A method, device, equipment and medium for optimizing and dispatching power load in a park

Abstract

The present invention discloses a method, device, equipment and medium for optimizing and dispatching power load in a park. The method includes: extracting characteristic vectors of power load data of each incoming line in the park and performing cluster analysis to determine the typical daily operation scene of each incoming line in the park; determining the typical daily carbon emissions according to the typical daily operation scene and carbon emission factor of each incoming line in the park, and then determining the annual total carbon emissions, and determining the typical daily carbon emission quota of each incoming line in the park according to the ratio of the two and the preset annual total carbon emission quota; taking the highest power comfort and the lowest power cost as the objective function, constructing the power load optimization dispatching model of each incoming line in the park, and solving it according to the typical daily carbon emission quota, transferable load constraint condition, shiftable load constraint condition and reducible load constraint condition, and obtaining the power load optimization dispatching result. The present invention can realize the optimized dispatching of power load that meets the carbon emission quota requirements and has high power comfort and low power cost.

Description

Technical Field

[0001] The present invention relates to the technical field of power consumption optimization scheduling, and in particular to a method, device, terminal equipment and computer-readable storage medium for optimizing and scheduling power loads in a park. Background Art

[0002] With the intensification of global climate change, carbon emission quota management and electricity load optimization scheduling have become important issues facing my country. As the basic core unit for the development of my country's industrial agglomeration, the "dual carbon" construction within the industrial park plays a vital role in the realization of my country's overall "dual carbon" goals. When the existing technology optimizes the electricity load scheduling for various scenarios in the park, it usually does not take into account the park's carbon emission quota, and it is impossible to quantify the carbon emission quota indicators into the park's electricity load optimization scheduling strategy. Summary of the invention

[0003] The present invention provides a method, device, equipment and medium for optimizing and scheduling power load in a park. Based on the typical daily operation scenarios of each incoming line in the park, the carbon emission quota of each incoming line in the park can be reasonably allocated. At the same time, multiple optimization objectives are considered when constructing a power load optimization scheduling model, and the model is solved with the carbon emission quota as a constraint condition, so as to obtain a power load optimization scheduling result that meets the carbon emission quota requirements and has high power comfort and low power cost.

[0004] In order to solve the above technical problems, a first aspect of an embodiment of the present invention provides a method for optimizing and scheduling power load in a park, comprising the following steps:

[0005] Cleaning and feature extraction are performed on the power load data of each incoming line in the park to obtain feature vectors of each incoming line in the park;

[0006] Performing cluster analysis on the characteristic vectors of each incoming line of the park to determine a typical daily operation scenario of each incoming line of the park; wherein the typical daily operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day;

[0007] Determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, and determine the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park;

[0008] Determine the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and the preset annual total carbon emission quota;

[0009] Taking the highest electricity comfort and the lowest electricity cost as the objective function, an electricity load optimization scheduling model for each incoming line of the park is constructed, and according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, the constraints of the electricity load optimization scheduling model are determined, and the electricity load optimization scheduling model is solved according to the constraints to obtain the electricity load optimization scheduling results of each incoming line of the park.

[0010] As a preferred solution, the power load data of each incoming line in the park is cleaned and feature extracted to obtain the feature vector of each incoming line in the park, which specifically includes the following steps:

[0011] Perform abnormal data cleaning on the power load data of each incoming line of the park every minute;

[0012] Calculate the hourly power load data of each incoming line of the park according to the minute-by-minute power load data of each incoming line of the park after abnormal data cleaning;

[0013] The power load data of each incoming line of the park per hour is normalized to obtain the normalized power load data of each incoming line of the park per hour and merge it with the preset normalized data to obtain the feature vector of each incoming line of the park; wherein the preset normalized data at least includes normalized temperature data and normalized day attribute data.

