Electricity price planning method and system based on artificial intelligence

Abstract

The invention relates to the technical field of electricity price planning, in particular to an electricity price planning method and system based on artificial intelligence. Comprising the following steps: establishing a power supply area and a plurality of power supply scenes, and generating a plurality of power purchasing user sets according to power purchasing user parameters in the power supply area; constructing an electricity price intelligent agent according to all user sets, wherein the intelligent agent generates a dynamic electricity price strategy based on the power grid operation parameters; acquiring a feedback data packet according to a preset feedback time node, and judging whether to correct the electricity price agent according to the feedback data packet; different power grid states are quantified by constructing a power supply scene sequence, a differential pricing strategy library is preset according to different power grid states, and the problem that a traditional electricity price mechanism is rigid is solved. Meanwhile, the time axis is dynamically adjusted according to the power grid fluctuation evaluation value, the optimal electricity price strategy is selected in real time, and the adaptability of the power grid to load sudden change is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of electricity price planning, in particular to an electricity price planning method and system based on artificial intelligence. BACKGROUND

[0002] As a basic energy of modern society, the price (electricity price) of electricity has a crucial influence on the stable operation of the electricity market, the optimal allocation of resources, the economic benefits of power generation enterprises, the safe dispatching of power grids, and the electricity cost of users.

[0003] The traditional electricity price planning scheme based on the economic model of fixed rules or simplified assumptions is insufficient in adaptability when facing problems such as rapid changes in the power system, such as dramatic fluctuations in new energy output, emergencies, market rule adjustments, etc. It is difficult to accurately capture the real-time characteristics and future trends of the dynamic market, resulting in a large lag or deviation of the planning results. SUMMARY

[0004] The purpose of the present application is to solve the above technical problems, and the present application provides an electricity price planning method and system based on artificial intelligence. The purpose is to improve the efficiency of electricity price planning and improve the adaptability of the power grid to load mutations.

[0005] In some embodiments of the present application, different power grid states are quantified by constructing a power supply scenario sequence, and a differentiated pricing strategy library is preset according to different power grid states to solve the rigidity problem of the traditional electricity price mechanism. At the same time, the time axis is dynamically adjusted according to the power grid fluctuation evaluation value, and the optimal electricity price strategy is selected in real time to improve the adaptability of the power grid to load mutations.

[0006] In some embodiments of the present application, an electricity price planning method based on artificial intelligence is provided, which comprises: establishing a power supply area and a plurality of power supply scenarios, and generating a plurality of electricity purchasing user sets according to the electricity purchasing user parameters in the power supply area; constructing an electricity price agent according to all user sets, and generating a dynamic electricity price strategy based on power grid operation parameters; obtaining a feedback data packet according to a preset feedback time node, and determining whether to correct the electricity price agent according to the feedback data packet; Wherein, when a plurality of power supply scenarios are set, it comprises: establishing a power supply scenario sequence A, A=(a1, a2…a i …a n ), wherein a i is the i-th power supply scenario; n is the number of power supply scenarios.

[0007] In some embodiments of the present application, when a plurality of electricity purchasing user sets are generated, it comprises; Establish a sequence of electricity purchasers P based on the electricity purchaser parameters, where P = (p1, p2, ..., p3). i …p m ), where p i Let be the i-th electricity purchaser within the power supply area; m is the number of electricity purchasers within the power supply area; Aggregate all electricity buyers based on category characteristics; Multiple sets of electricity purchasers are generated based on the aggregation results; Establish a sequence B, where B = (b1, b2, ..., bn) of electricity purchasers. i …b m1 ), where b i Let m1 be the set of the i-th electricity purchasers; m1 be the number of electricity purchasers in the set; and m1 <m。

[0008] In some embodiments of this application, the construction of the electricity price intelligent agent includes: Based on the power supply scenario sequence A, a is set sequentially. i Power supply scenario for target; Establish an evaluation sub-model for the target power supply scenario; The consumption evaluation value for each set of electricity buyers is generated based on the evaluation sub-model; A primary electricity price strategy for target power supply scenarios is set based on all consumption evaluation values; The primary electricity pricing strategy for each power supply scenario is generated sequentially; Construct a matching sub-model for the power supply scenario; Construct an intelligent electricity pricing agent based on all primary electricity pricing strategies and matching sub-models.

