Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become paramount.In this vein,efforts have been made to predict the HL and CL using a univariate approach.However,this approach necessitates two models for learning HL and CL,requiring more computational time.Moreover,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware requirement.In this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D CNN.Considering the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and CL.As the 1D data are not affected by excessive parameters,the pooling layer is not applied in this implementation.Besides,the use of pooling has been questioned by recent studies.The performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

Comprehensive power-supply planning for active distribution system considering cooling,heating and power load balance

An active distribution system power-supply planning model considering cooling,heating and power load balance is proposed in this paper.A regional energy service company is assumed to be in charge of the investment and operation for the system in the model.The expansion of substations,building up distributed combined cooling,heating and power(CCHP),gas heating boiler(GHB)and air conditioner(AC)are included as investment planning options.In terms of operation,the load scenarios are divided into heating,cooling and transition periods.Also,the extreme load scene is included to assure the power supply reliability of the system.Numerical results demonstrate the effectiveness of the proposed model and illustrate the economic benefits of applying distributed CCHP in regional power supply on investment and operation.

Optimal Thermal Insulation Thickness in Isolated Air-Conditioned Buildings and Economic Analysis

The removal building heat load and electrical power consumption by air conditioning system are proportional to the outside conditions and solar radiation intensity. Building construction materials has substantial effects on the transmission heat through outer walls, ceiling and glazing windows. Good thermal isolation for buildings is important to reduce the transmitted heat and consumed power. The buildings models are constructed from common materials with 0 - 16 cm of thermal insulation thickness in the outer walls and ceilings, and double-layers glazing windows. The building heat loads were calculated for two types of walls and ceiling with and without thermal insulation. The cooling load temperature difference method, CLTD, was used to estimate the building heat load during a 24-hour each day throughout spring, summer, autumn and winter seasons. The annual cooling degree-day, CDD was used to estimate the optimal thermal insulation thickness and payback period with including the solar radiation effect on the outer walls surfaces. The average saved energy percentage in summer, spring, autumn and winter are 35.5%, 32.8%, 33.2% and 30.7% respectively, and average yearly saved energy is about of 33.5%. The optimal thermal insulation thickness was obtained between 7 - 12 cm and payback period of 20 - 30 month for some Egyptian Cities according to the Latitude and annual degree-days.

Comparison of space cooling/heating load under non-uniform indoor environment with convective heat gain/loss from envelope

The indoor parameters are generally non-uniform distributed.Consequently,it is important to study the space cooling/heating load oriented to local requirements.Though the influence of indoor set point,heat sources,and ambient temperature of convective thermal boundary on cooling/heating load has been investigated in the uniform environment in previous research,the influence of these factors,particularly the convective heat gain/loss through a building envelope,on cooling/heating load of non-uniform environment has not yet been investigated.Therefore,based on the explicit expression of indoor temperature under the convective boundary condition,the expression of space cooling/heating load with convective heat transfer from the building envelope is derived and compared through case studies.The results can be summarized as follows.(1)The convective heat transferred through the building envelope is significantly related to the airflow patterns:the heating load in the case with ceiling supply air,where the supply air has a smaller contribution to the local zone,is 24%higher than that in the case with bottom supply air.(2)The degree of influence from each thermal boundary to the local zone of space cooling cases is close to that of a uniform environment,while the influence of each factor,particularly that of supply air,is non-uniformly distributed in space heating.(3)It is possible to enhance the influence of supply air and heat source with a reasonable airflow pattern to reduce the space heating load.In general,the findings of this study can be used to guide the energy savings of rooms with non-uniform environments for space cooling/heating.

Numerical simulation study on the hygrothermal performance of building exterior walls under dynamic wind-driven rain condition

Wind-driven rain(WDR)has a significant influence on the hygrothermal performance,durability,and energy consumption of building components.The calculation of WDR loads using semi-empirical models has been incorporated into the boundary conditions of coupled heat and moisture transfer models.However,prior research often relied on fixed WDR absorption ratio,which fail to accurately capture the water absorption characteristics of porous building materials under rainfall scenarios.Therefore,this study aims to investigate the coupled heat and moisture transfer of exterior walls under dynamic WDR boundary conditions,utilizing an empirically obtained WDR absorption ratio model based on field measurements.The developed coupled heat and moisture transfer model is validated against the HAMSTAD project.The findings reveal that the total WDR flux calculated with the dynamic WDR boundary is lower than that obtained with the fixed WDR boundary,with greater disparities observed in orientations experiencing higher WDR loads.The variations in moisture flow significantly impact the surface temperature and relative humidity of the walls,influencing the calculation of cooling and heating loads by different models.Compared to the transient heat transfer model,the coupled heat and moisture transfer model incorporating dynamic WDR boundary exhibits maximum increases of 17.6%and 16.2%in cooling and heating loads,respectively.The dynamic WDR boundary conditions provide more precise numerical values for surface moisture flux,offering valuable insights for the thermal design of building enclosures and load calculations for HVAC systems.

