A distribution network operation optimization method and system based on dynamic electricity price

Abstract

The present invention relates to the technical field of distribution network data processing, and in particular to a method and system for optimizing distribution network operation based on dynamic electricity pricing. The method comprises the following steps: obtaining an initial acceptance probability at each moment by collecting the difference between the electricity price and electricity consumption at the moment and the historical electricity price and electricity consumption; presetting an initial current solution at a moment, constructing an objective function for the solution at that moment, and randomly selecting a solution from the neighboring solution set of the current solution as a new solution; calculating the acceptance probability of the new solution in each iteration at that moment; obtaining a new current solution based on the acceptance probability of the new solution when the objective function value of the new solution is greater than the objective function value of the current solution; and iteratively obtaining the purchased electricity quantity at that moment to optimize the distribution network operation and effectively improve the operating efficiency of the distribution network based on dynamic electricity pricing.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network data processing, and in particular to a distribution network operation optimization method and system based on dynamic electricity prices. Background Art

[0002] To reduce carbon emissions and optimize the electricity market, a dynamic electricity pricing mechanism has been proposed. This mechanism reflects the supply and demand conditions in the electricity market. Users adjust their electricity purchases based on price signals, ensuring a stable energy supply even when electricity supply fluctuates and prices fluctuate. This reduces unnecessary electricity consumption and optimizes the allocation of electricity resources.

[0003] The patent application document with publication number CN112990600A discloses a microgrid optimization scheduling method based on a linearization method of a price discrete matrix. The application is applied to a microgrid optimization scheduling model based on dynamic time-of-use electricity prices. By introducing a price discrete matrix, the multiplication problem of real variables of purchase and sale electricity prices and electricity volume is converted into the multiplication problem of 0-1 variables and real variables. Then, by establishing Big-M constraints, the problem is further converted into a linear programming problem, and finally the mixed integer nonlinear programming problem is converted into a mixed integer linear programming problem.

[0004] The above-mentioned existing technology simplifies the microgrid optimization scheduling model through a linearization method. In a scenario where electricity prices fluctuate frequently, the linearization method may not be able to quickly adjust the power purchase strategy, and ignores the difficulty of calculating the user's purchase amount under dynamic electricity prices. The user's purchase amount is regarded as a known quantity, resulting in the inability to accurately realize the scheduling of the power grid based on dynamic electricity prices and user purchase amounts.

[0005] Based on this, how to accurately optimize the operation of the distribution network based on dynamic electricity prices is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] In order to solve the technical problem of how to accurately achieve distribution network operation optimization based on dynamic electricity prices, the present invention provides a distribution network operation optimization method and system based on dynamic electricity prices.

[0007] In a first aspect, the present invention provides a method for optimizing distribution network operation based on dynamic electricity pricing, which adopts the following technical solutions:

[0008] A method for optimizing distribution network operation based on dynamic electricity pricing comprises the following steps:

[0009] The initial acceptance probability at each moment is obtained by comparing the difference between the electricity price and electricity consumption at the acquisition moment and the historical electricity price and electricity consumption. The initial current solution at a moment is preset, the objective function of the solution at that moment is constructed, and a solution is randomly selected from the neighboring solution set of the current solution as the new solution.

[0010] ;

[0011] is the acceptance probability of the new solution in the j-th iteration at that moment, is the initial acceptance probability at that moment, is the variance of the current solution in the jth iteration at that moment and the current solution in the previous three iterations, 、 are the objective function values ​​of the new solution and the current solution in the j-th iteration at that moment, respectively. is the linear normalization function, is an exponential function with base e. When the objective function value of the new solution is greater than that of the current solution, a new current solution is obtained based on the acceptance probability of the new solution. The power purchase amount at that moment is obtained by iteration to achieve the optimization of distribution network operation.