[0014] As a preferred solution, cluster analysis is performed on the characteristic vectors of each incoming line of the park to determine the typical daily operation scenario of each incoming line of the park, which specifically includes the following steps:

[0015] Determine the number of clusters of the characteristic vectors of each incoming line of the park by using the elbow rule;

[0016] According to the number of clusters, the characteristic vectors of each incoming line of the park are clustered using the K-means algorithm to obtain the characteristic vector clustering results of each incoming line of the park;

[0017] The normalized data in the characteristic vector clustering results of each incoming line of the park are reversed to the original scale to determine the typical daily operation scene of each incoming line of the park.

[0018] As a preferred solution, the typical daily carbon emissions of each incoming line of the park are determined according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, which specifically includes the following steps:

[0019] Determine the power consumption of each typical destination of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park;

[0020] The typical daily carbon emissions of each incoming line of the park are determined according to the product of each typical purpose electricity consumption of each incoming line of the park and the carbon emission factor.

[0021] As a preferred solution, the objective function of the power load optimization scheduling model is specifically:

[0022] max(r,c);

[0023] Among them, r represents the electricity comfort level, and c represents the rate of change of electricity cost;

[0024] The expression of the electricity comfort is specifically:

[0025]

[0026] E t Represents the electricity load data per hour in a typical day, E′ t It represents the electricity load data per hour in a typical day after optimized electricity load scheduling;

[0027] The expression of the rate of change of the electricity cost is specifically:

[0028]

[0029] p t represents the electricity price per hour, and the change rate of the electricity cost is inversely proportional to the electricity cost.

[0030] As a preferred solution, the constraints of the power load optimization scheduling model are determined according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, which specifically include the following steps:

[0031] According to the typical daily carbon emission quota of each incoming line of the park, the carbon emission quota constraint condition is determined by the following expression:

[0032]

[0033] in, Indicates the carbon emissions per typical purpose, C total Indicates the carbon emission quota for each typical purpose;

[0034] The transferable load constraint conditions are specifically:

[0035]

[0036]

[0037] in, Indicates the transferable load per hour

[0038] The translation load constraint conditions are specifically:

[0039]

[0040]

[0041]

[0042]

[0043] in, Indicates the load that can be translated per hour; L in，t Indicates the load transferred in at hour t; L out，t represents the load transferred out at hour t; m SL1 Represents the total number of load types that can be translated; m SL2 Indicates the total number of load types that can be shifted when the power supply duration is greater than one scheduling period; h max Indicates the maximum power supply duration of the movable load unit; x k，t′，t represents the number of k-th type of translatable load units transferred from hour t to hour t′; p 1，k represents the power value of the kth type of movable load unit in the first hour; p (h+1)，k It represents the power value of the k-th type movable load unit in the h+1th working period during its power supply duration;

[0044] The load reduction constraint conditions are specifically:

[0045]

[0046] in, Indicates the load that can be curtailed per hour;

[0047] According to the hourly transferable load, the hourly shiftable load and the hourly curtailable load, the optimized power load constraint condition of the power load data per hour in the typical day after the power load optimization scheduling is determined by the following expression:

[0048]

[0049] E ′ t ≥0;

[0050] The constraints of the power load optimization scheduling model are determined based on the carbon emission quota constraints, the transferable load constraints, the shiftable load constraints, the reducible load constraints and the optimized power load constraints.

[0051] As a preferred solution, solving the power load optimization scheduling model according to the constraint conditions to obtain the power load optimization scheduling results of each incoming line of the park specifically includes the following steps:

[0052] According to the constraints, the power load optimization scheduling model is solved using a non-dominated sorting genetic algorithm to obtain the power load optimization scheduling results of each incoming line in the park.