[0009] In some embodiments of this application, the construction of the matching sub-model for the power supply scenario further includes: Set multiple power grid operation indicators; Fluctuation evaluation values ​​are generated based on historical parameters of various power grid operation indicators; A matching time axis is set based on the fluctuation evaluation value, and the matching time axis includes multiple matching time nodes; Real-time power grid operation parameters are obtained based on the matching time nodes, and matching values ​​with various power supply scenarios are generated. The primary electricity pricing strategy for the power supply scenario corresponding to the maximum value in the matching value is set as a dynamic electricity pricing strategy.

[0010] In some embodiments of this application, setting the primary electricity price strategy for the target power supply scenario includes: A sub-strategy is generated based on all absorption evaluation values; Based on the sequence B of electricity purchaser sets, bi is sequentially set as the target set; Establish a sub-user sequence W, W=(w1, w2…w) of the target set. i…w r ), where w i Let be the i-th sub-user in the i-th target set; r is the number of sub-users in the target set; The electricity price response value for each sub-user is generated based on the evaluation sub-model of the target power supply scenario; The target set is set as a secondary sub-strategy in the target power supply scenario based on the total electricity price response value; The secondary sub-strategies for each electricity purchasing user set in the target power supply scenario are generated sequentially; The primary electricity pricing strategy for the target power supply scenario is generated based on the allocation sub-strategy and all secondary sub-strategies.

[0011] In some embodiments of this application, the generation of electricity price response values ​​for each sub-user includes: Set w sequentially according to the sub-user sequence W. i For target sub-users; Generate the electricity price response value d for the target sub-user in the target power supply scenario; d=[ β i *k i ]; Where θ1 represents the number of response evaluation indicators; β i The influence factor of the i-th response evaluation index set for the evaluation sub-model based on the target power supply scenario; k i This is a reference value for the i-th response evaluation metric for the target sub-user; Generate the electricity price response value for each sub-user in sequence; Establish a sequence of electricity price response values ​​D, D=(d1, d2…d i …d r ), where d i Let be the electricity price response value for the i-th sub-user.

[0012] In some embodiments of this application, when setting the target set as a secondary sub-strategy in the target power supply scenario, the following are included: Define the initial electricity value and electricity price fluctuation range for the target set in the target power supply scenario; The scheduling evaluation value f of the target set is generated based on all electricity price response values; The electricity price update frequency and the amount of a single price change are set based on the dispatch evaluation value f. Establish multiple electricity price update time nodes based on the electricity price update frequency; Generate revenue evaluation values ​​for each update time point, and determine whether to generate a stop command based on the revenue evaluation values.

[0013] In some embodiments of this application, generating the scheduling evaluation value f includes: f=e1*Q1* d i ]+e2*Q2*[ Y(i)*(d i -d')] Where e1 is the preset first weighting coefficient; e2 is the preset second weighting coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d' is the preset electricity price response value threshold; Y(i) is the selection coefficient; if (d i -d')>0,Y(i)=1; if (d i -d')<0,Y(i)=0.

[0014] In some embodiments of this application, when determining whether to correct the electricity price agent based on the feedback data packet, the following are included: Establish a primary electricity pricing strategy sequence P, P=(p1, p2…p i …p n ), where p i Let n be the primary electricity pricing strategy for the i-th power supply scenario; n is the number of power supply scenarios. Set pi as the target primary electricity price strategy in sequence; The operational evaluation value h of the target primary electricity price strategy is generated based on the feedback data packet; h=e3*Q3*[ η i *j i ]+e4*Q4*[ λ i *s i ]; Where e3 is the preset third weighting coefficient; e4 is the preset fourth weighting coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; θ2 is the number of operational evaluation indicators; η i Let j be the influencing factor of the i-th operational evaluation index; i It is the reference value for the i-th operational evaluation indicator in the target primary electricity price strategy, generated based on feedback data packets; λ i s is the influencing factor for the i-th set of electricity buyers; i To generate user rating values ​​for the i-th set of electricity buyers based on feedback data packets; Preset performance evaluation threshold H1; If h The system sequentially determines whether to generate correction instructions for each primary electricity pricing strategy.

