Regional power dispatching method and device based on load free transaction market

Abstract

The invention discloses a regional power dispatching method and device based on a load free transaction market, and relates to the technical field of power dispatching, and the technical scheme is characterized in that the method comprises the steps: obtaining the load data of each region at the current moment and the electricity price data of the load free transaction market at the current moment; predicting the load data of each region at the current moment through a pre-configured load prediction model to obtain future load data of each region; determining an objective function for minimizing the power dispatching comprehensive cost, and constructing a power optimization dispatching model according to the objective function and a pre-configured power dispatching constraint condition; the future load data, the load data and the electricity price data of all the areas serve as input parameters of the power optimization dispatching model, the power optimization dispatching model is solved, and a power dispatching result is obtained; wherein the power dispatching result refers to the generating capacity and the power exchange value of each region in each time period.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power dispatching, and more specifically, to a regional electric power dispatching method and device based on a load free trading market. Background Art

[0002] In the power system, the optimization problem of power dispatching and load market involves how to allocate power resources efficiently and reliably to ensure the stable operation of the power system.

[0003] Traditional power dispatch methods mainly focus on optimization algorithms based on deterministic models, such as linear programming (LP), integer programming (IP) and dynamic programming (DP). These methods usually obtain the optimal dispatch plan by optimizing objective functions such as power generation cost, emission cost and grid operation cost. In the load market, the power exchange between regions is determined by the market mechanism, and users buy and sell power according to the real-time electricity price.

[0004] Most of the dispatching methods provided by related technologies rely on historical data or static load forecasts, and cannot flexibly respond to rapid changes in real-time loads. Especially when a large number of renewable energy sources are connected to the grid, the volatility of load and power supply increases, and it is difficult for existing dispatching methods to adapt quickly. In addition, traditional load markets often ignore the game behavior of buyers and sellers in the power market, and fail to fully consider the dynamic needs, price sensitivity and trading strategies of market participants. This will result in the load regulation and market transaction benefits not being maximized, and the optimal dispatching in different scenarios cannot be achieved. Summary of the invention

[0005] The purpose of the present invention is to provide a regional power dispatching method and device based on a load free trading market. The present invention solves the problem that related technologies cannot maximize the benefits of load regulation and market transactions.

[0006] A first aspect of the present invention provides a regional power dispatching method based on a load free trading market, the method comprising:

[0007] Obtain the current load data of each region and the current electricity price data of the load free trading market;

[0008] The current load data of each region is predicted by a pre-configured load prediction model to obtain the future load data of each region; wherein the load prediction model is obtained by training a long short-term memory neural network with the historical load data of each region;

[0009] Determine the objective function of minimizing the comprehensive cost of power dispatch, and build a power optimization dispatch model based on the objective function and pre-configured power dispatch constraints;

[0010] The future load data, load data and electricity price data of each region are used as input parameters of the power optimization scheduling model, the power optimization scheduling model is solved, and the power scheduling result is obtained; among which, the power scheduling result refers to the power generation and power exchange value of each region in each time period.

[0011] In one implementation, the objective function is expressed as:

[0012]

[0013] in, represents the power generation of the ith region at time t; C G,i represents the power generation cost of the ith region; represents the forecast load of the ith region at time t; U i represents the load regulation cost of the ith region; represents the cross-region power exchange value between the ith region and the jth region at time t; C T,ij represents the transmission cost between the i-th region and the j-th region; E represents the emission cost; λ e represents the emission cost weight; Loss represents the transmission loss; λ l represents the transmission loss weight; R i Represents the revenue of the ith region in the load trading market.

[0014] In one implementation, the pre-configured power dispatch constraints include power balance constraints, power exchange constraints, generator set operation constraints, energy storage system constraints, load regulation constraints, and load trading market constraints.

[0015] In one implementation, the expression of the power balance constraint is: Among them, η ij represents the transmission line loss efficiency from region i to region j; represents the energy storage release power of area i;

[0016] The expression of the power exchange constraint is: in, represents the maximum allowable current of the transmission line from area i to area j; Z ij represents the equivalent impedance of the transmission line from area i to area j;

[0017] The expression of the generator set operation constraint is: in, represents the ramp rate limit of the generator set in area i; represents the minimum generating capacity of the generator set in area i; represents the maximum generating capacity of the generator set in area i;

[0018] The expression of the energy storage system constraint is: in, represents the maximum release power of energy storage in area i; represents the energy storage value of the energy storage device in area i at time t; η c represents the environmental coefficient of area i; η d Indicates the temperature coefficient of the energy storage device; represents the minimum energy storage value of the energy storage device in area i; Indicates the maximum energy storage value of the energy storage device in area i;

[0019] The expression of the load regulation constraint is: in, represents the minimum load regulation value of area i; represents the maximum load regulation value of area i; represents the load regulation rate limit of area i;

[0020] The load trading market constraints are specifically shown in the following formula: in, represents the load sold in area i at time t; represents the load purchased by region i at time t.