Optimized scheduling of integrated energy systems for low carbon economy considering carbon transaction costs

With the introduction of the“dual carbon”goal and the continuous promotion of low-carbon development,the integrated energy system(IES)has gradually become an effective way to save energy and reduce emissions.This study proposes a low-carbon economic optimization scheduling model for an IES that considers carbon trading costs.With the goal of minimizing the total operating cost of the IES and considering the transferable and curtailable characteristics of the electric and thermal flexible loads,an optimal scheduling model of the IES that considers the cost of carbon trading and flexible loads on the user side was established.The role of flexible loads in improving the economy of an energy system was investigated using examples,and the rationality and effectiveness of the study were verified through a comparative analysis of different scenarios.The results showed that the total cost of the system in different scenarios was reduced by 18.04%,9.1%,3.35%,and 7.03%,respectively,whereas the total carbon emissions of the system were reduced by 65.28%,20.63%,3.85%,and 18.03%,respectively,when the carbon trading cost and demand-side flexible electric and thermal load responses were considered simultaneously.Flexible electrical and thermal loads did not have the same impact on the system performance.In the analyzed case,the total cost and carbon emissions of the system when only the flexible electrical load response was considered were lower than those when only the flexible thermal load response was taken into account.Photovoltaics have an excess of carbon trading credits and can profit from selling them,whereas other devices have an excess of carbon trading and need to buy carbon credits.

建筑内热源滞后冷负荷监测模型研究

准确获取内热源实时冷负荷对于制定供暖空调系统节能调控策略及降低建筑运行能耗具有重要意义,而辐射热传递过程产生的滞后冷负荷是内热源冷负荷计算的难点,为此,基于围护结构蓄放热规律、热传递特性及传递函数原理等建立内热源滞后冷负荷监测模型,该模型为10阶传递函数。为了简化计算过程、提高计算精度,利用辐射时间系数对该模型进行参数辨识及降阶分析,最终得到2阶传递函数。建立试验系统对模型进行验证,结果显示,模型的平均绝对百分比误差为8.19%。内热源滞后冷负荷监测模型可依托能耗监测平台实现负荷的在线监测,对描述滞后冷负荷的时间延迟规律及幅度衰减特性具有理论意义,为制定供暖空调系统节能调控策略提供理论依据。

计及区域建筑群生长特性的动态冷热负荷预测

考虑区域建筑群的动态生长特性,结合负荷计算理论、灰色Verhulst模型及等维新息灰色理论,采用MATLAB构建完整的区域动态冷热负荷预测方法,以常州高铁新城2017—2022年的建筑面积为历史数据,对区域未来10年的冷热负荷进行预测.结果表明,采用基于等维新息灰色理论的Verhulst灰色模型建立的3种业态面积预测方程拟合精度均达到一级.高铁新城未来10年冷热负荷先快速增长后缓慢增长直至饱和,达到饱和的时间约为2030年,冷、热负荷饱和规模分别为436、228 MW,与采用面积指标法的计算结果(冷负荷为472 MW、热负荷为285 MW)相比,分别降低了约7.52%、19.86%.

人工神经元网络和径向基网络模型预测建筑冷热负荷的研究

采用人工神经元网络(ANN)和径向基网络(RBF)模型预测了建筑冷热负荷,判断了影响建筑能耗的显著因素。通过对ANN和RBF模型隐含层神经元数量进行优化,发现8-65-1和8-97-1结构的ANN模型预测建筑热、冷负荷与数据集中的结果比较吻合,相关系数(R^(2))分别为0.962、0.953;8-28-1和8-6-1结构的RBF模型预测的结果更加吻合,R^(2)达到了0.985、0.997。RBF模型的预测精度要优于ANN模型,RBF模型预测热、冷负荷与数据集结果的R^(2)分别为0.989、0.992,而ANN的R^(2)分别为0.972、0.967。采用敏感性分析发现,影响建筑冷热负荷的8个参数中表面积的影响最显著,其次是墙面积、屋顶面积和玻璃面积,而玻璃面积分布及相对密实度的影响最不显著。