[0053] A second aspect of an embodiment of the present invention provides a park power load optimization scheduling device, including:

[0054] A feature vector acquisition module is used to clean and extract features of the power load data of each incoming line in the park to obtain feature vectors of each incoming line in the park;

[0055] A typical day operation scenario determination module is used to perform cluster analysis on the characteristic vectors of each incoming line of the park to determine the typical day operation scenario of each incoming line of the park; wherein the typical day operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day;

[0056] A carbon emission calculation module is used to determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and a preset carbon emission factor, and determine the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park;

[0057] A typical daily carbon emission quota determination module is used to determine the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and a preset annual total carbon emission quota;

[0058] The power load optimization scheduling module is used to construct a power load optimization scheduling model for each incoming line of the park with the highest power comfort and the lowest power cost as the objective function, and determine the constraints of the power load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, solve the power load optimization scheduling model according to the constraints, and obtain the power load optimization scheduling results of each incoming line of the park.

[0059] A third aspect of an embodiment of the present invention provides a terminal 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 computer program, the method for optimizing and scheduling power load in a park as described in any one of the first aspects is implemented.

[0060] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the park power load optimization scheduling method as described in any one of the first aspects.

[0061] Compared with the prior art, the beneficial effect of the embodiments of the present invention is that, based on the typical daily operation scenarios of each incoming line in the park, the carbon emission quota of each incoming line in the park can be reasonably allocated. At the same time, multiple optimization objectives are considered when constructing the electricity load optimization scheduling model, and the model is solved with the carbon emission quota as a constraint condition, so as to obtain an electricity load optimization scheduling result that meets the carbon emission quota requirements and has high electricity comfort and low electricity cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of a method for optimizing and dispatching power load in a park according to an embodiment of the present invention;

[0063] Figure 2 is a relationship diagram between the SSE and the number of clusters obtained by the elbow rule for a certain incoming line in a certain park in an embodiment of the present invention;

[0064] Figure 3 This is a schematic diagram of a typical operation scenario of a 380V incoming line switch in a certain park in an embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of the optimization scheduling result of the power load of a certain incoming line in a certain park in an embodiment of the present invention;

[0066] Figure 5 It is a structural schematic diagram of a park power load optimization scheduling device in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] See also Figure 1 According to a first aspect of an embodiment of the present invention, a method for optimizing and scheduling power load in a park is provided, comprising the following steps S1 to S5:

[0069] Step S1, cleaning and feature extraction of power load data of each incoming line of the park to obtain feature vectors of each incoming line of the park;

[0070] Step S2, performing cluster analysis on the characteristic vectors of each incoming line of the park to determine a typical daily operation scenario of each incoming line of the park; wherein the typical daily operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day;

[0071] Step S3, determining the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, and determining the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park;

[0072] Step S4, determining the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and the preset annual total carbon emission quota;

[0073] Step S5, taking the highest electricity comfort and the lowest electricity cost as the objective function, constructing an electricity load optimization scheduling model for each incoming line of the park, and determining the constraints of the electricity load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, solving the electricity load optimization scheduling model according to the constraints, and obtaining the electricity load optimization scheduling results for each incoming line of the park.

[0074] Specifically, when constructing the power load optimization scheduling model for each incoming line in the park, this embodiment selects multiple optimization objectives, namely, maximizing the park power comfort based on demand response and maximizing the rate of change of the park power cost based on demand response. Among them, the power comfort mainly reflects the degree of change of the user's power consumption behavior under demand response, and the rate of change of power cost mainly reflects the degree of change of the user's power cost under demand response. The greater the rate of change of power cost, the lower the power cost of the park.

[0075] As a preferred solution, the power load data of each incoming line in the park is cleaned and feature extracted to obtain the feature vector of each incoming line in the park, which specifically includes the following steps:

[0076] Perform abnormal data cleaning on the power load data of each incoming line of the park every minute;

[0077] Calculate the hourly power load data of each incoming line of the park according to the minute-by-minute power load data of each incoming line of the park after abnormal data cleaning;

[0078] The power load data of each incoming line of the park per hour is normalized to obtain the normalized power load data of each incoming line of the park per hour and merge it with the preset normalized data to obtain the feature vector of each incoming line of the park; wherein the preset normalized data at least includes normalized temperature data and normalized day attribute data.