[0012] The present invention obtains the current amount of electricity purchased through a random hill climbing algorithm, so that the distribution network can accurately distribute electricity based on the amount of electricity purchased. In this process, the present invention takes into account that the accuracy of the acceptance probability of the new solution set during the iteration of the random hill climbing algorithm is low and is easily affected by the quality of the data; based on this, the present invention obtains the initial acceptance probability by analyzing the difference between the electricity price and electricity consumption at the current moment and the historical collection moment, so that the initial acceptance probability depends on the actual data situation, thereby improving the accuracy of the initial acceptance probability and effectively improving the operating efficiency of the distribution network. On this basis, the present invention also takes into account that relying solely on the actual data situation may cause some new solutions of poor quality to be accepted as new current solutions; based on this, the present invention corrects the initial acceptance probability by analyzing the difference in the objective function values ​​of the current solution and the new solution during the iteration process, and can accurately obtain the acceptance probability of the new solution in each iteration, thereby accurately obtaining the current amount of electricity purchased, effectively improving the operating efficiency of the distribution network.

[0013] According to a distribution network operation optimization method based on dynamic electricity prices provided by the present invention, the initial acceptance probability at each moment is obtained by collecting the difference between the electricity price and electricity consumption at the moment and the historical electricity price and electricity consumption. The method also includes: obtaining electricity price data and electricity consumption data at each collection moment, and obtaining the electricity price and electricity consumption at each collection moment after preprocessing; obtaining the electricity purchase moment and the purchase amount at each moment.

[0014] The present invention takes into account the possibility of missing data and large differences in data values ​​of different types in the original collected data, so the data is preprocessed to facilitate subsequent data analysis.

[0015] According to a distribution network operation optimization method based on dynamic electricity pricing provided by the present invention, the initial acceptance probability at each moment is obtained by collecting the difference between the electricity price and electricity consumption at the moment and the historical electricity price and electricity consumption, including:

[0016] ;

[0017] is the initial acceptance probability at a moment, is the absolute value of the price difference between the current moment and the last updated price, is the absolute value of the difference between the current moment and the average price of electricity after 5 updates before this moment, is the absolute value of the difference in power consumption between the two collection moments before this moment, is the average power consumption of the five collection moments before the last collection moment. is a hyperparameter, is a linear normalization function.

[0018] The present invention obtains the prominence of the current electricity price and electricity consumption by analyzing the difference between the current electricity price and electricity consumption and the historical electricity price and electricity consumption. The higher the prominence, the more difficult it is to predict the electricity purchase amount at the current moment, and therefore the corresponding initial acceptance probability should also be higher, so that the global optimal solution at the current moment can be accurately obtained.

[0019] According to a distribution network operation optimization method based on dynamic electricity pricing provided by the present invention, the objective function of the solution at this moment is constructed, including:

[0020] ;

[0021] is the objective function value of the solution at that moment, To solve the corresponding power purchase amount, is the electricity price at that moment, is the amount of electricity purchased at the same historical moment with the same storage capacity and electricity price at that moment, is a linear normalization function.

[0022] By analyzing the electricity purchase cost of the solution at the current moment, the present invention can accurately obtain the objective function value corresponding to each solution at the current moment. The objective function value is negatively correlated with the preference of the solution. When selecting a new current solution in the subsequent step, an evaluation can be performed based on the preference of the solution, wherein the solution can include the new solution and the current solution.

[0023] According to a distribution network operation optimization method based on dynamic electricity prices provided by the present invention, the method for obtaining the neighbor solution set of the current solution includes: presetting the fluctuation range of the current solution, and forming the neighbor solution set of the current solution from all integers within the fluctuation range of the current solution.

[0024] According to a distribution network operation optimization method based on dynamic electricity prices provided by the present invention, when the objective function value of the new solution is greater than the objective function value of the current solution, a new current solution is obtained based on the acceptance probability of the new solution, and the method also includes: when the objective function value of the new solution is not greater than the objective function value of the current solution, the new solution is used as the new current solution.

[0025] According to a distribution network operation optimization method based on dynamic electricity prices provided by the present invention, the iterative method obtains the purchased electricity amount at the moment, including: presetting the number of iterations; and using the purchased electricity amount corresponding to the new current solution obtained from the last iteration as the purchased electricity amount at the moment.

