Umeå University's logo

umu.sePublications
Change search
Link to record
Permanent link

Direct link
Lu, Weizhuo, Professor
Publications (10 of 20) Show all publications
Penaka, S. R., Feng, K., Olofsson, T., Rebbling, A. & Lu, W. (2024). Improved energy retrofit decision making through enhanced bottom-up building stock modelling. Energy and Buildings, 318, Article ID 114492.
Open this publication in new window or tab >>Improved energy retrofit decision making through enhanced bottom-up building stock modelling
Show others...
2024 (English)In: Energy and Buildings, ISSN 0378-7788, E-ISSN 1872-6178, Vol. 318, article id 114492Article in journal (Refereed) Published
Abstract [en]

Modelling the performance of building stocks is crucial in facilitating the renovation at the building stock level. Bottom-up building stock modelling begins by detailing individual buildings and then aggregates them into stock level. Its primary advantage lies in capturing the inherent heterogeneity among distinct buildings, which enables tailored retrofitting. Naturally, this approach requires a comprehensive dataset with detailed building information such as geometry and envelope thermal properties. However, a common challenge is the incompleteness of available data in individual datasets. To address this, previous bottom-up studies have filled the missing data with representative or statistical data. Such practice could lead to homogeneous modelling of distinct buildings within the same statistical group. This limits the utilization of key ability of bottom-up building stock modelling in capturing heterogeneity, such as tailored retrofitting to explore potential retrofitting areas and strategies. To address this challenge of homogeneous modelling, we utilize data fusion framework for bottom-up building stock modelling, employing probabilistic record linkage and inverse modelling techniques to integrate multiple incomplete building performance datasets. This framework fills the missing data in one dataset with information from another, thus capturing inherent heterogeneity in the building stock. An empirical study was conducted in Umeå, Sweden, to investigate the framework's effectiveness by modelling building stock with various retrofitting strategies. This study contribution lies in enhancing bottom-up building stock modelling by capturing inherent heterogeneity, to provide tailored retrofitting solutions.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Bottom-up, Building stock modelling, Data fusion, Energy efficiency, Heterogeneity, Incomplete data, Inverse modelling, Record linkage
National Category
Other Civil Engineering
Identifiers
urn:nbn:se:umu:diva-227827 (URN)10.1016/j.enbuild.2024.114492 (DOI)2-s2.0-85197361082 (Scopus ID)
Projects
Intelligent Human-Buildings Interactions Lab: Identify, Quantify and Guide Energy-saving Behavior at University CampusRESILIENTa Energisystem Kompetenscentrum
Funder
Swedish Research Council Formas, 2022-01475Swedish Energy Agency, P2022-00141Swedish Energy Agency, 52686-1Swedish Research Council Formas, 2020-02085
Available from: 2024-07-12 Created: 2024-07-12 Last updated: 2024-07-12Bibliographically approved
Liu, B., Lu, W., Olofsson, T., Zhuang, X. & Rabczuk, T. (2024). Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of Polymeric graphene-enhanced composites. Composite structures, 327, Article ID 117601.
Open this publication in new window or tab >>Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of Polymeric graphene-enhanced composites
Show others...
2024 (English)In: Composite structures, ISSN 0263-8223, E-ISSN 1879-1085, Vol. 327, article id 117601Article in journal (Refereed) Published
Abstract [en]

We introduce an interpretable stochastic integrated machine learning based multiscale approach for the prediction of the macroscopic thermal conductivity in Polymeric graphene-enhanced composites (PGECs). This method encompasses the propagation of uncertain input parameters from the meso to macro scale, implemented through a foundational bottom-up multi-scale framework. In this context, Representative Volume Elements in Finite Element Modeling (RVE-FEM) are employed to derive the homogenized thermal conductivity. Besides, we employ two sets of techniques: Regression-tree-based methods (Random Forest and Gradient Boosting Machine) and Neural networks-based approaches (Artificial Neural Networks and Deep Neural Networks). To ascertain the relative influence of factors on output estimations, the SHapley Additive exPlanations (SHAP) algorithm is integrated. This interpretable machine learning methodology demonstrates strong alignment with published experimental data. It holds promise as an efficient and versatile tool for designing new composite materials tailored to applications involving thermal management.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Polymeric graphene-enhanced composites (PGECs), Interpretable Integrated Learning, Stochastic multi-scale modeling, Thermal properties, Data-driven technique
National Category
Composite Science and Engineering Applied Mechanics
Identifiers
urn:nbn:se:umu:diva-215912 (URN)10.1016/j.compstruct.2023.117601 (DOI)001102527500001 ()2-s2.0-85175088621 (Scopus ID)
Funder
The Kempe Foundations, JCK-2136EU, Horizon 2020, 101016854J. Gust. Richert stiftelse, 2023-00884Swedish Research Council, 2018-05973Swedish Research Council, 2022-06725
Available from: 2023-10-29 Created: 2023-10-29 Last updated: 2024-07-04Bibliographically approved
Man, Q., Yu, H., Feng, K., Olofsson, T. & Lu, W. (2024). Transfer of building retrofitting evaluations for data-scarce conditions: an empirical study for Sweden to China. Energy and Buildings, 310, Article ID 114041.
Open this publication in new window or tab >>Transfer of building retrofitting evaluations for data-scarce conditions: an empirical study for Sweden to China
Show others...
2024 (English)In: Energy and Buildings, ISSN 0378-7788, E-ISSN 1872-6178, Vol. 310, article id 114041Article in journal (Refereed) Published
Abstract [en]