[0079] Specifically, since the power load data of each incoming line in the park is usually acquired at the minute level, this embodiment first cleans up the abnormal data of the power load data of each incoming line in the park every minute, and then obtains the average power of each incoming line per hour, determines the power load data of each incoming line per hour, so as to extract the single-day power consumption characteristics of each incoming line in the park, and further, normalizes the power load data of each incoming line in the park per hour, obtains the normalized power load data of each incoming line in the park per hour and merges it with the preset normalized data, such as the normalized temperature data and the normalized day attribute data, the day attribute is a working day or a rest day, thereby obtaining a feature vector that can comprehensively describe the production status.

[0080] As a preferred solution, cluster analysis is performed on the characteristic vectors of each incoming line of the park to determine the typical daily operation scenario of each incoming line of the park, which specifically includes the following steps:

[0081] Determine the number of clusters of the characteristic vectors of each incoming line of the park by using the elbow rule;

[0082] According to the number of clusters, the characteristic vectors of each incoming line of the park are clustered using the K-means algorithm to obtain the characteristic vector clustering results of each incoming line of the park;

[0083] The normalized data in the characteristic vector clustering results of each incoming line of the park are reversed to the original scale to determine the typical daily operation scene of each incoming line of the park.

[0084] Specifically, this embodiment first uses the elbow rule to determine the number of clusters of the characteristic vectors of each incoming line of the park. It is worth noting that the elbow rule is a clustering algorithm evaluation indicator based on the sum of squared errors (SSE), which is mainly used to determine the optimal number of clusters. SSE is the sum of the squares of the distances from all points within each cluster to the center of the cluster, which can be used to evaluate the effect of clustering. The specific process of the elbow rule is as follows: First, for each possible number of clusters K, run the K-means clustering algorithm and calculate the SSE. Then, for all K, the corresponding SSE is plotted, with the horizontal axis representing the K value and the vertical axis representing the SSE. Finally, observe the curve and find the "elbow" of the curve, that is, the point where the rate of decrease of SSE slows down significantly. The K value corresponding to this point is considered to be the optimal number of clusters. For example, Figure 2As shown in the figure, it is a relationship diagram between the SSE and the number of clusters obtained by the elbow rule for a certain incoming line in a certain park. From the "elbow" of the curve, it can be seen that the optimal number of clusters for this incoming line is 6.

[0085] After determining the number of clusters, the K-means algorithm is used to cluster the feature vectors of each incoming line in the park, and the clustered normalized data is reversed to the original scale to obtain the typical daily operation scene of each incoming line in the park. Figure 3 The figure shows a typical operating scenario of a 380V incoming line switch in a certain park.

[0086] As a preferred solution, the typical daily carbon emissions of each incoming line of the park are determined according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, which specifically includes the following steps:

[0087] Determine the power consumption of each incoming line of the park on each typical day according to the typical daily operation scenario of each incoming line of the park;

[0088] The typical daily carbon emissions of each incoming line of the park are determined according to the product of each typical daily electricity consumption of each incoming line of the park and the carbon emission factor.

[0089] It is worth noting that, according to the ratio of the typical daily carbon emissions of each incoming line in the park obtained in this embodiment to the annual total carbon emissions, combined with the preset annual total carbon emissions quota, the typical daily carbon emissions quota of each incoming line in the park can be calculated. For example, the typical day and carbon emissions quota of the 380V incoming line in a park are shown in Table 1 below:

[0090] Table 1 Typical day and carbon emission quota of 380V incoming line in a certain park

[0091] Typical day number Carbon emission quota (t) 1 9.6750 2 2.8145 3 5.3991 4 4.9463 5 5.5879 6 3.3186

[0092] As a preferred solution, the objective function of the power load optimization scheduling model is specifically:

[0093] max(r,c);

[0094] Among them, r represents the electricity comfort level, and c represents the rate of change of electricity cost;

[0095] The expression of the electricity comfort is specifically:

[0096]

[0097] E t Represents the electricity load data per hour in a typical day, E′ t It represents the electricity load data per hour in a typical day after optimized electricity load scheduling;

[0098] The expression of the rate of change of the electricity cost is specifically:

[0099]

[0100] p t represents the electricity price per hour, and the change rate of the electricity cost is inversely proportional to the electricity cost.