[0021] In one implementation, the revenue calculation formula of the region in the load free trading market is: in, represents the market price of electricity sold in region i at time t; represents the load sold in area i at time t; represents the electricity sales transaction fee in area i; represents the fixed cost of electricity sales in region i; θ i represents the transaction penalty coefficient of region i; represents the market price of electricity purchased by region i at time t; represents the load purchased by region i at time t; represents the transaction fee for electricity purchase in area i; represents the fixed cost of region i when purchasing electricity.

[0022] In one implementation, the method further includes: constructing an error correction model to correct the errors in power generation and power exchange value of each region in each time period.

[0023] In one implementation, the error correction model is expressed as Among them, X adjIndicates the error correction value; X opt represents the model input value; f ML represents the machine learning model; Y represents the objective function parameter; ξ represents the auxiliary variable; ω represents the confidence of the machine learning model; N represents the length of the historical window; Indicates the actual value of the input variable at time tn; Represents the input value at time tn; ∈ is the historical correction weight; α represents the adjustment coefficient.

[0024] A second aspect of the present invention provides a regional power dispatching device based on a load free trading market, the device comprising:

[0025] The data acquisition module is used to obtain the current load data of each region and the current electricity price data of the load free trading market;

[0026] The load forecasting module is used to forecast the current load data of each region through a pre-configured load forecasting model to obtain the future load data of each region; wherein the load forecasting model is obtained by training a long short-term memory neural network through the historical load data of each region;

[0027] The dispatch model building module is used to determine the objective function of minimizing the comprehensive cost of power dispatch, and to build a power optimization dispatch model based on the objective function and pre-configured power dispatch constraints;

[0028] The scheduling result determination module is used to use the future load data, load data and electricity price data of each region as input parameters of the power optimization scheduling model, solve the power optimization scheduling model, and obtain the power scheduling result; wherein the power scheduling result refers to the power generation and power exchange value of each region in each time period.

[0029] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for regional power dispatching based on a load free trading market as provided in the first aspect of the present invention is implemented.

[0030] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, a regional power dispatching method based on a load free trading market as provided in the first aspect of the present invention is implemented.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention can predict power demand in real time and adjust power dispatch strategy more accurately by introducing machine learning models.

[0033] 2. The present invention introduces the profit function of the load trading market, taking into account the strategic behavior of buyers and sellers in the power market; each region makes the best decision when buying and selling loads according to the market mechanism, thereby improving the profits of market participants.

[0034] 3. The power dispatching model constructed by the objective function and constraint conditions of multiple dispatching costs in the present invention has higher optimization capability and system adaptability, and can achieve optimal dispatching in different scenarios whether it is power production, market trading or power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0036] Figure 1 A schematic diagram of a flow chart of a regional power dispatching method based on a load free trading market provided by an embodiment of the present invention;

[0037] Figure 2 A principle block diagram of a regional power dispatching device based on a load free trading market provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0039] It should be noted that the terms "include" or "may include" used in various embodiments of the present application indicate the presence of the function, operation or element applied for, and do not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present application, the terms "include", "have" and their cognates are only intended to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items.

[0040] In various embodiments of the present application, the expression "or" or "at least one of B or / and C" includes any combination or all combinations of the words listed at the same time. For example, the expression "B or C" or "at least one of B or / and C" may include B, may include C, or may include both B and C.

[0041] In the description of the present invention, “plurality” means two or more than two, unless otherwise clearly and specifically defined.

[0042] Please refer to Figure 1 , Figure 1 A flow chart of a regional power dispatching method based on a load free trading market provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes:

[0043] S101, obtaining the current load data of each region and the current electricity price data of the load free trading market.

[0044] In this embodiment, the division of distribution areas of the distribution network is a well-known probability to those skilled in the art. For example, taking xx city as an example, each district of xx city is regarded as a distribution area, or a 110kV substation is regarded as a distribution area.