[0026] According to a distribution network operation optimization method based on dynamic electricity prices provided by the present invention, the iterative method obtains the power purchase amount at that moment to achieve distribution network operation optimization, including: the distribution network allocates corresponding power based on the power purchase amount at that moment.

[0027] According to a distribution network operation optimization method based on dynamic electricity price provided by the present invention, the method for achieving distribution network operation optimization further includes: generating a user report based on the corresponding power purchase amount at each time.

[0028] The present invention takes into account that optimizing the operation of the distribution network depends not only on the current amount of electricity purchased, but also on the actual electricity consumption of the target object. Therefore, by generating a user report to analyze the electricity consumption of the target object, it is convenient to subsequently optimize the operation of the distribution network based on the electricity consumption of the target object.

[0029] In a second aspect, the present invention provides a distribution network operation optimization system based on dynamic electricity pricing, which adopts the following technical solutions:

[0030] A distribution network operation optimization system based on dynamic electricity prices includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the distribution network operation optimization method based on dynamic electricity prices is implemented.

[0031] By adopting the above technical solution, the above-mentioned distribution network operation optimization method based on dynamic electricity prices is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made based on the memory and the processor for easy use.

[0032] The present invention has the following technical effects:

[0033] Based on the above technical solution, the present invention provides a distribution network operation optimization method and system based on dynamic electricity pricing. During the operation of the distribution network, a random hill climbing algorithm is used to obtain the current amount of electricity purchased, so that the distribution network can accurately allocate electricity based on the amount of electricity purchased. In this process, the present invention takes into account that the acceptance probability of the new solution set during the random hill climbing algorithm iteration is less accurate and easily affected by data quality. Based on this, the present invention obtains the initial acceptance probability by analyzing the difference between the electricity price and electricity consumption at the current moment and the historical collection moment. This makes the initial acceptance probability dependent on the actual data, improves the accuracy of the initial acceptance probability, and effectively improves the distribution network operation efficiency. On this basis, the present invention also considers that relying solely on the actual data may result in some new solutions of poor quality being accepted as the new current solution. Based on this, the present invention corrects the initial acceptance probability by analyzing the difference in the objective function values ​​of the current solution and the new solution during the iteration process, and can accurately obtain the acceptance probability of the new solution in each iteration, thereby accurately obtaining the current amount of electricity purchased, effectively improving the distribution network operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flow chart of a method for optimizing distribution network operation based on dynamic electricity pricing is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0036] When the distribution network allocation to the target object is accurately realized based on the dynamic electricity price, the electricity allocation can be carried out based on the electricity purchase amount of the target object.

[0037] Based on this, an embodiment of the present invention discloses a distribution network operation optimization method based on dynamic electricity prices. This method accurately obtains the target object's current electricity purchase amount by analyzing the target object's historical electricity consumption data and dynamic changes in electricity prices, and allocates power resources based on the target object's current electricity purchase amount. This can reduce power consumption and resource waste, and effectively improve the distribution network operation efficiency.

[0038] For details, please refer to Figure 1 As shown, Figure 1 A flow chart of a method for optimizing distribution network operation based on dynamic electricity pricing is provided in an embodiment of the present invention. The method specifically includes the following steps.

[0039] S1: Obtain the electricity price, electricity consumption, and electricity purchase amount at each collection moment.

[0040] It should be noted that based on the preset collection frequency, the electricity price and target object's electricity consumption at each collection moment can be obtained. The electricity price and electricity consumption corresponding to each collection moment are used as a data point to obtain a set of time series. However, the target object's electricity purchasing behavior is generally random, and not every collection moment will have corresponding user purchase data. Therefore, the embodiment of the present invention analyzes the user's purchase data as an individual entity to obtain each time when the user purchases electricity and the corresponding purchase amount.