[0015] In some embodiments of this application, an artificial intelligence-based electricity pricing planning system is provided, comprising: ​The central control unit is configured to establish a power supply area and a plurality of power supply scenarios, generate a plurality of power purchasing user sets according to power purchasing user parameters in the power supply area; The central control unit is further configured to construct a power price intelligent agent according to all user sets, and the intelligent agent generates a dynamic power price strategy based on power grid operation parameters; The updating unit is configured to obtain a feedback data packet according to a preset feedback time node, and determine whether to correct the power price intelligent agent according to the feedback data packet; The central control unit comprises: The first processing module is configured to establish a power supply scenario sequence A, A=(a1, a2…a i …a n ), wherein a i is the i th power supply scenario; and n is the number of power supply scenarios; The second processing module is configured to establish a power purchasing user sequence P according to power purchasing user parameters, P=(p1, p2…p i …p m ), wherein p i is the i th power purchasing user in the power supply area; and m is the number of power purchasing users in the power supply area; All power purchasing users are aggregated based on category characteristics; A plurality of power purchasing user sets are generated according to the aggregation result; A power purchasing user set sequence B, B=(b1, b2…b i …b m1 ) is established, wherein b i is the i th power purchasing user set; m1 is the number of power purchasing user sets; and m1<m; The third processing module is configured to sequentially set a i as a target power supply scenario according to the power supply scenario sequence A; An evaluation sub-model of the target power supply scenario is established; An accommodation evaluation value of each power purchasing user set is generated according to the evaluation sub-model; A first-level power price strategy of the target power supply scenario is set according to all accommodation evaluation values; A first-level power price strategy of each power supply scenario is sequentially generated; A matching sub-model of the power supply scenario is constructed; A power price intelligent agent is constructed according to all first-level power price strategies and the matching sub-model.

[0016] Compared with the prior art, the power price planning method and system based on artificial intelligence has the following beneficial effects: By constructing a power supply scene sequence to quantify different power grid states, and according to different power grid states, a differential pricing strategy library is preset to solve the rigid problem of the traditional electricity price mechanism. At the same time, according to the power grid fluctuation evaluation value, the time axis is dynamically adjusted, and the optimal electricity price strategy is selected in real time, so as to improve the adaptability of the power grid to load mutation.

[0017] By aggregating all users, a plurality of different electricity purchasing user sets are constructed, and according to the characteristic parameters of each electricity purchasing user set, the pricing strategy and pricing frequency are dynamically adjusted, so as to realize accurate pricing for different electricity purchasing users and improve the consumption capacity and overall income of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of an electricity price planning method based on artificial intelligence in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0019] The specific embodiments of the present application will be further described in detail below in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but are not used to limit the scope of the present application.

[0020] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element indicated must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0021] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0022] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the communication between the two elements inside. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0023] As Figure 1As shown, the power price planning method based on artificial intelligence of the preferred embodiment of the present application comprises: S101: Establish a power supply area and a plurality of power supply scenarios, and generate a plurality of electricity purchasing user sets according to the electricity purchasing user parameters in the power supply area; S102: Construct an electricity price intelligent agent according to all user sets, and the intelligent agent generates a dynamic electricity price strategy based on power grid operation parameters; S103: Obtain a feedback data packet according to a preset feedback time node, and determine whether to correct the electricity price intelligent agent according to the feedback data packet; Among them, when setting a plurality of power supply scenarios, it includes: Establish a power supply scenario sequence A, A=(a1, a2…a i …a n ), wherein a i is the i-th power supply scenario; n is the number of power supply scenarios.

[0024] Specifically, a plurality of power grid operation indexes are set according to historical operation parameters of the power grid, which include but are not limited to power grid load rate, power generation power stability, power grid power supply demand proportion, maximum load, operation period, environmental parameters and a plurality of parameters affecting power supply and demand relationship of the power grid.

[0025] Specifically, by quantitatively processing each power grid operation index, a plurality of value ranges of each power grid operation index are generated, and a plurality of power supply scenarios are constructed according to random combinations of each value range.

[0026] Specifically, when generating a plurality of electricity purchasing user sets, it includes; Establish an electricity purchasing user sequence P according to the electricity purchasing user parameters, P=(p1, p2…p i …p m ), wherein p i is the i-th electricity purchasing user in the power supply area; m is the number of electricity purchasing users in the power supply area; Aggregate all electricity purchasing users based on category characteristics; Generate a plurality of electricity purchasing user sets according to the aggregation result; Establish a sequence B of electricity purchasing user sets, B=(b1, b2…b i …b m1 ), wherein b i is the i-th electricity purchasing user set; m1 is the number of electricity purchasing user sets; and m1

[0027] Specifically, the category features include, but are not limited to, a power purchase user category (industry, business, residents, etc.), price sensitivity, load response capability (adjustment speed and adjustable amount of power consumption), and the like. By quantifying each category feature, each constructed user is analyzed, thereby aggregating users with similar power purchase behaviors.

[0028] Specifically, by generating a similarity value of a single power purchase user and all power purchase users, all power purchase users with a similarity value greater than a similarity value threshold are selected to generate a power purchase user set with the current power purchase user. Then, the above process is repeated for the remaining power purchase users, and all power purchase user sets are generated by cyclic selection.

