Regional Power Peak-Shaving Resource Collaboration System and Method Based on Cloud Computing

Abstract

The present invention relates to the technical field of power dispatching, and specifically to a regional power peak shaving resource collaboration system and method based on cloud computing. The method includes: constructing a support vector machine regression model to predict the regional power consumption; calculating the regional power peak shaving demand based on the prediction results, power generation, and electricity storage, including the remaining power peak shaving time and power demand, and dividing the power peak shaving demand area, stable power consumption area, and power surplus area; constructing a regional power peak shaving resource pool; considering the power transmission path, resource reserves, and transmission loss, and constructing a collaborative dispatching model with the peak shaving time and power demand as constraints to calculate the response power of the power surplus area to the power peak shaving demand area; the power surplus area performs power dispatching on the power peak shaving demand area according to the allocated response power. The method provided by the present invention can improve the flexibility, working efficiency, and stability of regional power peak shaving.

Description

Technical Field

[0001] The present invention relates to the technical field of power dispatching, and specifically to a regional power peak shaving resource coordination system and method based on cloud computing. Background Art

[0002] With the rapid development of the economic society and the continuous growth of power load, the power system is facing increasingly severe challenges in supply-demand balance. The regional power peak shaving problem has become a key issue in the operation of the power system. Due to the uneven distribution of power resources among regions, some regions are facing the problem of power supply shortage.

[0003] In order to address the regional power peak shaving challenges, extensive research and practices have been carried out on the power peak shaving problem. Among them, the development of smart grid technology has provided new possibilities for solving the regional power peak shaving problem. Under the framework of the smart grid, the regional power peak shaving problem has been solved more systematically and comprehensively. By predicting and analyzing the regional electricity consumption load, potential power supply-demand imbalance problems can be identified in advance, providing a basis for formulating power peak shaving strategies. At the same time, by using advanced optimization algorithms and control strategies, the coordinated and optimized dispatching of power resources inside and outside the region can be achieved, maximizing the regulation capabilities of different types of power resources and improving the overall peak shaving efficiency of the power system.

[0004] In addition, big data analysis technology has also been widely applied in the field of power peak shaving. By mining and analyzing the massive operation data of the power system, the changing rules and influencing factors of the power load can be discovered, providing data support for power peak shaving decisions. The introduction of machine learning and artificial intelligence technologies has also provided new ideas for solving the power peak shaving problem. By training intelligent algorithm models, accurate prediction of power load and optimized allocation of power resources can be achieved, improving the automation and intelligence levels of power peak shaving.

[0005] In view of this, the present invention proposes a regional power peak shaving resource coordination system and method based on cloud computing. Summary of the Invention

[0006] To achieve the above object, the present invention provides the following technical solution: A regional power peak shaving resource coordination method based on cloud computing, including:

[0007] Construct a regional electricity power prediction model of support vector machine SVR, and predict the regional electricity power for a future time period based on the historical electricity consumption data of the region;

[0008] Based on the regional electricity consumption power prediction results, as well as the regional power generation power and electricity storage capacity, calculate the regional power peak shaving demand. The power peak shaving demand includes the remaining power peak shaving time and the power peak shaving power demand. Based on the calculation results of the regional power peak shaving demand, divide the electricity consumption areas in the future time period into power peak shaving demand areas, stable electricity consumption areas, and power surplus areas;

[0009] Construct a regional power peak shaving resource pool based on the regional power peak shaving resources. The regional power peak shaving resources include the generating units and electricity storage equipment within the region;

[0010] Based on the power transmission paths between regions and the reserves of power peak shaving resources, while considering the losses in power transmission between regions, construct a coordinated scheduling model for regional power peak shaving resources with the remaining power peak shaving time and the power peak shaving power demand as constraints, and calculate the power peak shaving response power of the power surplus area to the power peak shaving demand area;

[0011] The power surplus area conducts power scheduling for the areas with power peak shaving demands according to the allocated power peak shaving response power.