[0041] For example, in an embodiment of the present invention, the electricity price, electricity consumption, and electricity purchase amount at each collection moment are obtained, including: obtaining electricity price data and electricity consumption data at each collection moment, and obtaining the electricity price and electricity consumption at each collection moment after preprocessing; obtaining the electricity purchase moment and the electricity purchase amount at each moment.

[0042] Among them, the preprocessing can be missing data processing, data normalization processing, etc., which can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0043] Specifically, the electricity price and electricity consumption of the target object are collected at each collection moment based on a preset collection frequency, and each moment when the target object purchases electricity and the corresponding purchased electricity amount are obtained.

[0044] The acquisition frequency can be set to once per minute, and can be set according to actual needs.

[0045] The target object may be a community, which may be set according to actual needs.

[0046] It can be understood that the collection time mentioned later in the embodiment of the present invention is the collection time of electricity price and / or electricity consumption, and the time is the electricity purchase time of the target object.

[0047] The randomized hill climbing algorithm, also known as the randomized hill climbing method, is a heuristic search algorithm used to iteratively search for the global optimal solution in the solution space. During the iteration process, in order to avoid falling into the local optimal solution, the algorithm randomly selects a solution from the neighboring solution set of the current solution as the new solution, and obtains the final current solution based on the acceptance probability of the new solution.

[0048] Based on this, the embodiment of the present invention uses a random hill climbing algorithm to iteratively obtain the optimal solution based on the acceptance probability of the solution in the neighbor solution set at the current moment, and finally obtains the power purchase amount corresponding to the optimal solution, that is, performs the following steps.

[0049] S2: The initial acceptance probability at each moment is obtained by collecting the difference between the electricity price and electricity consumption at the moment and the historical electricity price and electricity consumption.

[0050] It should be noted that the random hill climbing algorithm sets an acceptance probability for a new solution randomly selected from the neighboring solution set. If the evaluation function of the new solution is greater than the evaluation function of the current solution, the new solution is selected as the new current solution. Otherwise, the new solution is accepted as the new current solution based on the acceptance probability of the new solution. The conventional way to set the acceptance probability is to compare the quality of the current solution with its neighboring solution set. This method has high requirements for the quality of the neighboring solution set. When the quality of the neighboring solution is high, the difference between the neighboring solution and the current solution can accurately reflect the optimization direction of the problem. The acceptance probability set based on the difference can guide the algorithm to approach the global optimal solution. If the quality of the neighboring solution is low, and there is a lot of noise or misleading information, it may cause the algorithm to deviate from the correct direction during the search process.

[0051] Based on this, in the embodiment of the present invention, during the process of iteratively determining the power purchase amount corresponding to the global optimal solution at the current moment, the initial acceptance probability at the moment is obtained by analyzing the electricity price fluctuations and the historical electricity consumption of the target object, so that the initial acceptance probability of the new solution at the current moment depends on the actual data changes, thereby accurately obtaining the value of the initial acceptance probability.

[0052] For example, in an embodiment of the present invention, the initial acceptance probability at each moment is obtained by calculating the difference between the electricity price and electricity consumption at the acquisition moment and the historical electricity price and electricity consumption. For details, see the following relationship:

[0053] ;

[0054] is the initial acceptance probability at a moment, is the absolute value of the price difference between the current moment and the last updated price, is the absolute value of the difference between the current moment and the average price of electricity after 5 updates before this moment, is the absolute value of the difference in power consumption between the two collection moments before this moment, is the average power consumption of the five collection moments before the last collection moment. is a hyperparameter, is a linear normalization function.

[0055] Among them, the hyperparameters are The purpose of this is to avoid the situation where the current electricity price is the same as the last updated electricity price, which makes the formula meaningless. That is, the electricity price has not changed since the last update. The hyperparameters are This is to avoid the situation where the absolute value of the difference between the current time and the average of the five previous electricity prices is the same, that is, the current time and the electricity prices after the five previous updates have not changed. The value of the hyperparameter can be set to 0.01. The value of the hyperparameter can be set according to actual needs and is not limited in this embodiment of the present invention.