[0029] It can be understood that in the above embodiments, different power grid states are quantified by constructing a power supply scenario sequence, and a differentiated pricing strategy library is preset according to different power grid states to solve the rigid problem of the traditional electricity pricing mechanism.

[0030] In the preferred embodiments of the present application, when constructing the electricity pricing agent, the following steps are included: According to the power supply scenario sequence A, a i target power supply scenario; establishing an evaluation sub-model of the target power supply scenario; generating a consumption evaluation value of each power purchase user set according to the evaluation sub-model; setting a first electricity pricing strategy of the target power supply scenario according to all consumption evaluation values; generating a first electricity pricing strategy of each power supply scenario in turn; constructing a matching sub-model of the power supply scenario; constructing the electricity pricing agent according to all first electricity pricing strategies and the matching sub-model.

[0031] Specifically, according to the adjustment requirements of the target power supply scenario, the influence factor and the value rule of each response evaluation index are set to construct the corresponding evaluation sub-model.

[0032] Specifically, in the target power supply scenario, the greater the influence of the response evaluation index on the electricity pricing plan, the greater the corresponding influence factor, for example, if load control is required in the target power supply scenario to reduce power consumption, the higher the sensitivity of the corresponding price increase, the greater the reference value of the corresponding response evaluation index, the greater the adjustable power range, the greater the corresponding reference value, and the greater the value of the corresponding influence factor. When the user is an individual, a hospital, or the like, the reference value of the corresponding response evaluation index is smaller, and the reference value of the corresponding response evaluation index for industry and business is greater. In the power supply scenario where power consumption needs to be increased, the higher the sensitivity to price reduction, the greater the reference value of the corresponding response evaluation index.

[0033] Specifically, the power supply scenario corresponding to the power grid is determined by a matching sub-model in the electricity price agent, so that a corresponding first electricity price strategy is selected for electricity price planning, thereby improving the planning efficiency of the electricity price.

[0034] Specifically, when the matching sub-model of the power supply scenario is constructed, the following steps are further included: A plurality of power grid operation indexes are set; A fluctuation evaluation value is generated according to historical parameters of each power grid operation index; A matching time axis is set according to the fluctuation evaluation value, and the matching time axis includes a plurality of matching time nodes; Real-time power grid operation parameters are obtained according to the matching time nodes, and a matching value corresponding to each power supply scenario is generated; The first electricity price strategy of the power supply scenario corresponding to the maximum value in the matching value is set as a dynamic electricity price strategy.

[0035] Specifically, the historical parameters of each power grid operation index are obtained, a corresponding sub-fluctuation value is generated, and the corresponding sub-fluctuation value is greater when the probability of fluctuation of a single power grid operation index is greater.

[0036] Specifically, the greater the fluctuation evaluation value, the greater the possibility of fluctuation of the power grid in the operation process, and the shorter the time interval between adjacent matching time nodes on the corresponding matching time axis.

[0037] Specifically, by obtaining the real-time power grid operation parameters of the matching time nodes, real-time reference values of each power grid operation index are generated, and by comparing with the reference values of each power grid operation index in a single power supply scenario, corresponding matching values are generated. The smaller the difference between the real-time reference value of each power grid operation index and the reference value in the power supply scenario, the greater the corresponding matching value.

[0038] Specifically, by periodically judging the operation state of the power supply grid, the corresponding power supply scenario is matched in time, so that the corresponding electricity price strategy is selected.

[0039] It can be understood that in the above embodiments, the time axis is dynamically adjusted according to the fluctuation evaluation value of the power grid, the optimal electricity price strategy is selected in real time, and the adaptability of the power grid to load mutation is improved.

[0040] In the preferred embodiments of the present application, when the first electricity price strategy of the target power supply scenario is set, the following steps are included: A distribution sub-strategy is generated according to all consumption evaluation values; The bi is set as the target set according to the purchase user set sequence B in turn; A sub-user sequence W of the target set is established, W=(w1, w2…wn), and the following steps are further included: i …wn r), wherein w i is the i-th sub-user in the i-th target set; r is the number of sub-users in the target set; generating the electricity price response value of each sub-user according to the evaluation sub-model of the target power supply scenario; setting the secondary sub-strategy of the target set in the target power supply scenario according to all electricity price response values; generating the secondary sub-strategy of each electricity purchasing user set in the target power supply scenario in turn; generating the primary electricity price strategy of the target power supply scenario according to the allocated sub-strategy and all secondary sub-strategies.