[0045] The load free trading market is usually composed of multiple participants, including electricity users (load side), power sales companies, load aggregators, power trading institutions, etc.

[0046] S102, predicting the current load data of each region through a pre-configured load prediction model to obtain the future load data of each region; wherein the load prediction model is obtained by training a long short-term memory neural network through the historical load data of each region.

[0047] In this embodiment, the long short-term memory neural network is a relatively mature neural network, which is mainly used to process and predict important events with long intervals and delays in time series data. Long short-term memory neural network (LSTM neural network for short) is a special recurrent neural network (RNN) architecture, specially designed to solve the gradient vanishing or gradient explosion problems encountered by traditional RNN when processing long sequence data. LSTM neural network can capture long-distance dependencies, that is, the mutual influence between events far apart in time series data by introducing self-loop feedback connections and complex gating mechanisms. The core of LSTM neural network is LSTM cell, each of which contains three main gating mechanisms: forget gate, input gate and output gate, as well as a cell state. These gating mechanisms implement information screening and updating through sigmoid function or tanh function, thereby controlling the flow of information.

[0048] Forget Gate: Decides which information to discard from the previous LSTM cell state. The Forget Gate looks at the current input and the previous hidden state, and outputs a value between 0 and 1 through the sigmoid function, indicating the proportion of retention or forgetting.

[0049] Input gate: determines what new information needs to be added to the state of the current LSTM unit. The input gate also determines the importance of the new information based on the current input and the previous hidden state, and generates a candidate cell state.

[0050] Cell state: It is the "memory" part in the LSTM network and is responsible for storing long-term information. The cell state updates its content through the forget gate and the input gate, that is, how much old information is retained according to the forget gate, and how much new information is added according to the input gate and the candidate cell state.

[0051] Output gate: Based on the current cell state and hidden state, decide what value to output. The output gate generates an output gating signal through the sigmoid function, then scales the cell state through the tanh function and multiplies it with the output gating signal to get the final hidden state output.

[0052] LSTM neural networks excel in processing sequence data, especially in tasks that require capturing long-range dependencies, such as speech recognition, natural language processing (such as machine translation, sentiment analysis), time series forecasting (such as stock price prediction, weather forecasting), and image and video analysis.

[0053] Therefore, this embodiment uses the historical load data of each region to train the long short-term memory neural network, so that it has the ability to predict the future load data of a region. Of course, as those skilled in the art can understand, in addition to using the long short-term memory neural network, a machine learning model (such as linear regression, XGBoost) with the same prediction ability as the long short-term memory neural network can also be used, and this embodiment does not make redundant descriptions. The load forecasting model provided in this embodiment can predict power demand in real time and adjust the power dispatching strategy more accurately.

[0054] S103, determining an objective function for minimizing the comprehensive cost of power dispatching, and constructing a power optimization dispatching model based on the objective function and pre-configured power dispatching constraints.

[0055] In this embodiment, the expression of the objective function is:

[0056]

[0057] in, represents the power generation of the ith region at time t; C G,i represents the power generation cost of the ith region; represents the forecast load of the ith region at time t; U i represents the load regulation cost of the ith region; represents the cross-region power exchange value between the ith region and the jth region at time t; C T,ij represents the transmission cost between the i-th region and the j-th region; E represents the emission cost; λ e represents the emission cost weight; Loss represents the transmission loss; λ l represents the transmission loss weight; R i Represents the revenue of the ith region in the load trading market.

[0058] Specifically, the calculation formula for power generation cost is:

[0059] in: represents the fuel cost coefficient of region i, reflecting the unit cost of fuel; It indicates the impact coefficient of power generation in the previous period, reflecting the cost impact of starting and shutting down power generation equipment; represents the power generation efficiency coefficient of region i. As the efficiency changes, the fuel cost consumed per unit of power generation; represents the efficiency of power generation equipment in region i. When it decreases, the cost of power generation increases. K represents the type of fuel. f k represents the unit price coefficient of the kth fuel; P k represents the usage ratio of the kth fuel; represents the fuel consumption of area i at time t; δ i represents the aging coefficient of power generation equipment in region i, the coefficient of the impact of equipment aging on power generation cost, and reflects the cost increase due to the reduction of equipment efficiency;

[0060] The calculation formula for load regulation cost is as follows: Where: P represents the type of load regulation equipment; θ p represents the regulation cost coefficient of the p-th load regulation device; R p The efficiency of the pth load regulation device; M represents the total number of load regulation strategies; represents the implementation cost coefficient of the mth load regulation strategy; S m It indicates the influence of the mth load regulation strategy on load regulation;