[0056] It is understandable that electricity prices are affected by many factors. The updated electricity price may be the same as the original price or may change. Therefore, if the current price is the same as the price after the previous five updates, then is 0.

[0057] In the above formula, It indicates the prominence of the electricity price at the current moment. The greater the prominence of the electricity price, the greater the fluctuation of the electricity price, and the more difficult it is to predict the target object's electricity purchase amount at the current moment. In order to accurately obtain the global optimal solution, it is necessary to increase the acceptance probability of the new solution, and the corresponding initial acceptance probability is also larger.

[0058] It indicates the credibility of the prominence of the electricity price at the current moment. The larger the value, the higher the credibility of the prominence of the electricity price, and the greater the corresponding initial acceptance probability.

[0059] Indicates the prominence of electricity consumption at the current moment. The larger the value, the greater the difference in electricity consumption between the current moment and the previous collection moment. The more difficult it will be to predict the target object's electricity purchase amount at the current moment. In order to accurately obtain the global optimal solution, it is necessary to increase the acceptance probability of the new solution, and the corresponding initial acceptance probability will also be larger.

[0060] It indicates the credibility of the prominence of electricity consumption at the current moment. The larger the value, the higher the credibility of the prominence of electricity consumption at the current moment, and the corresponding initial acceptance probability is also greater.

[0061] Take an example to illustrate some parameters in the above formula: the collection moments are collection moment 1 to collection moment 9. If the current moment is between collection moment 8 and collection moment 9, then the previous collection moment of the current moment is collection moment 8; the two collection moments before the current moment are collection moment 8 and collection moment 7; the five collection moments before the previous collection moment of the current moment are collection moment 3 to collection moment 7. Based on the power consumption at each collection moment, the current moment's and .

[0062] If the current moment is the same as collection moment 8, that is, the current moment and collection moment 8 are the same moment, then the previous collection moment of the current moment is collection moment 7; the two collection moments before the current moment are collection moment 7 and collection moment 6; the five collection moments before the previous collection moment of the current moment are collection moment 2 to collection moment 6.

[0063] For example, when calculating the initial acceptance probability at the current moment, if the number of collection moments before the current moment is insufficient, the number of collection moments actually collected is used for calculation. The specific setting can be made according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0064] It should be noted that the above method can be used to obtain the initial acceptance probability at the current moment. The larger the initial acceptance probability, the more likely the current solution will accept the new solution, making the algorithm more random and less likely to fall into a local optimal solution. However, the above method only considers the changes in electricity prices and electricity consumption in the historical period before the current moment when calculating the initial acceptance probability, ignoring the actual changes during the iteration process. If the initial acceptance probability is too large, a new solution of poor quality may be accepted as the new current solution, affecting the accuracy of the final purchased electricity quantity.

[0065] Based on this, the embodiment of the present invention can obtain the difference in evaluation functions between the current solution and the new solution at the current moment in the iterative process, correct the initial acceptance probability at the current moment, and thus accurately obtain the acceptance probability of the new solution at the current moment, that is, continue to execute the following steps.

[0066] S3: Preset the current solution at an initial moment, construct the objective function of the solution at that moment, randomly select a solution from the neighbor solution set of the current solution as the new solution, and calculate the acceptance probability of the new solution.

[0067] Among them, the initial current solution at a moment can be set to 100,000, with the unit being kilowatt-hour; the value of the initial current solution can be set specifically according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0068] It should be noted that the objective function of the solution constructed in the embodiment of the present invention is the evaluation function of the solution, and the initial acceptance probability can be corrected by the difference between the objective functions of the current solution and the new solution.

[0069] For example, in an embodiment of the present invention, a method for obtaining a neighbor solution set of a current solution includes: presetting a fluctuation range of the current solution, and forming a neighbor solution set of the current solution from all integers within the fluctuation range of the current solution.