[0041] Specifically, the accommodation evaluation value is set according to the adjustable electricity quantity of all electricity purchasing users in the target set, and the greater the total value of the adjustable electricity quantity, the greater the corresponding accommodation evaluation value.

[0042] Specifically, the corresponding allocation proportion is set according to the ratio of each accommodation evaluation value to the total value of the accommodation evaluation value, the expected adjustable electricity quantity in the power supply scenario is allocated, and the corresponding allocation sub-strategy is generated.

[0043] Specifically, the response ability of each sub-user in the target power supply scenario is analyzed, and a personalized bidding strategy is formulated to improve the efficiency of electricity price planning.

[0044] Specifically, when generating the electricity price response value of each sub-user, the following steps are included: setting w i in turn according to the sub-user sequence W generating the electricity price response value d of the target sub-user in the target power supply scenario; d=[ β i *k i ]; wherein θ1 is the number of response evaluation indexes; β i is the influence factor of the i-th response evaluation index set based on the evaluation sub-model of the target power supply scenario; k i is the reference value of the i-th response evaluation index of the target sub-user; generating the electricity price response value of each sub-user in turn; establishing the electricity price response value sequence D, D=(d1, d2…d i …d r ), wherein d i is the electricity price response value of the i-th sub-user.

[0045] Specifically, the response evaluation index includes but is not limited to price sensitivity, price sensitive range, adjustable power range, expected power to be consumed, user category and other parameters. By quantifying each response evaluation index, accurate evaluation of each power purchase user is realized. The greater the response evaluation value is, the faster the current sub-user responds to the price change, and the more the adjustable power is.

[0046] In the preferred embodiment of the present application, when setting the secondary sub-strategy of the target set in the target power supply scenario, the following steps are included: setting the initial electricity value and the electricity price fluctuation interval of the target set in the target power supply scenario; generating a scheduling evaluation value f of the target set according to all electricity price response values; setting the electricity price update frequency and the electricity price single change amount according to the scheduling evaluation value f; establishing a plurality of electricity price update time nodes according to the electricity price update frequency; generating a benefit evaluation value of each update time node, and determining whether to generate a stop instruction according to the benefit evaluation value.

[0047] Specifically, when generating the scheduling evaluation value f, the following steps are included: f = e1*Q1 d i + e2*Q2 Y(i)*(d i -d') Wherein, e1 is a preset first weight coefficient; e2 is a preset second weight coefficient; Q1 is a preset first fixed coefficient; Q2 is a preset second fixed coefficient; d' is a preset electricity price response value threshold; Y(i) is a selection coefficient; if (d i -d') > 0, Y(i) = 1; if (d i -d') < 0, Y(i) = 0.

[0048] Specifically, by normalizing all parameters in the model through the preset first fixed coefficient and the second fixed coefficient, each parameter in the model is within the same value range.

[0049] Specifically, the greater the scheduling evaluation value is, the greater the overall electricity price adjustment of the current target set is, and the smaller the electricity price update frequency and the single change amount are. By dynamically adjusting the electricity price, the adjustment ability of the target set to the power grid is improved, and the stable operation of the power grid is ensured.

[0050] Specifically, the smaller the scheduling evaluation value is, the poorer the response ability to the price in the current target set is, and the lower the corresponding price frequency is, thereby reducing the overall operation and maintenance cost of the price system.

[0051] Specifically, if the benefit evaluation value of the current update time node is lower than that of the last update time node, the electricity price updating is stopped, and the electricity price of the last update time node is adopted. If the state of the power grid changes, the corresponding power supply scenario is updated, and the bidding is re-performed.

[0052] It can be understood that, in the above embodiments, all users are aggregated to construct a plurality of different electricity purchasing user sets, and the bidding strategy and the bidding frequency are dynamically adjusted according to the characteristic parameters of each electricity purchasing user set, so as to realize accurate bidding for different electricity purchasing users and improve the consumption capacity and overall benefit of the power grid.