[0101] Specifically, this embodiment defines a typical hourly power load data sequence as: E = [E0, E1, ..., E 23 ]; the hourly power load data sequence after power load optimization scheduling is: E′=[E′0,E′1,...,E′ 23 ]; Considering the peak and valley electricity prices of the large power grid to the park, the hourly electricity price is defined as: p = [p0, p1, ..., p 23 ].

[0102] For the power consumption comfort index, when the park does not respond to demand, users consume electricity on demand, and the power consumption plan is not changed at this time, and the power consumption comfort is the highest. After implementing the demand response of power load optimization scheduling, the power load is changed, and the power consumption comfort is defined as:

[0103]

[0104] The larger r is, the higher the comfort level of electricity use.

[0105] As for the rate of change of electricity cost, after implementing the demand response of optimal dispatch of electricity load, the electricity cost will also change according to the demand response, so the rate of change of electricity cost is defined as:

[0106]

[0107] The larger c is, the lower the electricity cost of the park after demand response.

[0108] As a preferred solution, the constraints of the power load optimization scheduling model are determined according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, which specifically include the following steps:

[0109] According to the typical daily carbon emission quota of each incoming line of the park, the carbon emission quota constraint condition is determined by the following expression:

[0110]

[0111] in, Indicates the carbon emissions per typical purpose, C total Indicates the carbon emission quota for each typical purpose;

[0112] The transferable load constraint conditions are specifically:

[0113]

[0114]

[0115] in, Indicates the transferable load per hour

[0116] The translation load constraint conditions are specifically:

[0117]

[0118]

[0119]

[0120]

[0121] in, Indicates the load that can be translated per hour; L in，t Indicates the load transferred in at hour t; L out，t represents the load transferred out at hour t; m SL1 Represents the total number of load types that can be translated; m SL2 Indicates the total number of load types that can be shifted when the power supply duration is greater than one scheduling period; h max Indicates the maximum power supply duration of the movable load unit; x k，t′，t represents the number of k-th type of translatable load units transferred from hour t to hour t′; p 1，k represents the power value of the kth type of movable load unit in the first hour; p (h+1)，k It represents the power value of the k-th type movable load unit in the h+1th working period during its power supply duration;

[0122] The load reduction constraint conditions are specifically:

[0123]

[0124] in, Indicates the load that can be curtailed per hour;

[0125] According to the hourly transferable load, the hourly shiftable load and the hourly curtailable load, the optimized power load constraint condition of the power load data per hour in the typical day after the power load optimization scheduling is determined by the following expression:

[0126]

[0127] E′ t ≥0;

[0128] The constraints of the power load optimization scheduling model are determined based on the carbon emission quota constraints, the transferable load constraints, the shiftable load constraints, the reducible load constraints and the optimized power load constraints.

[0129] Specifically, this embodiment sets several constraints for the power load optimization scheduling model.

[0130] Regarding the carbon emission quota constraint condition, this embodiment sets the carbon emission amount of each typical purpose to be no greater than its corresponding carbon emission quota.

[0131] For the transferable load constraint condition, this embodiment sets the transferable load to be no more than m%. If This means that the load is moved in, and at the same time, the sum of all transferable loads must be equal to 0.

[0132] For the translation load constraint condition, this embodiment sets the translation load not to exceed h%, and limits the translation interval to ±n hours, t∈[0+n, 23-n]. At the same time, the sum of all translation loads must be equal to O.

[0133] For the load reduction constraint condition, this embodiment sets the load reduction to not exceed z%.