[0012] Preferably, the regional electricity consumption power prediction model constructed by the support vector machine SVR includes: using the mathematical model of the support vector machine SVR to predict the regional electricity consumption power. Let the electricity consumption power in the region at time be , and the historical electricity consumption data be , where is the input feature, n is the number of historical electricity consumption data, and the mathematical model of the support vector machine SVR is as follows:

[0013] ;

[0014] ;

[0015] Among them, is the weight vector, is the bias term, and are used to define the regression plane, and are slack variables, is the maximum regression deviation, is used to control the smoothness of the regression plane; is the input mapping function; is the transpose of the weight vector; is the regularization term in the support vector machine SVR objective function; is the time of the nth historical electricity consumption data;

[0016] Regional power consumption prediction model based on Support Vector Machine SVR:

[0017] ;

[0018] Among them, and are Lagrange multipliers, is the kernel function, is the power consumption predicted for region at time t, and N is the total number of regions.

[0019] Preferably, calculating the power peak shaving demand of the region based on the regional power consumption prediction result and the power generation and electricity storage of the region includes: calculating the power peak shaving demand of region . When there is a predicted peak power consumption in region from the current time to the future time greater than the power generation in region , calculate the predicted power consumption in region from the current time to the future time point t:

[0020] ;

[0021] If the predicted power consumption in region from the current time to the future time point t is greater than the sum of the electricity storage and the power generation in region , that is: , then region has a power peak shaving demand. Mark region as a power peak shaving demand region, and calculate the remaining power peak shaving time of region ;

[0022] ;

[0023] Among them, is the electricity storage of region i, is the power consumption of region at the current time ;

[0024] Obtain the power peak shaving power demand of region : .

[0025] Preferably, when the region at the current time to the future time there is a predicted peak power consumption greater than the power generation in the region and when the predicted power consumption in the region from the current time to the future time point t is less than or equal to the sum of the electricity storage and the power generation in the region that is:

[0026] ;

[0027] The self - power generation and electricity storage of the region can meet its own electricity demand, and the region is divided into a stable electricity consumption region;

[0028] When the predicted peak power consumption in the region from the current time to the future time is always less than the power generation in the region then the power generation in the region from the current time to the future time is greater than the power consumption, and the region has no electricity peak - shaving demand, and the region is divided into a power surplus region.

[0029] Preferably, the regional power peak - shaving resource pool is constructed based on the regional power peak - shaving resources, including: assuming that the i - th region has a power peak - shaving demand and the j - th region has a power surplus, from the current time to the future time the power available for power peak - shaving in the power surplus region j is the sum of the surplus power of the generator set and the output power of the electricity storage device :

[0030] ;

[0031] ;

[0032] Calculate the power available for power peak - shaving in all power surplus regions :

[0033] ;

[0034] Among them, represents the number of regions with power surplus; the available power for peak shaving of all power surplus regions constitutes the regional power peak shaving resource pool.

[0035] Preferably, based on the power transmission path between regions and the power peak shaving resource reserves, while considering the loss of power transmission between regions, with the remaining power peak shaving time and power peak shaving power demand as constraint conditions, a regional power peak shaving resource collaborative scheduling model is constructed to calculate the power peak shaving response power of the power surplus region to the power peak shaving demand region, including: Let the set of power surplus regions be A, and the set of power peak shaving demand regions be B, then the power peak shaving demand region , the power surplus region , define the power variable as the power peak shaving response power of the power surplus region j to the power peak shaving demand region ;

[0036] Construct an objective function to minimize the power peak shaving response power of the power surplus region to the power peak shaving demand region, as the regional power peak shaving resource collaborative scheduling model, for calculating the power peak shaving response power of a single power surplus region to a single power peak shaving demand region :

[0037] ;

[0038] Calculate the power peak shaving response power in the regional power peak shaving resource collaborative scheduling model through the constraint conditions ;

[0039] The constraint conditions include that the power peak shaving response power of the th region in the regional power peak shaving resource pool does not exceed the available power for peak shaving of the th region, that is , that is ;

[0040] The constraint conditions also include that the sum of the power peak shaving response powers obtained by the power peak shaving demand region from the regional power peak shaving resource pool is , considering the power transmission efficiency , ; and ;

[0041] The constraint conditions also include considering the power transmission time from the power surplus region to the power peak shaving demand region, then:

[0042] ;

[0043] According to the regional power peak shaving resource collaborative scheduling model, the power peak shaving response power of a single power surplus area to a single power peak shaving demand area is calculated. .

