KR-20260065206-A - Building load management device and method

KR20260065206AKR 20260065206 AKR20260065206 AKR 20260065206AKR-20260065206-A

Abstract

According to an embodiment, a building load management device is provided, comprising: one or more processors; and a memory for storing one or more programs executed by the one or more processors, wherein the processor comprises: a first processing unit that performs clustering based on past building load data stored in the memory to cluster a plurality of buildings and calculates a distance value between the center point of the cluster and a building included in the cluster; a second processing unit that predicts the load of a first building at a future point in time using the past building load data; a third processing unit that predicts the load of a first cluster at a future point in time using the past building load data of a first cluster including the first building; and a fourth processing unit that assigns weights to the load prediction value of the first building and the load prediction value of the first cluster using the distance value between the center point of the first cluster and the first building, and calculates a final load prediction value of the first building using the load prediction value of the first building and the load prediction value of the first cluster to which the weights are assigned.

Inventors

이민규
김현섭
정재윤
최정훈
박나연
고대건
한혜승
김성규
박범수

Assignees

현대자동차주식회사
기아 주식회사

Dates

Publication Date: 20260508
Application Date: 20241101

Claims (20)

One or more processors; and A device having a memory for storing one or more programs executed by the above-mentioned one or more processors, The above processor is, A first processing unit that performs clustering based on past building load data stored in the memory to cluster multiple buildings, and calculates a distance value between the center point of the cluster and the buildings included in the cluster; A second processing unit that predicts the load of the first building at a future point in time using the aforementioned past building load data; A third processing unit that predicts the load of the first cluster at the future point in time using past building load data of the first cluster including the first building; and A building load management device comprising a fourth processing unit that assigns weights to the load prediction value of the first building and the load prediction value of the first cluster using the distance value between the center point of the first cluster and the first building, and calculates the final load prediction value of the first building using the weighted load prediction value of the first building and the load prediction value of the first cluster.
In paragraph 1, The above first processing unit A building load management device that calculates a load pattern for a certain past period from the above past building load data, calculates at least one of a Euclidean distance value, a feature vector, and a Dynamic Time Warping (DTW) distance value with respect to a load average using the load pattern, and clusters the plurality of buildings using at least one of the Euclidean distance value, the feature vector, and the Dynamic Time Warping (DTW) distance value.
In paragraph 2, A building load management device that clusters the plurality of buildings by applying at least one of the Euclidean distance value, feature vector, and DTW (Dynamic Time Warping) distance value to the K-MEANS algorithm.
In paragraph 1, The above second processing unit is a building load management device comprising a first deep learning model trained with first learning data including building load data, weather data, and day of the week data for a past period of the first building.
In paragraph 1, The above third processing unit is a building load management device comprising a second deep learning model trained with second learning data including building load data, weather data, and day of the week data for each building included in the first cluster during a past period.
In paragraph 5, The above third processing unit is a building load management device that normalizes the building load data of the above second learning data and trains the above second deep learning model.
In paragraph 1, The above-mentioned fourth processing unit is a building load management device that increases the weight of the load prediction value of the first building and decreases the load prediction value of the first cluster in proportion to the distance value between the center point of the first cluster and the first building.
In paragraph 1, The above-mentioned fourth processing unit is a building load management device that calculates the final load prediction value of the first building by summing the load prediction value of the first building with the weights assigned and the load prediction value of the first cluster.
In paragraph 1, The above processor is a building load management device that calculates the weekday final load prediction and the weekend final load prediction of the first building using weekday building load data and weekend building load data, respectively.
In paragraph 1, A building load management device further comprising a fifth processing unit that generates a charging and discharging schedule for an electric vehicle using the final load prediction value of the first building.
A method performed by a computing device having one or more processors and a memory for storing one or more programs executed by said one or more processors, wherein The above processor, A step of clustering multiple buildings by performing clustering based on past building load data stored in the memory; A step of calculating the distance between the center point of the cluster and the buildings included in the cluster; A step of predicting the load of the first building at a future point in time using the aforementioned past building load data; A step of predicting the load of the first cluster at the future point in time using past building load data of the first cluster including the first building; A step of assigning weights to the load prediction value of the first building and the load prediction value of the first cluster using the distance value between the center point of the first cluster and the first building; and A building load management method comprising the step of calculating a final load prediction value of the first building using the load prediction value of the first building and the load prediction value of the first cluster to which the above weights are assigned.
In Clause 11, the clustering step is, A step of calculating a load pattern for a past period from the above past building load data; A step of calculating at least one of a Euclidean distance value with respect to the load average, a feature vector, and a Dynamic Time Warping (DTW) distance value using the above load pattern; and A building load management method comprising the step of clustering the plurality of buildings using at least one of the Euclidean distance value, feature vector, and DTW (Dynamic Time Warping) distance value.
In Clause 12, the clustering step is, A building load management method for clustering a plurality of buildings by applying at least one of the above Euclidean distance value, feature vector, and DTW (Dynamic Time Warping) distance value to the K-MEANS algorithm.
In Clause 11, the step of predicting the load of the first building is, A building load management method for predicting the load of the first building using a first deep learning model trained with first training data including building load data, weather data, and day of the week data for a past period of the first building.
In paragraph 11, the step of predicting the load of the first cluster is, A building load management method for predicting the load of a first cluster using a second deep learning model trained with second training data including building load data, weather data, and day of the week data for each building included in the first cluster over a past period.
In item 15, the step of predicting the load of the first cluster is, A building load management method comprising the step of normalizing the building load data of the second learning data and training the second deep learning model.
In Clause 11, the step of assigning the above weights is, A building load management method comprising the step of increasing the weight of the load prediction value of the first building in proportion to the distance value between the center point of the first cluster and the first building, and decreasing the load prediction value of the first cluster.
In Clause 11, the step of calculating the final load prediction of the first building is, A building load management method that calculates the final load prediction of the first building by summing the load prediction of the first building with the weights assigned and the load prediction of the first cluster.
In Paragraph 11, A building load management method in which the above processor calculates the weekday final load forecast and the weekend final load forecast of the first building using weekday building load data and weekend building load data, respectively.
In Clause 11, after the step of calculating the final load prediction of the first building, A building load management method further comprising the step of generating a charging and discharging schedule for an electric vehicle using the final load prediction value of the first building.