[0070] Among them, the fluctuation range of the current solution can be set to the current solution , the unit is kilowatt-hour; the fluctuation range can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0071] For example, if the current solution is 100,000 kWh, then its corresponding fluctuation range is 95,000 kWh to 105,000 kWh. All integers between 95,000 kWh and 105,000 kWh are taken as the neighbor solution set of the current solution. The obtained neighbor solution set includes 95,000 kWh and 105,000 kWh.

[0072] After obtaining the neighbor solution set of the current solution based on the above steps, the objective function can be constructed for each solution.

[0073] For example, in an embodiment of the present invention, the objective function of the solution at this moment is constructed, and the specific relationship can be seen in the following formula:

[0074] ;

[0075] is the objective function value of the solution at that moment, To solve the corresponding power purchase amount, is the electricity price at that moment, is the amount of electricity purchased at the same historical moment with the same storage capacity and electricity price at that moment, is the linear normalization function, is the absolute value symbol.

[0076] In the above formula, It indicates the electricity purchase cost corresponding to a solution at the current moment. The larger the value, the greater the electricity purchase cost corresponding to the solution. Therefore, the lower the preference of the solution, the smaller the corresponding objective function value.

[0077] This is the difference between the current solution's purchased electricity and the corresponding purchased electricity at a historical time with the same storage capacity and electricity price. Storage and purchased electricity complement each other in a community's distribution network. Storage equipment can provide power during power shortages or peak electricity prices, while purchased electricity ensures the stability of power supply under normal circumstances. Therefore, a larger value indicates a greater difference between the current solution's purchased electricity and the corresponding purchased electricity at historical times under the same conditions. This also indicates a greater difference between the solution and the optimal solution, a larger corresponding objective function value, and a lower preference.

[0078] For example, if there is more than one historical moment with the same storage capacity and electricity price corresponding to the current moment, the historical moment closest to the current moment will be taken as the historical moment with the same storage capacity and electricity price corresponding to the current moment; if there is no historical moment with the same storage capacity and electricity price corresponding to the current moment, the storage capacity and electricity price of a moment can be selected within a preset error range as the historical moment.

[0079] The preset error range of the storage capacity can be the current storage capacity. , the unit is kilowatt-hour, the preset error range of the electricity price can be the current electricity price , in units of RMB / kWh; it can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this. If the current moment does not have a corresponding historical moment within the error range, you can Set to 1.

[0080] It can be understood that the larger the objective function value of a solution is, the smaller the probability that the solution is the global optimal solution is, and the corresponding preference degree is also lower.

[0081] For example, in an embodiment of the present invention, the acceptance probability of a new solution in each iteration at each moment is determined, and the details can be seen in the following relationship:

[0082] ;

[0083] is the acceptance probability of the new solution in the j-th iteration at that moment, is the initial acceptance probability at that moment, is the variance of the current solution in the jth iteration at that moment and the current solution in the previous three iterations, is the objective function value of the new solution in the j-th iteration at that moment, is the objective function value of the current solution in the j-th iteration at that moment, is the linear normalization function, is an exponential function with base e.

[0084] It can be understood that the current solutions in the first three iterations of the j-th iteration at the current moment are sequence Second and The current solution in iterations.

[0085] In the above formula, the smaller the variance between the current solution in the j-th iteration at the current moment and the current solution in the previous three iterations, the greater the probability that the algorithm will fall into a local optimal solution. In this case, it is necessary to give a greater acceptance probability to the new solution so that the algorithm can jump out of the local optimal solution and have higher flexibility.

[0086] It represents the difference between the objective function value of the new solution in the j-th iteration at the current moment and the objective function value of the current solution. The larger the value, the lower the preference of the new solution in the j-th iteration at the current moment is, and the smaller the corresponding acceptance probability is. By constraining the solution, the possibility of taking a new solution with poor quality as the new current solution can be reduced, and the accuracy of the probability of accepting the new solution in this iteration can be improved.