[0044] Preferably, the power surplus area conducts power scheduling for the area with power peak shaving demand according to the allocated power peak shaving response power, including: according to the calculated power peak shaving response power of the power surplus area to the power peak shaving demand area , the power surplus area conducts peak shaving response to the power peak shaving demand area with the power peak shaving response power , and after reaching time, the regional power consumption power is predicted again and the scheduling response power is calculated to ensure stable power consumption in the area.

[0045] A regional power peak shaving resource collaborative system based on cloud computing, which is used to implement the regional power peak shaving resource collaborative method based on cloud computing, includes a power consumption power prediction module, a peak shaving demand calculation module, a peak shaving resource formation module, a power peak shaving response power calculation module, and a power peak shaving execution module;

[0046] The power consumption power prediction module uses a regional power consumption power prediction model constructed by support vector machine SVR to predict the regional power consumption power in the future time period based on the historical power consumption data of the region;

[0047] The peak shaving demand calculation module calculates the regional power peak shaving demand based on the regional power consumption power prediction result, the regional power generation power and the electricity storage capacity. The power peak shaving demand includes the remaining power peak shaving time and the power peak shaving power demand. Based on the calculation result of the regional power peak shaving demand, the power consumption areas in the future time period are divided into power peak shaving demand areas, stable power consumption areas and power surplus areas;

[0048] The peak shaving resource formation module constructs a regional power peak shaving resource pool based on the regional power peak shaving resources. The regional power peak shaving resources include the generator sets and electricity storage equipment in the region;

[0049] The power peak shaving response power calculation module constructs a regional power peak shaving resource collaborative scheduling model based on the power transmission path between regions and the power peak shaving resource reserves, and considering the loss of power transmission between regions, and calculates the power peak shaving response power of the power surplus area to the power peak shaving demand area with the remaining power peak shaving time and the power peak shaving power demand as constraints;

[0050] The power peak shaving execution module conducts power peak shaving scheduling for the area with power peak shaving demand by the power surplus area according to the allocated power peak shaving response power.

[0051] Beneficial effects: By constructing a regional electricity power prediction model based on the support vector machine SVR and using the historical electricity consumption data of the region to predict the electricity power for future time periods, the present invention can improve the accuracy of power load prediction. Accurate power load prediction is an important prerequisite for realizing effective power peak shaving, which helps to detect potential power supply-demand imbalance problems early and provides a basis for formulating reasonable power peak shaving strategies.

[0052] Based on the regional electricity power prediction results and combined with the power generation power and electricity storage capacity information of the region, the present invention can accurately calculate the power peak shaving demand of the region, including the remaining power peak shaving time and the power peak shaving power demand. By accurately identifying the power peak shaving demand, it is possible to specifically divide the power peak shaving demand area, the stable electricity consumption area, and the power surplus area, laying a foundation for the subsequent optimal allocation of power peak shaving resources.

[0053] By constructing a regional power peak shaving resource pool and incorporating the generating units and electricity storage devices in the region into unified management and scheduling, the present invention can achieve the optimal allocation of power peak shaving resources.

