a power supply plan corresponding to the area based on the total demand load curve. The electricity price plan generation module is used to generate an electricity price plan based on the total demand load curve and the power supply plan; The predicted electricity cost calculation module is used to calculate the predicted electricity cost for each user based on the electricity price plan and the appliance plan corresponding to each user, and to send the electricity price plan and each predicted electricity cost to the terminal of the corresponding user so that the user can adjust the appliance plan based on the corresponding predicted electricity cost and electricity price plan; The electricity price plan update module is used to identify users who upload new appliance plans after the latest electricity price plan is issued as first users, and to use the latest appliance plan uploaded by each first user as its corresponding first appliance plan; to identify other users in the area besides the first users as second users; and to determine the user type of each second user and to build an initial model. Multiple users belonging to this user type will be used as training users respectively; Multiple historical load adjustment behaviors of each training user are obtained, and samples corresponding to each historical load adjustment behavior are determined. Each sample includes the historical electricity price plan, the first historical appliance plan, and the second historical appliance plan corresponding to the historical load adjustment behavior. The first historical appliance plan is adjusted by the corresponding historical load adjustment behavior to form the second historical appliance plan. The initial model is trained sequentially using each sample and its corresponding historical load adjustment behavior until the initial model meets the preset training stopping condition. The final initial model is used as the load adjustment model matching the user type. The latest electricity price plan and the latest appliance plan of the second user are input into the load adjustment model to obtain the load adjustment behavior corresponding to the second user output by the load adjustment model. Based on the load adjustment behavior and the latest appliance plan corresponding to the second user, the second appliance plan corresponding to the second user is generated. Based on each first electrical appliance plan and each second electrical appliance plan, the total demand load curve is updated, and the power supply plan generation module and its subsequent modules are called back until the electricity price plan converges.

Images