[0087] Take an example to illustrate some parameters in the above formula: , then it is the 6th iteration at the current moment. The previous 3 current solutions of the current solution in the 6th iteration are the current solution after the 5th iteration at the current moment, the current solution after the 4th iteration, and the current solution after the 3rd iteration. is the variance of the current solution after the 6th, 5th, 4th, and 3rd iterations at the current moment. If the number of iterations at the current moment is not greater than 3, then Set to 1.

[0088] After obtaining the acceptance probability of the new solution in each iteration process at the current moment based on the above steps, the new current solution after each iteration can be obtained based on the acceptance probability of the new solution during the iteration process, and finally the power purchase amount corresponding to the global optimal solution at the current moment is obtained, that is, the following steps are executed.

[0089] S4: When the objective function value of the new solution is greater than the objective function value of the current solution, a new current solution is obtained based on the acceptance probability of the new solution.

[0090] It should be noted that if the objective function value of the new solution is greater than that of the current solution, when a new current solution is obtained based on the acceptance probability of the new solution, the new current solution may be the current solution or the new solution. The objective function values ​​of both the current solution and the new solution can be obtained using the objective function constructed in the above steps.

[0091] For example, when a new current solution is obtained based on the acceptance probability of the new solution, if the new current solution is the current solution, the neighbor solution set is further constructed based on the current solution; if the new current solution is the new solution, the neighbor solution set is further constructed based on the new solution.

[0092] For example, in an embodiment of the present invention, when the objective function value of the new solution is greater than the objective function value of the current solution, a new current solution is obtained based on the acceptance probability of the new solution, and it also includes: when the objective function value of the new solution is not greater than the objective function value of the current solution, the new solution is used as the new current solution.

[0093] It can be understood that when the random hill climbing algorithm obtains the current electricity purchase amount, it iteratively obtains a solution with a higher evaluation function as the current solution. The smaller the objective function value of the solution constructed based on the above steps, the higher the preferred degree of the solution and the higher the evaluation function. Therefore, if the objective function value of the new solution is not greater than the objective function value of the current solution, it means that the new solution is more preferred than the current solution. In this case, the new solution can be used as the new current solution.

[0094] After obtaining the new current solution in the current iteration based on the above steps, continue to perform the following steps.

[0095] S5: Iterate to obtain the power purchase amount at that moment to optimize the operation of the distribution network.

[0096] For example, in an embodiment of the present invention, the new solution is used as the current solution, and the purchased electricity amount at that moment is obtained by iteration, including: presetting the number of iterations; and using the purchased electricity amount corresponding to the new current solution obtained by the last iteration as the purchased electricity amount at that moment.

[0097] The number of iterations may be preset to 50 times; the number of iterations may be set according to actual needs, and the embodiment of the present invention does not impose any excessive restrictions on this.

[0098] For example, in an embodiment of the present invention, the new solution is used as the current solution, and the power purchase amount at that moment is iteratively obtained to achieve distribution network operation optimization, including: the distribution network allocates corresponding power based on the power purchase amount at that moment.

[0099] It is understandable that after the target distribution network purchases the electricity, it will allocate the purchased electricity based on factors such as the user's electricity load, electricity consumption time, and electricity consumption location. The specific settings can be made according to actual needs, and the embodiments of the present invention do not impose too many restrictions on this.

[0100] For example, in an embodiment of the present invention, the operation optimization of the distribution network is achieved, and then the method further includes: generating a user report based on the corresponding power purchase amount at each time.

[0101] In this way, by generating user reports, we can analyze the amount of electricity purchased by users at different times, identify peak and low periods of electricity consumption, and take corresponding measures to optimize electricity consumption behavior.