[0053] In the preferred embodiments of the present application, when determining whether to correct the electricity price agent according to the feedback data packet, the following steps are included: A first electricity price strategy sequence P is established, P=(p1, p2…pn), wherein pi is the first electricity price strategy of the i th power supply scenario; n is the number of power supply scenarios; i …p n ), wherein p i is the first electricity price strategy of the i th power supply scenario; n is the number of power supply scenarios; Pi is sequentially set as the target first electricity price strategy; The running evaluation value h of the target first electricity price strategy is generated according to the feedback data packet; h=e3*Q3*[ η i *j i ]+e4*Q4*[ λ i *s i ]; Wherein e3 is a preset third weight coefficient; e4 is a preset fourth weight coefficient; Q3 is a preset third fixed coefficient; Q4 is a preset fourth fixed coefficient; θ2 is the number of running evaluation indexes; η i is the influence factor of the i th running evaluation index; j i is the reference value of the i th running evaluation index in the target first electricity price strategy generated based on the feedback data packet; λ i is the influence factor of the i th electricity purchasing user set; s i is the user evaluation value of the i th electricity purchasing user set generated based on the feedback data packet; A preset running evaluation value threshold H1 is set; If h The correction instruction of each first electricity price strategy is sequentially determined.

[0054] Specifically, the third fixed coefficient and the fourth fixed coefficient are used to normalize all parameters in the model, so that all parameters in the model are in the same value range.

[0055] Specifically, the operational evaluation indicators include, but are not limited to, the power grid's capacity to absorb electricity, the time required to reach the best bids from each electricity purchaser, and the overall load factor of the power grid. The influence factors of each operational indicator are set according to their impact on the overall operational revenue of the power grid. The greater the impact, the larger the value of the corresponding influence factor.

[0056] Specifically, the higher the operational evaluation value, the higher the overall operational benefits of the current power grid.

[0057] Specifically, user ratings are set based on users' actual electricity consumption; the higher the rating, the less impact the current electricity pricing plan has on the user's life. The impact factors for each user are set based on their electricity price response values; the higher the response value, the greater the corresponding impact factor.

[0058] Specifically, the performance evaluation threshold can be set based on historical parameters.

[0059] Specifically, the correction instruction refers to optimizing and iterating each of the secondary sub-strategies within the current primary electricity pricing strategy, thereby improving the overall efficiency of electricity pricing planning.

[0060] Specifically, a threshold for the number of correction instructions is preset. If the number of correction instructions in real time exceeds the threshold, the agent needs to be optimized as a whole. The original set of electricity buyers and the power supply scenario need to be further refined. Based on the refinement results, the corresponding first-level electricity price strategy is reset.

[0061] In another preferred embodiment of the artificial intelligence-based electricity pricing planning method based on any of the above preferred embodiments, this preferred embodiment provides an artificial intelligence-based electricity pricing planning method, including: The central control unit is used to establish power supply areas and multiple power supply scenarios, and generate multiple sets of electricity purchasers based on the electricity purchaser parameters within the power supply area; The central control unit is also used to construct an intelligent electricity pricing agent based on the entire user set. The agent generates a dynamic electricity pricing strategy based on the grid operation parameters. The update unit is used to obtain feedback data packets according to preset feedback time nodes, and to determine whether to correct the electricity price agent based on the feedback data packets; The central control unit includes: The first processing module is used to establish the power supply scenario sequence A, A=(a1,a2…a…). i …a n ), where a i Let i be the i-th power supply scenario; n is the number of power supply scenarios; The second processing module is used to establish a sequence P of electricity purchasers based on the electricity purchaser parameters, where P = (p1, p2…p…). i …pm ), wherein p i is the ith power purchase user in the power supply area; m is the number of power purchase users in the power supply area; aggregating all power purchase users based on category characteristics; generating a plurality of power purchase user sets according to the aggregation result; establishing a power purchase user set sequence B, B = (b1, b2…bm1), wherein bi is the ith power purchase user set; m1 is the number of power purchase user sets; and m1 < m; i …bm1 m1 ), wherein bi i is the ith power purchase user set; m1 is the number of power purchase user sets; and m1 < m; a third processing module, configured to sequentially set ai according to the power supply scenario sequence A, wherein i = 1, 2, …, m; i is the target power supply scenario; establishing an evaluation sub-model of the target power supply scenario; generating a consumption evaluation value of each power purchase user set according to the evaluation sub-model; setting a primary electricity price strategy of the target power supply scenario according to all consumption evaluation values; sequentially generating a primary electricity price strategy of each power supply scenario; constructing a matching sub-model of the power supply scenario; constructing an electricity price intelligent agent according to all primary electricity price strategies and the matching sub-model.

[0062] According to the first concept of the present application, different power grid states are quantified by constructing a power supply scenario sequence, and a differentiated pricing strategy library is preset according to different power grid states, thereby solving the rigidity problem of the traditional electricity price mechanism. At the same time, the time axis is dynamically adjusted according to the power grid fluctuation evaluation value, and the optimal electricity price strategy is selected in real time, thereby improving the adaptability of the power grid to load mutation.