冷热双向全周期维度蓄能空调系统设计优化

蓄能空调系统涉及“源”侧电力供应和“荷”侧建筑冷热需求双重动态变化特性,系统的容量配置是一个技术经济寻优问题。受室内外多种因素共同影响,建筑冷热负荷每天的逐时分布规律差别较大,传统上仅基于设计日等典型周期逐时负荷分布规律的设计方法使得蓄能空调系统容量的配置不合理。突破传统设计方法的不足,提出以空调系统全年运行性能为导向的冷热双向全周期维度蓄能空调系统性能化设计方法,能够考虑到全供暖季、全制冷季每天的逐时动态负荷分布规律,耦合建筑冷热负荷双向需求,获得更加科学合理的蓄能空调系统容量配置方案。用具体案例进行了设计方法展示。

电机冷却水热时间常数模型分析及影响因素研究

为保证半导体精密运动设备内精密温度控制模块的精度及稳定性,建立了负载电机冷却水热时间常数理论计算模型,用于计算电机工作时的最大热负荷梯度,为精密温度控制模块选型提供依据。理论模型表明冷却水热时间常数主要受电机结构、材料热物性和冷却水流量影响。仿真结果表明,电机冷却水温度随时间变化基本符合时间常数理论模型,冷却水时间常数与电机热功率无关,但随着电机冷却水流量的减小而增大,仿真值与理论模型计算差值为27%。实验结果与仿真结果基本一致,相同工况下仿真与实验得到的冷却水时间常数最大差值为7%。

多能耦合互补系统在公路房建既有建筑应用中的性能分析

在碳达峰、碳中和政策背景下,以公路房建单体建筑为研究对象,对其供能系统进行分析。针对传统单一供能系统的不足,文章提出将冷热电气多联产供能系统应用在房建单体建筑中,并对设计的多联产供能系统进行分析,利用Trnsys软件对其进行仿真模拟,与传统建筑供能系统进行对比,得到该冷热电气多联产供能系统运用在公路房建中的可行性与优越性。对系统中的沼气池最佳保温层厚度进行了研究,利用Fluent模拟了在最佳保温层厚度下沼气池温度场的分布情况。

气候变化对我国不同气候区办公建筑能耗影响分析

自工业文明以来,全球气候持续变化,且在不同时期的变化规律也不尽相同,近年来全球气候变化呈现加剧态势。室外环境是影响建筑能耗的关键因素,在全球气候变化加剧的背景下,准确分析气候变化对建筑冷热负荷的影响对办公建筑节能低碳技术的发展与应用具有重要意义。选取10个位于中国不同气候区的城市,基于各城市1960—2014年(西安市为1960—2013年)的真实历史气象数据,以及2种典型浓度路径(RCP)(即高水平RCP 8.5和中等水平RCP 4.5)下的未来气象预测数据,采用建筑能耗模拟软件和回归分析方法探究气候变化对不同气候区办公建筑能耗的影响。结果表明受到气候变化的影响,不同城市的建筑冷热负荷变化为40%~400%,在未来建筑和暖通空调系统设计时应更加关注气候变化及其对建筑能耗的潜在影响。

基于热湿负荷与自适应预测时域微网优化调度

为了提升建筑冷热电联供(CCHP)微网灵活性并减少负荷波动,开展建筑湿负荷参与日前需求响应的效果和日内预测时域的自适应调节方法研究.在日前阶段,构建包含建筑湿负荷的冷负荷需求响应模型;在日内阶段,提出基于预测负荷方差的自适应预测时域模型预测控制(MPC)方法.在日前阶段,分析分时电价下包含湿负荷的冷负荷需求响应对总经济成本和蓄能水罐蓄冷量的影响;在日内阶段,分析采用自适应预测时域MPC方法对计算时间、成本和各类设备工作状态的影响.结果表明,考虑湿负荷的冷负荷需求响应降低了日前阶段成本7.75%;在日内阶段,自适应预测时域MPC方法不仅能够平衡计算时间和成本,还能够增加蓄能量和平滑燃气内燃机出力.