[0061] The calculation formula for transmission cost is as follows: Where: A represents the number of transmission lines between two transmission areas; ω arepresents the construction and maintenance cost of the a-th transmission line; D a represents the current loss factor of the ath transmission line;

[0062] The calculation formula for emission costs is as follows: Where: emission represents the emission factor, the cost per unit of emission; V represents the energy type; γ v represents the carbon emission factor of the vth energy source; E v represents the carbon emission intensity of the vth energy source, which is affected by the power generation method (such as coal, natural gas, etc.); σ i It represents the environmental policy adjustment coefficient of region i, reflecting the subsidy or penalty of the policy on emission costs;

[0063] The specific formula for calculating transmission loss is: Where: loss represents the loss cost coefficient; represents the transmission loss efficiency of the ath transmission line; L a represents the loss value of the ath transmission line during the transmission process; ρ a It is the coefficient that indicates the increase of the loss of the ath transmission line, reflecting the additional loss in the case of long distance and high current of the transmission line.

[0064] In some embodiments, the pre-configured power dispatch constraints include power balance constraints, power exchange constraints, generator set operation constraints, energy storage system constraints, load regulation constraints, and load trading market constraints.

[0065] Specifically, the expression of the power balance constraint is: Among them, η ij represents the transmission line loss efficiency from region i to region j; represents the energy storage release power of area i;

[0066] The expression of the power exchange constraint is: in, represents the maximum allowable current of the transmission line from area i to area j; Z ij represents the equivalent impedance of the transmission line from area i to area j;

[0067] The expression of the generator set operation constraint is: in, represents the ramp rate limit of the generator set in area i; represents the minimum generating capacity of the generator set in area i; represents the maximum generating capacity of the generator set in area i;

[0068] The expression of the energy storage system constraint is: in, represents the maximum release power of energy storage in area i; represents the energy storage value of the energy storage device in area i at time t; η c represents the environmental coefficient of area i; η d Indicates the temperature coefficient of the energy storage device; represents the minimum energy storage value of the energy storage device in area i; Indicates the maximum energy storage value of the energy storage device in area i;

[0069] The expression of the load regulation constraint is: in, represents the minimum load regulation value of area i; represents the maximum load regulation value of area i; represents the load regulation rate limit of area i;

[0070] The load trading market constraints are specifically shown in the following formula: in, represents the load sold in area i at time t; represents the load purchased by region i at time t.

[0071] The profit calculation formula of the area in the load free trading market is: in, represents the market price of electricity sold in region i at time t; represents the load sold in area i at time t; represents the electricity sales transaction fee in area i; represents the fixed cost of electricity sales in region i; θ i represents the transaction penalty coefficient of region i; represents the market price of electricity purchased by region i at time t; represents the load purchased by region i at time t; represents the transaction fee for electricity purchase in area i; represents the fixed cost of region i when purchasing electricity.

[0072] Specifically: It represents the market price of electricity sold in region i at time t. The price is determined according to the dynamic pricing mechanism of the load market and may fluctuate over time and with supply and demand. It represents the load sold in region i at time t, subject to the excess power situation in the region. It represents the electricity sales transaction fee in region i, reflecting the fee ratio of the market intermediary in the electricity sales process; represents the fixed cost of electricity sales in region i, including electricity transmission, dispatching and management costs; θi Represents the transaction penalty coefficient of region i, which is used to constrain the market volatility risk or resource utilization caused by excessive transaction volume; It represents the market price of electricity purchased by region i at time t, which is usually higher than the electricity selling price, reflecting the contradiction between supply and demand and the market mechanism; It represents the load purchased by region i at time t, which is related to the load gap in the region and the transmission capacity of the power grid; represents the transaction fee for electricity purchase in area i; It represents the fixed cost of region i when purchasing electricity, including the cost of power reception, dispatching and system coordination.

[0073] S104, using the future load data, load data and electricity price data of each region as input parameters of the power optimization scheduling model, solving the power optimization scheduling model, and obtaining the power scheduling result; wherein the power scheduling result refers to the power generation and power exchange value of each region in each time period.

[0074] In this embodiment, combined with the objective function of the power optimization dispatch model described above, it can be known that the comprehensive cost of power dispatch refers to the power generation cost, load regulation cost, transmission cost, etc. of each region. Therefore, this embodiment uses the future load data, load data and electricity price data of each region as input parameters of the power optimization dispatch model, and then solves the model with the minimization of the objective function as the goal, so as to obtain the power generation of region i at all times and the cross-regional power exchange value.