[0054] Using the regional power peak shaving resource collaborative scheduling model and comprehensively considering factors such as the power transmission path between regions, the power peak shaving resource reserves, and the transmission losses, the present invention can calculate the optimal power peak shaving response strategy of the power surplus area to the power peak shaving demand area. This optimization and allocation method can maximize the adjustment ability of power resources in different regions and improve the overall power peak shaving efficiency of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic flowchart of the regional power peak shaving resource collaborative method based on cloud computing according to the present invention;

[0056] Figure 2 It is a schematic structural diagram of the regional power peak shaving resource collaborative system based on cloud computing according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] To better understand the present application, more detailed descriptions of various aspects of the present application will be made with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of the exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0058] In the accompanying drawings, for ease of illustration, the sizes, dimensions, and shapes of the elements have been slightly adjusted. The drawings are for illustrative purposes only and are not drawn to an exact scale. As used herein, terms such as "substantially", "approximately", and similar terms are used as terms indicating approximation, rather than terms indicating degree, and are intended to account for the inherent deviations in measured or calculated values that would be recognized by a person of ordinary skill in the art. Additionally, in this application, the order in which the steps of each process are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise clearly specified or derivable from the context.

[0059] It should also be understood that expressions such as "comprising", "including", "having", "containing", and / or "including having" are open-ended rather than closed-ended expressions in this specification, which means that the stated features, elements, and / or components exist, but do not exclude the existence of one or more other features, elements, components, and / or their combinations. In addition, when an expression such as "at least one of..." appears after a list of listed features, it modifies the entire list of features, rather than just an individual element in the list. Further, when describing the embodiments of this application, the use of "may" indicates "one or more embodiments of this application". And the term "exemplary" is intended to refer to an example or illustration.

[0060] Unless otherwise defined, all terms used herein (including engineering terms and scientific and technical terms) have the same meaning as commonly understood by a person of ordinary skill in the art to which this application pertains. It should also be understood that, unless clearly stated in this application, words defined in a commonly used dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense.

[0061] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will describe this application in detail with reference to the accompanying drawings and in combination with the embodiments.

[0062] Embodiment 1

[0063] Referring to Figure 1 , the first embodiment of the present invention provides a regional power peak shaving resource coordination method based on cloud computing.

[0064] Step 1: Adopt a regional power consumption prediction model that constructs a support vector machine SVR, and based on the historical power consumption data of the region, predict the regional power consumption for a future time period.

[0065] The regional power consumption prediction model that constructs a support vector machine SVR includes: using the mathematical model of the support vector machine SVR to predict the regional power consumption, assuming the region at time The power consumption is , and the historical power consumption data is , where is the input feature, n is the number of historical power consumption data, and the mathematical model of the support vector machine SVR is as follows:

[0066] ;

[0067] ;

[0068] Among them, is the weight vector, is the bias term, and are used to define the regression plane, and are slack variables, is the maximum regression deviation, is used to control the smoothness of the regression plane; is the input mapping function; is the transpose of the weight vector; is the regularization term in the objective function of the support vector machine SVR, is the time of the nth historical power consumption data.

[0069] The regional power consumption prediction model constructed based on the support vector machine SVR:

[0070] ;

[0071] Among them, N is the total number of regions, and are Lagrange multipliers, is the kernel function, is the region The predicted power consumption at time t. Using the regional power consumption prediction model constructed based on the support vector machine SVR and combining the input features of the future time period of the region, the power consumption of the region can be predicted.

[0072] The present invention uses the support vector machine regression model SVR to predict the regional power consumption. The SVR model has good generalization ability and nonlinear fitting ability, can effectively capture the change trend of the power consumption, and provides an important basis for the subsequent analysis of the power peak shaving demand.

[0073] Step 2: Based on the regional power consumption forecast results and the regional power generation power and power storage capacity, calculate the regional power peak demand, the power peak demand includes the remaining power peak time and the power peak power demand, and based on the regional power peak demand calculation results, divide the power consumption area in the future time period into power peak demand area, stable power consumption area and power surplus area.

[0074] Calculation area The peak load demand of electricity is At current time To the future time Predicted peak power consumption Larger than area Power generation in When , the calculation area At current time Predicted electricity consumption at future time point t :

[0075] ;

[0076] If the area At current time Predicted electricity consumption at future time point t Larger than area The amount of power stored in When the sum of the power generation is: , then the area There is a demand for power peak load regulation. Mark as power peak demand area and calculate the area The remaining power peak-shaving time :

[0077] ;

[0078] in, is the storage capacity of region i, It is a region At current time The power consumption at each moment.