[0134] As a preferred solution, solving the power load optimization scheduling model according to the constraint conditions to obtain the power load optimization scheduling results of each incoming line of the park specifically includes the following steps:

[0135] According to the constraints, the power load optimization scheduling model is solved using a non-dominated sorting genetic algorithm to obtain the power load optimization scheduling results of each incoming line in the park.

[0136] For example, after a certain incoming line in a certain park is processed by the power load optimization scheduling method of the embodiment of the present invention, the power load optimization scheduling result obtained is as follows: Figure 4 shown.

[0137] The embodiment of the present invention provides a method for optimizing the power load scheduling of a park. Based on the typical daily operation scenarios of each incoming line in the park, the carbon emission quota of each incoming line in the park can be reasonably allocated. At the same time, multiple optimization objectives are considered when constructing the power load optimization scheduling model, and the model is solved with the carbon emission quota as a constraint condition, so that the power load optimization scheduling result that meets the carbon emission quota requirements and has high power comfort and low power cost can be obtained. While meeting the carbon emission quota requirements, the resulting power discomfort is reduced as much as possible, and the park's operating costs are minimized, providing strong support for the park to effectively achieve the carbon peak and carbon neutrality goals.

[0138] See also Figure 5 According to a second aspect of an embodiment of the present invention, a device for optimizing and dispatching power load in a park is provided, comprising:

[0139] The feature vector acquisition module 501 is used to clean and extract features of the power load data of each incoming line in the park to obtain the feature vectors of each incoming line in the park;

[0140] A typical day operation scenario determination module 502 is used to perform cluster analysis on the characteristic vectors of each incoming line of the park to determine the typical day operation scenario of each incoming line of the park; wherein the typical day operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day;

[0141] The carbon emission calculation module 503 is used to determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, and determine the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park;

[0142] A typical daily carbon emission quota determination module 504 is used to determine the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and a preset annual total carbon emission quota;

[0143] The power load optimization scheduling module 505 is used to construct a power load optimization scheduling model for each incoming line of the park with the highest power comfort and the lowest power cost as the objective function, and determine the constraints of the power load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, solve the power load optimization scheduling model according to the constraints, and obtain the power load optimization scheduling results of each incoming line of the park.

[0144] It should be noted that the park electricity load optimization scheduling device provided by the embodiment of the present invention can implement all the processes of the park electricity load optimization scheduling method described in any of the above embodiments. The functions of each module in the device and the technical effects achieved are respectively the same as the functions and technical effects achieved by the park electricity load optimization scheduling method described in the above embodiments, and will not be repeated here.

[0145] A third aspect of an embodiment of the present invention provides a terminal 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 computer program, the method for optimizing and scheduling power load in a park as described in any embodiment of the first aspect is implemented.

[0146] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory. The terminal device may also include an input / output device, a network access device, a bus, etc.

[0147] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0148] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0149] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the park power load optimization scheduling method as described in any embodiment of the first aspect.