[0075] Therefore, the power dispatch model constructed by the objective function and constraint conditions of multiple dispatch costs in this embodiment has higher optimization capability and system adaptability, and can achieve optimal dispatch in different scenarios, whether it is power production, market trading or power grid operation. For example, if the power generation in a certain area exceeds the load, the excess power generation in the area can be put on the load free trading market and purchased by the entities participating in the market, thereby achieving power optimization dispatch.

[0076] In some embodiments, the method further includes: constructing an error correction model to correct the errors in the power generation and power exchange value of each region in each time period.

[0077] Specifically, in the power system, due to the existence of uncertain factors such as load forecast errors, renewable energy fluctuations, market price changes, and transmission losses in the actual operation process, the power generation and power exchange values ​​calculated by the optimization model may deviate from the actual operation situation. These errors may cause local supply and demand imbalances and equipment overload problems, affecting the stability and economy of the power system.

[0078] Therefore, this embodiment introduces an error adjustment function to dynamically correct the power generation and power exchange values ​​of each region in each time period, which helps to reduce the impact of these errors and thus improve the safety and reliability of system operation; corrects the error in regional power generation to ensure the balance of power supply and demand in each region in each time period, and avoids problems such as voltage instability and power outages caused by insufficient power generation; corrects the error in power exchange to ensure the safety of cross-regional transmission lines and prevent chain failures caused by overload.

[0079] In this embodiment, the expression of the error correction model is: Where: X adj Indicates the error correction value; X opt represents the model input value; f ML represents a machine learning model (such as linear regression, LSTM or XGBoost), which is used to capture nonlinear error relationships; Y represents the objective function parameters (such as electricity price, load, environmental parameters); ξ represents auxiliary variables (such as historical data, external disturbances); ω represents the confidence of the machine learning model, reflecting the degree of trust in the machine learning model; N represents the length of the historical window; Indicates the actual value of the model input variable at time tn; represents the model input value at time tn; ∈ historical correction weight, used to smooth the error trend; α represents the adjustment coefficient, which ensures that the adjusted result is within an acceptable range; Indicates the sensitivity of the variable to the optimization objective.

[0080] Please refer to Figure 2 , Figure 2 The principle block diagram of the regional power dispatching device based on the load free trading market provided by the embodiment of the present invention is as follows: Figure 2 As shown, the device comprises:

[0081] The data acquisition module 210 is used to acquire the current load data of each region and the current electricity price data of the load free trading market;

[0082] The load forecasting module 230 is used to forecast the current load data of each region through a pre-configured load forecasting model to obtain the future load data of each region; wherein the load forecasting model is obtained by training a long short-term memory neural network through the historical load data of each region;

[0083] The dispatch model building module 240 is used to determine the objective function of minimizing the comprehensive cost of power dispatch, and to build a power optimization dispatch model according to the objective function and pre-configured power dispatch constraints;

[0084] The scheduling result determination module 250 is used to use the future load data, load data and electricity price data of each region as input parameters of the power optimization scheduling model, solve the power optimization scheduling model, and obtain the power scheduling result; wherein the power scheduling result refers to the power generation and power exchange value of each region in each time period.

[0085] A regional power dispatching device based on a load free trading market in an embodiment of the present application is Figure 1 The regional power dispatching method based on the load free trading market shown is a technical solution based on the same inventive concept. Through the detailed description of the regional power dispatching method based on the load free trading market provided in the above embodiment, technical personnel in this field can clearly understand the implementation process of the regional power dispatching device based on the load free trading market in this embodiment, so for the sake of conciseness of the specification, it will not be repeated here.

[0086] Accordingly, the regional power dispatching device based on the load free trading market provided in this embodiment can respond to power demand fluctuations and market uncertainties more accurately, maximize market profits, optimize power transmission, balance economic benefits and environmental protection goals, and provide strong support for the future development of smart grids and green energy.

[0087] An embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the regional power dispatching method based on the load free trading market as provided in the above embodiment is implemented.

[0088] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the regional power dispatching method based on a load free trading market as provided in the above embodiment.