[0079] The remaining power peak load time It is a region The remaining time during which the power generation and storage can guarantee stable power consumption in the region is required to be during the remaining power peak load time. Internal area Transmit power at a rate greater than the peak load demand, otherwise the region During the remaining power peak load period It will not be possible to ensure stable electricity supply in the area.

[0080] Then the area The peak power demand of : .

[0081] When the area At current time To the future time Predicted peak power consumption Larger than area Power generation in When and area At current time Predicted electricity consumption at future time point t Less than or equal to area The amount of power stored in When the sum of the power generation is:

[0082] ;

[0083] The power generation and storage within region i can meet its own electricity demand, and region i is divided into a stable power consumption area.

[0084] When the area At current time To the future time Predicted peak power consumption within Always smaller than area Power generation in Time, area At current time To the future time The power generated within the area is greater than the power consumed. There is no peak load demand and the area Divided into power surplus areas.

[0085] Based on the prediction results of regional power consumption, combined with the regional power generation and storage information, the regional power peak-shaving demand can be analyzed and calculated. Specifically, when the predicted regional power consumption peak exceeds the regional power generation, it means that the region may face the problem of insufficient power supply; at this time, it is necessary to calculate the predicted power consumption of the region in the future time period and compare it with the regional power storage and power generation; if the predicted power consumption is greater than the sum of the power storage and power generation, it indicates that there is a power peak-shaving demand in the region.

[0086] For areas with power peak-shaving needs, it is necessary to further calculate the remaining power peak-shaving time, that is, the remaining time that the region's own power generation and storage can maintain stable power consumption. The calculation of this time takes into account the region's storage capacity, predicted power consumption and real-time power consumption. During the remaining power peak-shaving time, sufficient electricity needs to be transferred in from other regions to meet the region's power demand.

[0087] In addition to the power peak shaving demand areas, it is also necessary to identify stable power consumption areas and power redundant areas; the characteristic of stable power consumption areas is that the predicted power consumption is less than or equal to the sum of the stored power and the generated power, indicating that the power supply within the area can meet the power demand. While the power redundant areas are those where the predicted power consumption is always less than the generated power, indicating that there is power surplus within the area, which can be used as the supply side for power peak shaving.

[0088] Step 3: Construct a regional power peak shaving resource pool based on the regional power peak shaving resources, where the regional power peak shaving resources include the generating units and energy storage devices within the region.

[0089] Suppose the th region has a power peak shaving demand, and the th region has a power surplus. During the current time to the future time period, the power available for power peak shaving in the power surplus area is the sum of the surplus power of the generating unit and the output power of the energy storage device :

[0090] ;

[0091] ;

[0092] Calculate the power available for power peak shaving in all power surplus areas

[0093] :

[0094] Among them, represents the number of areas with power surplus; the power available for power peak shaving in all power surplus areas constitutes the regional power peak shaving resource pool.

[0095] In order to achieve power peak shaving among regions, it is necessary to construct a regional power peak shaving resource pool; the resource pool includes the generating units and energy storage devices within each region. For the areas with power redundancy, their surplus generating power and the output power of the energy storage devices can be incorporated into the resource pool as the power resources available for peak shaving; through the management and scheduling of the resource pool, the optimal allocation of power resources among regions can be achieved, and the overall peak shaving capacity of the power system can be improved.

[0096] Step 4: Based on the power transmission paths between regions and the power peak shaving resource reserves, while considering the losses in power transmission between regions, with the remaining power peak shaving time and the power peak shaving power demand as the constraint conditions, construct a coordinated scheduling model for regional power peak shaving resources, and calculate the power peak shaving response power of the power surplus region to the power peak shaving demand region.

[0097] Let the set of power surplus regions be A and the set of power peak shaving demand regions be B. Then, for the power peak shaving demand region , and for the power surplus region , define the power variable as the power peak shaving response power of power surplus region j to power peak shaving demand region i.