[0063] According to the second concept of the present application, all users are aggregated, thereby constructing a plurality of different power purchase user sets, and the bidding strategy and bidding frequency are dynamically adjusted according to the characteristic parameters of each power purchase user set, thereby realizing accurate bidding for different power purchase users and improving the consumption capacity and overall income of the power grid.

[0064] The above only describes the preferred embodiments of the present application. It should be noted that those skilled in the art can make several improvements and replacements without departing from the technical principles of the present application, and these improvements and replacements should also be considered as the protection scope of the present application.

Claims

1. An artificial intelligence-based electricity pricing planning method, characterized in that, Including: Establish a power supply area and multiple power supply scenarios, and generate multiple sets of power purchase users according to the parameters of power purchase users in the power supply area; Construct a price intelligent agent based on all user sets, and the intelligent agent generates a dynamic electricity price strategy based on grid operation parameters; Obtain a feedback data packet according to a preset feedback time node, and determine whether to correct the price intelligent agent according to the feedback data packet; Among them, when setting multiple power supply scenarios, it includes: Establish a power supply scenario sequence A, A=(a1,a2…a…) i …a n ), where a i Let be the i-th power supply scenario; n is the number of power supply scenarios.

2. The artificial intelligence-based electricity pricing planning method as described in claim 1, characterized in that, When generating multiple sets of power purchase users, it includes; Establish a sequence of electricity purchasers P based on the electricity purchaser parameters, where P = (p1, p2, ..., p3). i …p m ), where p i Let be the i-th electricity purchaser within the power supply area; m is the number of electricity purchasers within the power supply area; Aggregate all power purchase users based on category characteristics; Generate multiple sets of power purchase users according to the aggregation result; Establish a sequence B, where B = (b1, b2, ..., bn) of electricity purchasers. i …b m1 ), where b i Let m1 be the set of the i-th electricity purchasers; m1 be the number of electricity purchasers in the set; and m1 <m。 3. The artificial intelligence-based electricity pricing planning method as described in claim 2, characterized in that, When constructing a price intelligent agent, it includes: Based on the power supply scenario sequence A, a is set sequentially. i Power supply scenario for target; Establish an evaluation sub-model for the target power supply scenario; Generate the absorption evaluation value of each set of power purchase users according to the evaluation sub-model; Set the primary electricity price strategy for the target power supply scenario according to all absorption evaluation values; Generate the primary electricity price strategy for each power supply scenario in sequence; Construct a matching sub-model for the power supply scenario; Construct a price intelligent agent according to all primary electricity price strategies and the matching sub-model.

4. The artificial intelligence-based electricity pricing planning method as described in claim 3, characterized in that, When constructing the matching sub-model for the power supply scenario, it further includes: Set multiple grid operation indicators; Generate a fluctuation evaluation value according to the historical parameters of each grid operation indicator; Set a matching time axis according to the fluctuation evaluation value, and the matching time axis includes multiple matching time nodes; Obtain real-time grid operation parameters according to the matching time nodes and generate matching values for each power supply scenario; Set the primary electricity price strategy of the power supply scenario corresponding to the maximum value in the matching values as the dynamic electricity price strategy.

5. The artificial intelligence-based electricity pricing planning method as described in claim 3, characterized in that, When setting the primary electricity price strategy for the target power supply scenario, it includes: Generate an allocation sub-strategy according to all absorption evaluation values; Set bi as the target set in sequence according to the sequence B of power purchase user sets; Establish a sub-user sequence W, W=(w1, w2…w) of the target set. i …w r ), where w i Let be the i-th sub-user in the i-th target set; r is the number of sub-users in the target set; Generate the electricity price response value of each sub-user according to the evaluation sub-model of the target power supply scenario; Set the secondary sub-strategy of the target set in the target power supply scenario according to all electricity price response values; Generate the secondary sub-strategy of each set of power purchase users in the target power supply scenario in sequence; Generate the primary electricity price strategy for the target power supply scenario according to the allocation sub-strategy and all secondary sub-strategies.

6. The artificial intelligence-based electricity pricing planning method as described in claim 5, characterized in that, When generating the electricity price response value of each sub-user, it includes: Set w sequentially according to the sub-user sequence W. i For target sub-users; Generate the electricity price response value d of the target sub-user in the target power supply scenario; d=[ b i *k i ]; Where θ1 represents the number of response evaluation indicators; β i The influence factor of the i-th response evaluation index set for the evaluation sub-model based on the target power supply scenario; k i This is a reference value for the i-th response evaluation metric for the target sub-user; Generate the electricity price response value of each sub-user in sequence; Establish a sequence of electricity price response values ​​D, D=(d1, d2…d i …d r ), where d i Let be the electricity price response value for the i-th sub-user.