[0150] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary hardware platform, and of course can also be implemented entirely by hardware. Based on such an understanding, all or part of the contribution of the technical solution of the present invention to the background technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0151] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for optimizing the dispatching of power load in a park, characterized in that: The steps include: Cleaning and feature extraction are performed on the power load data of each incoming line in the park to obtain feature vectors of each incoming line in the park; Performing cluster analysis on the characteristic vectors of each incoming line of the park to determine a typical daily operation scenario of each incoming line of the park; wherein the typical daily operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day; Determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, and determine the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park; Determine the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and the preset annual total carbon emission quota; Taking the highest electricity comfort and the lowest electricity cost as the objective function, construct an electricity load optimization scheduling model for each incoming line of the park, and determine the constraints of the electricity load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, solve the electricity load optimization scheduling model according to the constraints, and obtain the electricity load optimization scheduling results of each incoming line of the park; The objective function of the power load optimization scheduling model is specifically: max(r,c); Among them, r represents the electricity comfort level, and c represents the rate of change of electricity cost; The expression of the electricity comfort is specifically: E t Represents the electricity load data per hour in a typical day, E t ′ represents the hourly electricity load data of a typical day after optimized electricity load scheduling; The expression of the rate of change of the electricity cost is specifically: p t represents the hourly electricity price, and the rate of change of the electricity cost is inversely proportional to the electricity cost; Determining the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor specifically includes the following steps: Determine the power consumption of each incoming line of the park on each typical day according to the typical daily operation scenario of each incoming line of the park; Determine the typical daily carbon emissions of each incoming line of the park according to the product of each typical day's electricity consumption of each incoming line of the park and the carbon emission factor; Determining the constraint conditions of the power load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraint conditions, the shiftable load constraint conditions and the reducible load constraint conditions specifically includes the following steps: According to the typical daily carbon emission quota of each incoming line of the park, the carbon emission quota constraint condition is determined by the following expression: in, represents the carbon emissions per typical day, C total Indicates the carbon emission quota for each typical day; The transferable load constraint conditions are specifically: in, represents the transferable load per hour; The translation load constraint conditions are specifically: in, Indicates the load that can be translated per hour; L in,t Indicates the load transferred in at hour t; L out,t represents the load transferred out at hour t; m SL1 Represents the total number of load types that can be translated; m SL2 Indicates the total number of load types that can be shifted when the power supply duration is greater than one scheduling period; h max Indicates the maximum power supply duration of the movable load unit; x k,t′,t represents the number of k-th type of translatable load units transferred from hour t to hour t′; p 1,k represents the power value of the kth type of movable load unit in the first hour; p (h+1),k It represents the power value of the k-th type movable load unit in the h+1th working period during its power supply duration; The load reduction constraint conditions are specifically: in, Indicates the load that can be curtailed per hour; According to the hourly transferable load, the hourly shiftable load and the hourly curtailable load, the optimized power load constraint condition of the power load data per hour in the typical day after the power load optimization scheduling is determined by the following expression: E t ′ ≥0； The constraints of the power load optimization scheduling model are determined based on the carbon emission quota constraints, the transferable load constraints, the shiftable load constraints, the reducible load constraints and the optimized power load constraints.

2. The method for optimizing the dispatching of the power load in a park according to claim 1, characterized in that: The cleaning and feature extraction of the power load data of each incoming line of the park to obtain the feature vector of each incoming line of the park specifically includes the following steps: Perform abnormal data cleaning on the power load data of each incoming line of the park every minute; Calculate the hourly power load data of each incoming line of the park according to the minute-by-minute power load data of each incoming line of the park after abnormal data cleaning; The power load data of each incoming line of the park per hour is normalized to obtain the normalized power load data of each incoming line of the park per hour and merge it with the preset normalized data to obtain the feature vector of each incoming line of the park; wherein the preset normalized data at least includes normalized temperature data and normalized day attribute data.

3. The method for optimizing the dispatching of the power load in a park according to claim 2, characterized in that: The cluster analysis of the characteristic vectors of the incoming lines of the park to determine the typical daily operation scenarios of the incoming lines of the park specifically includes the following steps: Determine the number of clusters of the characteristic vectors of each incoming line of the park by using the elbow rule; According to the number of clusters, the characteristic vectors of each incoming line of the park are clustered using the K-means algorithm to obtain the characteristic vector clustering results of each incoming line of the park; The normalized data in the characteristic vector clustering results of each incoming line of the park are reversed to the original scale to determine the typical daily operation scene of each incoming line of the park.

4. The method for optimizing the dispatching of the power load in a park according to claim 1, characterized in that: Solving the power load optimization scheduling model according to the constraint conditions to obtain the power load optimization scheduling results of each incoming line of the park specifically includes the following steps: According to the constraints, the power load optimization scheduling model is solved using a non-dominated sorting genetic algorithm to obtain the power load optimization scheduling results of each incoming line in the park.