数据中心园区供冷供热方案浅析

对于同时有供冷供热需求的数据中心园区,有些数据中心会采用冷热源独立设置的方式,例如供冷采用间接蒸发冷却空调系统,供热采用市政热水或燃气锅炉。也有些数据中心会使用冷凝热回收技术,采用热泵机组夏季供冷,冬季同时供冷供热。本文针对冷热都有需求的数据中心园区进行系统分析,通过数据对比,探讨不同方案的可行性和应用场景。

大型建筑群复合式热泵供热供冷技术研究及规模化应用

建筑供热供冷是社会各界高度关注的民生工程,热泵是将热能从低品位提升到高品位的高效低碳供能方式,也是国际建筑领域实现碳中和的重要途径。本项目针对大型建筑群复合式热泵供热供冷系统存在总冷热负荷动态预测方法缺失、规划设计体系不完备、系统运行能效低、关键技术和产品不配套、规模化推广难度大等问题,以提升复合式热泵系统能效、有效推进规模化应用为目标,系统性地开展了“负荷预测-优化设计-智慧运行-关键产品-标准推广”的全链条创新工作:提出了基于建筑特征、用户需求的大型建筑群供热供冷系统总负荷动态预测方法,开发了冷热动态负荷特征因子数据库和建筑群负荷集合寻优工具;提出了一种多场景复合式热泵系统能源总线架构理论,建立了仿真平台及综合评价体系,形成了系统容量弹性配置方法;建立了数字孪生复合式热泵系统模型,提出分层控制架构和预测方法,建立了智慧优化运行控制体系;研发了大型复合式热泵系统的关键技术和成套产品;制定了相关工程标准。相关研究成果实现了规模化稳定高效利用可再生能源供热供冷的技术突破,对推进建筑用能方式变革和实现建筑领域国家双碳战略起到重要支撑作用。

基于改进型以热定电模式的CCHP系统最优运行方法研究

冷热电联产(CCHP)系统是提高能源集约使用效率,深化能源体系转型,实现“双碳”目标的重要方式。搭建了含有微型燃气轮机、光伏发电单元、燃气锅炉和蓄电池组等在内的CCHP系统模型,基于常见的以热定电运行模式和以电定热运行模式提出了改进型以热定电运行模式。所提运行模式能有效提升系统运行的经济性和系统能源管理的有效性,实现更高的能源节约率。

Analysis and Economic Evaluation of Hourly Operation Strategy Based on MSW Classification and LNG Multi-Generation System

In this study,a model of combined cooling,heating and power system with municipal solid waste(MSW)and liquefied natural gas(LNG)as energy sources was proposed and developed based on the energy demand of a large community,andMSW was classified and utilized.The systemoperated by determining power by heating load,and measures were taken to reduce operating costs by purchasing and selling LNG,natural gas(NG),cooling,heating,and power.Based on this system model,three operation strategies were proposed based on whether MSW was classified and the length of kitchen waste fermentation time,and each strategy was simulated hourly throughout the year.The results showed that the strategy of MSW classified and centralized fermentation of kitchen waste in summer(i.e.,strategy 3)required the least total amount of LNG for the whole year,which was 47701.77 t.In terms of total annual cost expenditure,strategy 3 had the best overall economy,with the lowest total annual expenditure of 2.7730×108 RMB at LNG and NG unit prices of 4 and 4.2 RMB/kg,respectively.The lower heating value of biogas produced by fermentation of kitchen waste from MSW being classified was higher than that of MSW before being classified,so the average annual thermal economy of the operating strategy of MSW being classified was better than that of MSW not being classified.Among the strategies in which MSW was classified and utilized,strategy 3 could better meet the load demand of users in the corresponding season,and thus this strategy had better thermal economy than the strategy of year-round fermentation of kitchen waste(i.e.,strategy 2).The hourly analysis data showed that the net electrical efficiency of the system varies in the same trend as the cooling,heating and power loads in all seasons,while the relationship between the energy utilization efficiency and load varied from season to season.This study can provide guidance for the practical application of MSW being classified in the system.

带新风功能的房间空气调节器全年新风耗电量理论分析

为了分析带新风功能的房间空气调节器的全年耗电量,在上海地区标准年气象条件下,对某款带新风功能的挂壁式房间空气调节器的全年新风耗电量进行计算及理论分析。结果表明:按需换新风、提高新风电机效率以及回收冬季换新风过程中的室内排向室外空气中的热量,是实现带新风功能的房间空气调节器节能减碳运行的重要途径。

某高层办公楼变风量空调系统设计

介绍某办公楼标准层变风量空调系统的设计方法,详细计算每个温控区的送风量、空调器送风量和冷负荷、各项温升、供热量、供热送风温度等参数,绘制空气处理过程焓湿图,总结了系统设计的注意事项,供同类工程设计参考。