[0089] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A regional power dispatching method based on a load free trading market, characterized in that: Methods include: Obtain the current load data of each region and the current electricity price data of the load free trading market; The current load data of each region is predicted by a pre-configured load prediction model to obtain the future load data of each region; wherein the load prediction model is obtained by training a long short-term memory neural network with the historical load data of each region; Determine the objective function of minimizing the comprehensive cost of power dispatch, and build a power optimization dispatch model based on the objective function and pre-configured power dispatch constraints; The future load data, load data and electricity price data of each region are used as input parameters of the power optimization scheduling model, the power optimization scheduling model is solved, and the power scheduling result is obtained; among which, the power scheduling result refers to the power generation and power exchange value of each region in each time period.

2. The method according to claim 1, characterized in that The expression of the objective function is: in, represents the power generation of the ith region at time t; C G,i represents the power generation cost of the ith region; represents the forecast load of the ith region at time t; U i represents the load regulation cost of the ith region; represents the cross-region power exchange value between the ith region and the jth region at time t; C T,ij represents the transmission cost between the i-th region and the j-th region; E represents the emission cost; λ e represents the emission cost weight; Loss represents the transmission loss; λ l represents the transmission loss weight; R i Represents the revenue of the ith region in the load trading market.

3. The method according to claim 1, characterized in that The pre-configured power dispatch constraints include power balance constraints, power exchange constraints, generator set operation constraints, energy storage system constraints, load regulation constraints and load trading market constraints.

4. The method according to claim 3, characterized in that The expression of the power balance constraint is: Among them, η ij represents the transmission line loss efficiency from region i to region j; represents the energy storage release power of area i; The expression of the power exchange constraint is: in, represents the maximum allowable current of the transmission line from area i to area j; Z ij represents the equivalent impedance of the transmission line from area i to area j; The expression of the generator set operation constraint is: in, represents the ramp rate limit of the generator set in area i; represents the minimum generating capacity of the generator set in area i; represents the maximum generating capacity of the generator set in area i; The expression of the energy storage system constraint is: in, represents the maximum release power of energy storage in area i; represents the energy storage value of the energy storage device in area i at time t; η c represents the environmental coefficient of area i; η d Indicates the temperature coefficient of the energy storage device; represents the minimum energy storage value of the energy storage device in area i; Indicates the maximum energy storage value of the energy storage device in area i; The expression of the load regulation constraint is: in, Indicates the minimum load adjustment value of area i; represents the maximum load regulation value of area i; represents the load regulation rate limit of area i; The load trading market constraints are specifically shown in the following formula: in, represents the load sold in area i at time t; represents the load purchased by region i at time t.

5. The method according to claim 4, characterized in that The profit calculation formula of the area in the load free trading market is: in, represents the market price of electricity sold in region i at time t; represents the load sold in area i at time t; represents the electricity sales transaction fee in area i; represents the fixed cost of electricity sales in region i; θ i represents the transaction penalty coefficient of region i; represents the market price of electricity purchased by region i at time t; represents the load purchased by region i at time t; represents the transaction fee for electricity purchase in area i; represents the fixed cost of region i when purchasing electricity.

6. The method according to claim 1, characterized in that The method further comprises: constructing an error correction model to correct the errors of the power generation and power exchange value of each area in each time period.

7. The method according to claim 6, characterized in that The expression of the error correction model is: Among them, X adj Indicates the error correction value; X opt represents the model input value; f ML represents the machine learning model; Y represents the objective function parameter; ξ represents the auxiliary variable; ω represents the confidence of the machine learning model; N represents the length of the historical window; Indicates the actual value of the input variable at time tn; Represents the input value at time tn; ∈ is the historical correction weight; α represents the adjustment coefficient.

8. A regional power dispatching device based on a load free trading market, characterized in that: The device includes: The data acquisition module is used to obtain the current load data of each region and the current electricity price data of the load free trading market; The load forecasting module is used to forecast the current load data of each region through a pre-configured load forecasting model to obtain the future load data of each region; wherein the load forecasting model is obtained by training a long short-term memory neural network through the historical load data of each region; The dispatch model building module is used to determine the objective function of minimizing the comprehensive cost of power dispatch, and to build a power optimization dispatch model based on the objective function and pre-configured power dispatch constraints; The scheduling result determination module is used to use the future load data, load data and electricity price data of each region as input parameters of the power optimization scheduling model, solve the power optimization scheduling model, and obtain the power scheduling result; wherein the power scheduling result refers to the power generation and power exchange value of each region in each time period.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the regional power dispatching method based on the load free trading market as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the regional power dispatching method based on the load free trading market as described in any one of claims 1 to 7 is implemented.

Images