5. A park power load optimization scheduling device, characterized in that: include: A feature vector acquisition module is used to clean and extract features of the power load data of each incoming line in the park to obtain feature vectors of each incoming line in the park; A typical day operation scenario determination module is used to perform cluster analysis on the characteristic vectors of each incoming line of the park to determine the typical day operation scenario of each incoming line of the park; wherein the typical day operation scenario is used to characterize the power load data of any incoming line of the park per hour on each typical day; A carbon emission calculation module is used to determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and a preset carbon emission factor, and determine the annual total carbon emissions of each incoming line of the park according to the typical daily carbon emissions of each incoming line of the park; A typical daily carbon emission quota determination module is used to determine the typical daily carbon emission quota of each incoming line of the park according to the ratio of the typical daily carbon emission of each incoming line of the park to the annual total carbon emission and a preset annual total carbon emission quota; The power load optimization scheduling module is used to construct a power load optimization scheduling model for each incoming line of the park with the highest power comfort and the lowest power cost as the objective function, and determine the constraints of the power load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, solve the power load optimization scheduling model according to the constraints, and obtain the power load optimization scheduling results of each incoming line of the park; The objective function of the power load optimization scheduling model is specifically: max(r,c); Among them, r represents the electricity comfort level, and c represents the rate of change of electricity cost; The expression of the electricity comfort is specifically: E t Represents the electricity load data per hour in a typical day, E t ′ It represents the electricity load data per hour in a typical day after optimized electricity load scheduling; The expression of the rate of change of the electricity cost is specifically: p t represents the hourly electricity price, and the rate of change of the electricity cost is inversely proportional to the electricity cost; The carbon emission calculation module is used to determine the typical daily carbon emissions of each incoming line of the park according to the typical daily operation scenario of each incoming line of the park and the preset carbon emission factor, specifically including: Determine the power consumption of each incoming line of the park on each typical day according to the typical daily operation scenario of each incoming line of the park; Determine the typical daily carbon emissions of each incoming line of the park according to the product of each typical day's electricity consumption of each incoming line of the park and the carbon emission factor; The power load optimization scheduling module is used to determine the constraints of the power load optimization scheduling model according to the typical daily carbon emission quota of each incoming line of the park, the preset transferable load constraints, the shiftable load constraints and the reducible load constraints, specifically including: According to the typical daily carbon emission quota of each incoming line of the park, the carbon emission quota constraint condition is determined by the following expression: in, represents the carbon emissions per typical day, C total Indicates the carbon emission quota for each typical day; The transferable load constraint conditions are specifically: in, represents the transferable load per hour; The translation load constraint conditions are specifically: in, Indicates the load that can be translated per hour; L in,t Indicates the load transferred in at hour t; L out,t represents the load transferred out at hour t; m SL1 Represents the total number of load types that can be translated; m SL2 Indicates the total number of load types that can be shifted when the power supply duration is greater than one scheduling period; h max Indicates the maximum power supply duration of the movable load unit; x k,t′,t represents the number of k-th type of translatable load units transferred from hour t to hour t′; p 1,k represents the power value of the kth type of movable load unit in the first hour; p (h+1),k It represents the power value of the k-th type movable load unit in the h+1th working period during its power supply duration; The load reduction constraint conditions are specifically: in, Indicates the load that can be curtailed per hour; According to the hourly transferable load, the hourly shiftable load and the hourly curtailable load, the optimized power load constraint condition of the power load data per hour in the typical day after the power load optimization scheduling is determined by the following expression: E t ′ ≥0； The constraints of the power load optimization scheduling model are determined based on the carbon emission quota constraints, the transferable load constraints, the shiftable load constraints, the reducible load constraints and the optimized power load constraints.

6. A terminal device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the park power load optimization scheduling method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the park power load optimization scheduling method according to any one of claims 1 to 4.

Images