非住宅空置率数据

通过电力数据构建非住宅空置率模型，可以真实迅速地反映非住宅的空置水平，从而有效解决传统依赖未使用办公面积占比计算空置率的方法所带来的高人力资源消耗和动态监控难题。1.数据清洗：对数据集进行清洗，包括去除异常数据、处理缺失值。 2.算法模型：本模型可以计算每月地市及区县维度的非住宅空置率情况，具体计算逻辑如下： （1）整体模型构建思路 主要参考传统楼房空置率计算方法（以未使用的办公面积占比作为空置水平），本模型通过电力数据中楼房月平均负荷占楼房满负载容量的比重来反映楼房使用率，那么空置率则可以表示为1-楼房使用率，楼房满负载容量通过楼房合同容量乘以满负载比例计算而得，满负载比例则可以通过基准空置率以及月平均负荷计算出来。因此，只需要通过外部数据获取楼房的基准空置率，结合电力数据即可计算后续每月空置率情况。 （2）模型推导 R=1-(Q/22/8)/（C*(βt+αt)） R：为要计算的非住宅空置率； Q：为该月用电量； C：为该月的合同容量 ；βt+αt：为满负载比例 ；βt在租负载比例：为在租负载比例；αt空置负载比例： αt=（βt*基准空置率）/(1-基准空置率)。 （3）基准空置率：戴德梁行发布的上年度非住宅空置率。 3、数据来源：国网浙江省电力公司营销服务中心作为电力行业核心业务管理部门，有权对电力用户的基础信息、用电行为、计量数据及业务运营信息进行权威采集、整合与处理，并传输至省电力公司数据中台进行产品加工。Constructing a non-residential vacancy rate model using electricity data can accurately and rapidly reflect the vacancy level of non-residential buildings, effectively resolving the high labor costs and dynamic monitoring challenges caused by traditional methods that calculate vacancy rates based on the proportion of unused office area. 1. Data Cleaning Clean the dataset, including removing abnormal data and handling missing values. 2. Algorithm Model This model can calculate the non-residential vacancy rate at the municipal and district/county levels on a monthly basis. The specific calculation logic is as follows: (1) Overall Model Construction Rationale This model primarily draws on the traditional building vacancy rate calculation framework, which uses the proportion of unused office space as the vacancy level. This model utilizes the proportion of a building's monthly average load to its full load capacity from electricity data to reflect the building's utilization rate. Thus, the vacancy rate can be expressed as 1 minus the building's utilization rate. The full load capacity of a building is calculated by multiplying its contract capacity by the full load ratio, which can be derived using the benchmark vacancy rate and the monthly average load. Therefore, only by obtaining the building's benchmark vacancy rate via external data can the monthly vacancy rates for subsequent periods be calculated in combination with the electricity data. (2) Model Derivation $$R=1-frac{Q}{22 imes8}/left[C imes(eta_t+alpha_t) ight]$$ Where: $R$: The non-residential vacancy rate to be calculated; $Q$: Monthly electricity consumption; $C$: Monthly contract capacity; $eta_t+alpha_t$: Full load ratio; $eta_t$: Leased load ratio; $alpha_t$: Vacant load ratio, and $alpha_t=frac{eta_t imes ext{benchmark vacancy rate}}{1- ext{benchmark vacancy rate}}$. (3) Benchmark Vacancy Rate The non-residential vacancy rate of the previous year released by Cushman & Wakefield. 3. Data Source As the core business management department of the power industry, the Marketing Service Center of State Grid Zhejiang Electric Power Company has the authority to conduct authoritative collection, integration and processing of basic information, electricity consumption behavior, metering data and business operation information of power users, and transmit these data to the provincial power company data middle platform for product processing.

搜集汇总

背景与挑战

背景概述

非住宅空置率数据集包含500条记录，每月更新，通过电力数据计算非住宅空置率，用于解决传统空置率计算方法的高成本和动态监控问题。