[0098] Construct an objective function to minimize the power peak shaving response power of the power surplus region to the power peak shaving demand region, which serves as a coordinated scheduling model for regional power peak shaving resources and is used to calculate the power peak shaving response power of a single power surplus region to a single power peak shaving demand region :

[0099] ;

[0100] Calculate the power peak shaving response power in the coordinated scheduling model of regional power peak shaving resources through the constraint conditions .

[0101] The constraint conditions include that the power peak shaving response power of the j-th region in the regional power peak shaving resource pool does not exceed the available power peak shaving power of the j-th region , that is .

[0102] The constraint conditions also include that the sum of the power peak shaving response powers obtained by the power peak shaving demand region i from the regional power peak shaving resource pool is , considering the power transmission efficiency , ; and .

[0103] The constraint conditions also include considering the power transmission time from the power surplus region to the power peak shaving demand region , then:

[0104] ;

[0105] According to the coordinated scheduling model of regional power peak shaving resources, calculate the power peak shaving response power of a single power surplus region to a single power peak shaving demand region .

[0106] On the basis of constructing a regional power peak shaving resource pool, it is necessary to further establish a collaborative scheduling model for regional power peak shaving resources. This model comprehensively considers factors such as the power transmission path between regions, the reserve of power peak shaving resources, and power transmission losses. Taking the remaining power peak shaving time and the power peak shaving power demand of the region with power peak shaving requirements as constraints, through mathematical modeling and optimization solution, the optimal response strategy for the power redundant region to provide power support to the power peak shaving demand region can be calculated, that is, the power peak shaving response power of each power redundant region to each power peak shaving demand region. The goal of the collaborative scheduling model is to minimize the total power peak shaving response of the power redundant region as much as possible on the premise of ensuring the stable power consumption of the power peak shaving demand region, and realize the optimal allocation of power resources between regions.

[0107] Step 5: The power surplus region conducts power scheduling for the region with power peak shaving requirements according to the allocated power peak shaving response power.

[0108] According to the calculated power peak shaving response power of the power surplus region to the power peak shaving demand region , the power surplus region responds to the power peak shaving demand region with the power peak shaving response power After reaching time t, the regional power consumption is predicted again and the scheduling response power is calculated to ensure stable regional power consumption.

[0109] According to the calculation results of the regional power peak shaving resource collaborative scheduling model, the power redundant region needs to conduct power scheduling for the power peak shaving demand region according to the allocated power peak shaving response power. Considering factors such as the real-time operation state of the power grid and the working state of power equipment, the reliability and safety of power scheduling are ensured.

[0110] Through reasonable power scheduling, the power supply pressure of the power peak shaving demand region can be effectively relieved, and the normal power consumption demand of users in the region can be guaranteed. At the same time, the power peak shaving response of the power redundant region also helps to improve the overall operation efficiency of the power system and promote the optimal allocation of power resources between regions.

[0111] Embodiment 2

[0112] Refer to Figure 2 , the second embodiment of the present invention provides a regional power peak shaving resource collaborative system based on cloud computing.

[0113] The system includes a power consumption prediction module, a peak shaving demand calculation module, a peak shaving resource construction module, a power peak shaving response power calculation module, and a power peak shaving execution module.

[0114] The electricity consumption power prediction module uses a regional electricity consumption power prediction model constructed by support vector machine (SVR) to predict the regional electricity consumption power in a future time period based on the historical electricity consumption data of the region.

[0115] The peak shaving demand calculation module calculates the power peak shaving demand of the region based on the regional electricity consumption power prediction result, the power generation power and the electricity storage capacity of the region. The power peak shaving demand includes the remaining power peak shaving time and the power peak shaving power demand. Based on the calculation result of the regional power peak shaving demand, the electricity consumption regions in the future time period are divided into power peak shaving demand regions, stable electricity consumption regions and power surplus regions.

[0116] The peak shaving resource formation module forms a regional power peak shaving resource pool based on the regional power peak shaving resources. The regional power peak shaving resources include the generator sets and electricity storage devices within the region.