7. The artificial intelligence-based electricity pricing planning method as described in claim 6, characterized in that, When setting the secondary sub-strategy of the target set in the target power supply scenario, it includes: Set the initial electricity price value and the electricity price change interval of the target set in the target power supply scenario; Generate the scheduling evaluation value f of the target set according to all electricity price response values; Set the electricity price update frequency and the single electricity price change amount according to the scheduling evaluation value f; Establish multiple electricity price update time nodes according to the electricity price update frequency; Generate the revenue evaluation value of each update time node, and determine whether to generate a stop instruction according to the revenue evaluation value.

8. The artificial intelligence-based electricity pricing planning method as described in claim 7, characterized in that, When generating the scheduling evaluation value f, it includes: f=e1*Q1* d i ]+e2*Q2*[ Y(i)*(d i -d')] Where e1 is the preset first weighting coefficient; e2 is the preset second weighting coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d' is the preset electricity price response value threshold; Y(i) is the selection coefficient; if (d i -d')>0,Y(i)=1; if (d i -d')<0,Y(i)=0.

9. The artificial intelligence-based electricity pricing planning method as described in claim 8, characterized in that, When determining whether to correct the price intelligent agent according to the feedback data packet, it includes: Establish a primary electricity pricing strategy sequence P, P=(p1, p2…p i …p n ), where p i Let n be the primary electricity pricing strategy for the i-th power supply scenario; n is the number of power supply scenarios. Set pi as the target primary electricity price strategy in sequence; Generate the operation evaluation value h of the target primary electricity price strategy according to the feedback data packet; h=e3*Q3*[ or i *j i ]+e4*Q4*[ l i *s i ]; Where e3 is the preset third weighting coefficient; e4 is the preset fourth weighting coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; θ2 is the number of operational evaluation indicators; η i Let j be the influencing factor of the i-th operational evaluation index; i It is the reference value for the i-th operational evaluation indicator in the target primary electricity price strategy, generated based on feedback data packets; λ i s is the influencing factor for the i-th set of electricity buyers; i To generate user rating values ​​for the i-th set of electricity buyers based on feedback data packets; Preset the operation evaluation value threshold H1; If h < H1, generate a correction instruction for the target primary electricity price strategy; Judge whether to generate a correction instruction for each primary electricity price strategy in sequence.

10. An artificial intelligence-based electricity pricing planning system, employing the artificial intelligence-based electricity pricing planning method according to any one of claims 1-9, characterized in that, Including: The central control unit is used to establish power supply areas and multiple power supply scenarios, and generate multiple sets of electricity purchasers based on the electricity purchaser parameters within the power supply area; The central control unit is also used to construct an intelligent electricity price agent based on the entire user set, and the intelligent agent generates a dynamic electricity price strategy based on the power grid operating parameters. The update unit is used to obtain feedback data packets according to preset feedback time nodes, and to determine whether to correct the electricity price agent based on the feedback data packets; The central control unit includes: The first processing module is used to establish the power supply scenario sequence A, A=(a1,a2…a…). i …a n ), where a i Let i be the i-th power supply scenario; n is the number of power supply scenarios; The second processing module is used to establish a sequence P of electricity purchasers based on the electricity purchaser parameters, where P = (p1, p2…p…). i …p m ), where p i Let be the i-th electricity purchaser within the power supply area; m is the number of electricity purchasers within the power supply area; Aggregate all electricity buyers based on category characteristics; Multiple sets of electricity purchasers are generated based on the aggregation results; Establish a sequence B, where B = (b1, b2, ..., bn) of electricity purchasers. i …b m1 ), where b i Let m1 be the set of the i-th electricity purchasers; m1 be the number of electricity purchasers in the set; and m1 <m; The third processing module is used to set a sequentially according to the power supply scenario sequence A. i Power supply scenario for target; Establish an evaluation sub-model for the target power supply scenario; The consumption evaluation value for each set of electricity buyers is generated based on the evaluation sub-model; A primary electricity price strategy for target power supply scenarios is set based on all consumption evaluation values; The primary electricity pricing strategy for each power supply scenario is generated sequentially; Construct a matching sub-model for the power supply scenario; Construct an intelligent electricity pricing agent based on all primary electricity pricing strategies and matching sub-models.

Images