[0102] It can be seen that in the embodiment of the present invention, when optimizing the distribution network operation based on dynamic electricity prices, the initial acceptance probability at each moment can be obtained by collecting the difference between the electricity price and electricity consumption at the moment and the historical electricity price and electricity consumption; a current solution at an initial moment is preset, the objective function of the solution at that moment is constructed, and a solution is randomly selected from the neighboring solution set of the current solution as a new solution;

[0103] ;

[0104] is the acceptance probability of the new solution in the j-th iteration at that moment, is the initial acceptance probability at that moment, is the variance of the current solution in the jth iteration at that moment and the current solution in the previous three iterations, 、 are the objective function values ​​of the new solution and the current solution in the j-th iteration at that moment, respectively. is the linear normalization function, is an exponential function with base e. When the objective function value of the new solution is greater than that of the current solution, a new current solution is obtained based on the acceptance probability of the new solution. The power purchase amount at that moment is obtained by iteration to optimize the operation of the distribution network and effectively improve the operation efficiency of the distribution network based on dynamic electricity prices.

[0105] An embodiment of the present invention also discloses a distribution network operation optimization system based on dynamic electricity prices, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a distribution network operation optimization method based on dynamic electricity prices provided by the present invention is implemented.

[0106] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0107] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0108] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A distribution network operation optimization method based on dynamic electricity price, characterized in that: include: The initial acceptance probability at each moment is obtained by calculating the difference between the electricity price and electricity consumption at the time of collection and the historical electricity price and electricity consumption, including: ； is the initial acceptance probability at a moment, is the absolute value of the price difference between the current moment and the last updated price, is the absolute value of the difference between the current moment and the average price of electricity after 5 updates before this moment, is the absolute value of the difference in power consumption between the two collection moments before this moment, is the average power consumption of the five collection moments before the last collection moment. is a hyperparameter, is a linear normalization function; Preset the current solution at a certain moment and construct the objective function of the solution at that moment, including: ； is the objective function value of the solution at that moment, To solve the corresponding power purchase amount, is the electricity price at that moment, is the amount of electricity purchased at the same historical moment with the same storage capacity and electricity price at that moment, is a linear normalization function; Randomly select a solution from the neighboring solution set of the current solution as the new solution; ； is the acceptance probability of the new solution in the j-th iteration at that moment, is the initial acceptance probability at that moment, is the variance of the current solution in the jth iteration at that moment and the current solution in the previous three iterations, 、 are the objective function values ​​of the new solution and the current solution in the j-th iteration at that moment, respectively. is an exponential function with base e; When the objective function value of the new solution is greater than that of the current solution, a new current solution is obtained based on the acceptance probability of the new solution; the power purchase amount at that moment is obtained iteratively to achieve distribution network operation optimization.

2. A method for optimizing distribution network operation based on dynamic electricity pricing according to claim 1, characterized in that: The method for obtaining the neighbor solution set of the current solution includes: The fluctuation range of the current solution is preset, and all integers within the fluctuation range of the current solution constitute the neighbor solution set of the current solution.

3. The method for optimizing distribution network operation based on dynamic electricity price according to claim 1, characterized in that: When the objective function value of the new solution is greater than the objective function value of the current solution, obtaining a new current solution based on the acceptance probability of the new solution further includes: If the objective function value of the new solution is not greater than the objective function value of the current solution, the new solution is used as the new current solution.

4. The method for optimizing distribution network operation based on dynamic electricity pricing according to claim 1, characterized in that: The iterative process of obtaining the amount of electricity purchased at that moment includes: Preset number of iterations; The purchased electricity amount corresponding to the new current solution obtained in the last iteration is used as the purchased electricity amount at that moment.

5. The method for optimizing distribution network operation based on dynamic electricity pricing according to claim 1, characterized in that: The iteration to obtain the power purchase amount at that moment to optimize the operation of the distribution network includes: The distribution network allocates the corresponding amount of electricity based on the amount of electricity purchased at that moment.

6. The method for optimizing distribution network operation based on dynamic electricity pricing according to claim 1, characterized in that: The above-mentioned implementation of the distribution network operation optimization further includes: Generate user reports based on the amount of electricity purchased at each time.

7. A distribution network operation optimization system based on dynamic electricity price, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a distribution network operation optimization method based on dynamic electricity price according to any one of claims 1 to 6 is implemented.

Images