[0117] The power peak shaving response power calculation module constructs a coordinated scheduling model of regional power peak shaving resources based on the power transmission paths between regions and the reserves of power peak shaving resources, and also considers the losses in power transmission between regions. With the remaining power peak shaving time and the power peak shaving power demand as the constraint conditions, it calculates the power peak shaving response power of the power surplus region to the power peak shaving demand region.

[0118] The power peak shaving execution module performs power peak shaving scheduling on the regions with power peak shaving demands in the power surplus region according to the allocated power peak shaving response power.

[0119] In addition, in the above technical solutions provided in the embodiments of the present invention, the parts that are the same as the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid excessive elaboration.

[0120] As described in the specific embodiments above, the purpose, technical solutions and beneficial effects of the present invention have been further elaborated in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A regional power peak load resource coordination method based on cloud computing, characterized in that: include: Construct a regional power consumption prediction model using support vector machine (SVR) to predict regional power consumption in the future based on the historical power consumption data of the region; Based on the regional power consumption forecast results and the regional power generation and storage capacity, the regional power peak demand is calculated, including: The peak load demand of electricity in the region At current time To the future time Predicted peak power consumption Larger than area Power generation in When , the calculation area At current time Predicted electricity consumption at future time point t : ； If the area At current time Predicted electricity consumption at future time point t Larger than area The amount of power stored in When the sum of the power generation is: , then the area There is a demand for power peak load regulation. Mark as power peak demand area and calculate the area The remaining power peak-shaving time ; ； in, is the storage capacity of region i, It is a region At current time The power consumption at the time, It is a region The predicted power consumption at time t; Get Region The peak power demand of : ; The power peak-shaving demand includes the remaining power peak-shaving time and the power peak-shaving power demand. Based on the calculation result of the power peak-shaving demand of the region, the power consumption area in the future time period is divided into a power peak-shaving demand area, a stable power consumption area and a power surplus area; A regional power peak-shaving resource pool is constructed based on regional power peak-shaving resources, wherein the regional power peak-shaving resources include power generating units and power storage equipment within the region; Based on the inter-regional power transmission paths and power peak-shaving resource reserves, and taking into account the inter-regional power transmission losses, a regional power peak-shaving resource coordinated scheduling model is constructed with the remaining power peak-shaving time and power peak-shaving power demand as constraints, and the power peak-shaving response power of the power surplus area to the power peak-shaving demand area is calculated; The power surplus areas will dispatch power to the areas with power peak shaving demand according to the allocated power peak shaving response power.

2. The regional power peak load resource coordination method based on cloud computing according to claim 1 is characterized in that: The construction of the regional power consumption prediction model of the support vector machine SVR includes: using the mathematical model of the support vector machine SVR to predict the regional power consumption, setting the regional In time The power consumption is , the historical electricity consumption data is ,in is the input feature, n is the number of historical electricity consumption data, and the mathematical model of the support vector machine SVR is as follows: ； ； in, is the weight vector, For paranoid items, and Used to define the regression plane, and is the slack variable, is the maximum regression deviation, It is used to control the smoothness of the regression plane; is the input mapping function; is the transpose of the weight vector; It is the regularization term in the support vector machine SVR objective function; is the time of the nth historical electricity consumption data; The regional power consumption prediction model is constructed based on the mathematical model of support vector machine SVR: ； in, and is the Lagrange multiplier, is the kernel function and N is the total number of regions.

3. The regional power peak load resource coordination method based on cloud computing according to claim 2 is characterized in that: The method further comprises: when the area At current time To the future time Predicted peak power consumption Larger than area Power generation in When and area At current time Predicted electricity consumption at future time point t Less than or equal to area The amount of power stored in When the sum of the power generation is: ； area The power generation and storage of the region can meet its own electricity demand. Divided into stable electricity consumption areas; When the area At current time To the future time Predicted peak power consumption within Always smaller than area Power generation in Time, area At current time To the future time The power generated within the area is greater than the power consumed. There is no peak load demand and the area Divided into power surplus areas.