Description

Building load management device and method One embodiment of the present invention relates to a building load management device and method, and more specifically, to a building load management device and method applicable to a V2B (vehicle to building) platform. As electric vehicle technology advances, Vehicle-to-Grid (V2G) technology is developing by treating them as individual energy storage systems (ESS) and connecting them to the power grid. This V2G technology is seen as capable of resolving the issue of stabilizing the supply and demand of the power grid by utilizing electric vehicle batteries. Depending on where the electricity is used, it is referred to as V2H (vehicle to home), V2B (vehicle to building), or V2G. Among these, V2B, which supplies power from electric vehicle batteries to buildings, is being demonstrated, and attempts are being made toward the future commercialization of V2G. If the building's maximum load is exceeded, the contracted power may be increased, potentially leading to a rise in the basic electricity rate; therefore, securing available resources for electric vehicles through accurate load forecasting is emerging as a critical issue for the commercialization of V2B. FIG. 1 is a drawing for explaining an electric vehicle power management system according to an embodiment. FIG. 2 is a block diagram of a building load management device according to an embodiment. FIG. 3 is a diagram illustrating the operation of a building load management device according to an embodiment. FIGS. 4 to 12 are drawings for explaining the operation of a first processing unit according to an embodiment. FIG. 13 is a diagram for explaining the operation of a second processing unit according to an embodiment. FIG. 14 is a diagram for explaining the operation of a third processing unit according to an embodiment. FIG. 15 is a diagram illustrating the operation of a fourth processing unit according to an embodiment. FIG. 16 is a diagram illustrating the operation of the fifth processing unit according to an embodiment. FIG. 17 is a flowchart of a building load management method according to an embodiment. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. However, the technical concept of the present invention is not limited to some of the described embodiments but can be implemented in various different forms, and within the scope of the technical concept of the present invention, one or more of the components among the embodiments may be selectively combined or substituted. In addition, terms used in the embodiments of the present invention (including technical and scientific terms) may be interpreted in a sense that is generally understood by those skilled in the art to which the present invention belongs, unless explicitly and specifically defined otherwise. Terms that are commonly used, such as terms defined in advance, may be interpreted in consideration of their meaning in the context of the relevant technology. Furthermore, the terms used in the embodiments of the present invention are for the purpose of describing the embodiments and are not intended to limit the present invention. In this specification, the singular form may include the plural form unless specifically stated otherwise in the text, and when described as "at least one of A and B and C (or more than one)," it may include one or more of all combinations that can be formed from A, B, and C. In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention. These terms are intended merely to distinguish a component from other components and are not limited by the nature, order, sequence, etc., of the said component. And, where it is stated that a component is 'connected', 'combined', or 'joined' to another component, this may include not only cases where the component is directly connected, combined, or joined to the other component, but also cases where it is 'connected', 'combined', or 'joined' due to another component located between the component and the other component. Furthermore, when described as being formed or placed "above or below" each component, "above" or "below" includes not only cases where two components are in direct contact with each other, but also cases where one or more other components are formed or placed between the two components. Additionally, when expressed as "above or below," it may include the meaning of a downward direction as well as an upward direction relative to a single component. Hereinafter, embodiments will be described in detail with reference to the attached drawings, provided that identical or corresponding components are given the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted. FIG. 1 is a drawing for illustrating an electric vehicle power management system according to