4. The regional power peak load resource coordination method based on cloud computing according to claim 3 is characterized in that: The regional power peak-shaving resource pool is constructed based on regional power peak-shaving resources, including: assuming that the i-th region has power peak-shaving demand, the j-th region has power surplus, and the current time To the future time The power available for peak load regulation in the power surplus area j is Surplus power of the generator set And the output power of the storage device sum: ； ； Calculate the power available for peak load regulation in all power surplus areas : ； in, Indicates the number of regions with power surplus; the power available for power peak regulation in all power surplus regions Form a regional power peak-shaving resource pool.

5. The regional power peak load resource coordination method based on cloud computing according to claim 4 is characterized in that: Based on the inter-regional power transmission path and power peak-shaving resource reserves, while taking into account the inter-regional power transmission loss, taking the remaining power peak-shaving time and power peak-shaving power demand as constraints, a regional power peak-shaving resource collaborative scheduling model is constructed to calculate the power peak-shaving response power of the power surplus area to the power peak-shaving demand area, including: Assume that the set of power surplus areas is A, and the set of power peak demand areas is B, then the power peak demand areas , power surplus area , define the power variable The power surplus area j is the power peak demand area The power peak load response power; The objective function of minimizing the power peak-shaving response power of the power surplus area to the power peak-shaving demand area is constructed as a regional power peak-shaving resource coordinated scheduling model to calculate the power peak-shaving response power of a single power surplus area to a single power peak-shaving demand area. : ； Calculation of power peak load response power in regional power peak load resource coordinated dispatch model based on constraint conditions ; The constraints include: The peak load response power of the power supply in each area shall not exceed The available peak power in each region ,Right now ; The constraints also include the power peak demand area The sum of the power peak load response power obtained from the regional power peak load resource pool is , considering the power transmission efficiency , ;and ; The constraints also include considering the transmission time from the power surplus area to the power peak demand area. ,but: ； According to the regional power peak load resource coordinated dispatch model, the power peak load response power of a single power surplus area to a single power peak load demand area is calculated. .

6. The regional power peak load resource coordination method based on cloud computing according to claim 5 is characterized in that: The power surplus area performs power dispatching to the area with power peak-shaving demand according to the allocated power peak-shaving response power, including: dispatching the power peak-shaving response power of the power surplus area to the area with power peak-shaving demand according to the calculated power peak-shaving response power of the power surplus area , power surplus areas respond to power peak load Respond to the peak demand area of ​​power load regulation and After a certain period of time, the regional power consumption is predicted again and the dispatch response power is calculated to ensure stable power consumption in the region.

7. A regional power peak-shaving resource coordination system based on cloud computing, which is used to implement the regional power peak-shaving resource coordination method based on cloud computing according to any one of claims 1 to 6, characterized in that: It includes an electric power prediction module, a peak-shaving demand calculation module, a peak-shaving resource assembly module, an electric power peak-shaving response power calculation module and an electric power peak-shaving execution module; The power consumption prediction module adopts a regional power consumption prediction model constructed by a support vector machine (SVR) to predict regional power consumption in future time periods based on historical power consumption data of the region; The peak-shaving demand calculation module calculates the regional power peak-shaving demand based on the regional power consumption prediction result and the regional power generation power and power storage capacity. The power peak-shaving demand includes the remaining power peak-shaving time and the power peak-shaving power demand. Based on the regional power peak-shaving demand calculation result, the power consumption area in the future time period is divided into a power peak-shaving demand area, a stable power consumption area and a power surplus area; The peak-shaving resource building module builds a regional power peak-shaving resource pool based on regional power peak-shaving resources, wherein the regional power peak-shaving resources include power generating units and power storage equipment in the region; The power peak-shaving response power calculation module is based on the inter-regional power transmission path and power peak-shaving resource reserves, while taking into account the inter-regional power transmission loss, and taking the remaining power peak-shaving time and power peak-shaving power demand as constraints, to build a regional power peak-shaving resource collaborative scheduling model, and calculate the power peak-shaving response power of the power surplus area to the power peak-shaving demand area; The power peak-shaving execution module performs power peak-shaving scheduling for the power surplus area according to the allocated power peak-shaving response power and for the area with power peak-shaving demand.

Images