Evaluating and comparing the performances of different strategies is critical for energy-efficient building retrofitting. Data-driven modelling based on large building performance datasets is an effective method for such evaluations. However, it could be challenging to apply this approach to buildings from data-scarce areas where local building performance datasets have not been well-established, which means the data falls short of the high demand for building retrofitting on a global level. To address this, a transfer learning approach is proposed in this study that can evaluate the performance of buildings without local well-established building performance datasets. The proposed approach is applied in the Swedish-Chinese empirical study that relies on the Swedish dataset to transfer and predict the building performance in China without well-established datasets. It was achieved by applying fuzzy C-means clustering and a neural network (FCM-BRBNN) to pre-train the evaluation model based on the Swedish dataset. Then, the proposed approach collects a small sample of Chinese buildings in the data-scarce area and transfers the model to local building performance prediction. The results show that the transfer learning approach can reliably predict the performance of building retrofitting in data-scarce areas with only hundreds of local building samples. As such, this study provides a novel methodology that can support the evaluation and comparison of retrofitting strategies in data-scarce regions and countries with only limited local data. It could efficiently assist designers in optimizing energy-efficient designs in the pre-retrofit stage. Crucially, the methodology enables the transfer of knowledge regarding building performance across different countries and regions, being pivotal for the international collaboration required to stimulate the global energy-efficiency transformation.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Building retrofitting, Data-driven model, Energy-efficient, Transfer learning
National Category
Building Technologies
Identifiers
urn:nbn:se:umu:diva-223261 (URN)10.1016/j.enbuild.2024.114041 (DOI)2-s2.0-85187962486 (Scopus ID)
Funder
Swedish Research Council Formas, 2020-02085Swedish Research Council Formas, 2022-01475Swedish Energy Agency, P2022-00141
Available from: 2024-04-18 Created: 2024-04-18 Last updated: 2024-04-18Bibliographically approved
Hu, S., Qiu, S., Feng, K., Man, Q., Olofsson, T. & Lu, W. (2023). A data-driven exploration of the relations between occupant behaviors and comfort performances of energy-efficient measures. In: Yaowu Wang; Feng Lan; Geoffrey Q. P. Shen (Ed.), ICCREM 2023: the human-centered construction transformation - proceedings of the international conference on construction and real estate management 2023. Paper presented at 2023 International Conference on Construction and Real Estate Management: The Human-Centered Construction Transformation, ICCREM 2023, Xi'an, China, 23-24 September, 2023. (pp. 592-604). American Society of Civil Engineers (ASCE)
Open this publication in new window or tab >>A data-driven exploration of the relations between occupant behaviors and comfort performances of energy-efficient measures
Show others...
2023 (English)In: ICCREM 2023: the human-centered construction transformation - proceedings of the international conference on construction and real estate management 2023 / [ed] Yaowu Wang; Feng Lan; Geoffrey Q. P. Shen, American Society of Civil Engineers (ASCE), 2023, p. 592-604Conference paper, Published paper (Refereed)
Abstract [en]

Energy-efficient building retrofitting plays a crucial role in reducing energy consumption and carbon emissions within the building sector. Energy-efficient retrofitting brings about changes in the built environment and it could influence the occupant behaviors. Additionally, occupant behaviors, in turn, alter the indoor environment, thereby affecting the comfort performance of the building after retrofitting. To explore this intricate relation between occupant behaviors and comfort performances of energy-efficient measures, this paper employs a data-driven approach to compile a comprehensive dataset encompassing occupant behaviors, energy-efficient measures, and associated indoor comfort of an office building in Umeå University, Sweden. Multiple binary logistic regression is applied to quantify the relationship between occupant behaviors and comfort performances of energy-efficient measures. The findings of this study hold significant value, providing guidance for occupants in adapting to energy-efficient measures while also informing future retrofitting implementation.

Place, publisher, year, edition, pages
American Society of Civil Engineers (ASCE), 2023
National Category
Construction Management
Identifiers
urn:nbn:se:umu:diva-219498 (URN)10.1061/9780784485217.058 (DOI)2-s2.0-85181534282 (Scopus ID)9780784485217 (ISBN)
Conference
2023 International Conference on Construction and Real Estate Management: The Human-Centered Construction Transformation, ICCREM 2023, Xi'an, China, 23-24 September, 2023.
Available from: 2024-01-25 Created: 2024-01-25 Last updated: 2024-01-25Bibliographically approved
Penaka, S. R., Feng, K., Rebbling, A., Azizi, S., Lu, W. & Olofsson, T. (2023). A data-driven framework for building energy benchmarking and renovation decision-making support in Sweden. In: SBE23-Thessaloniki: Sustainable built environments: Paving the way for achieving the targets of 2030 and beyond. Paper presented at 2023 Sustainable Built Environments: Paving the Way for Achieving the Targets of 2030 and Beyond, SBE23-Thessaloniki, Online, March 22-24, 2023. Institute of Physics (IOP), Article ID 012005.
Open this publication in new window or tab >>A data-driven framework for building energy benchmarking and renovation decision-making support in Sweden
Show others...
2023 (English)In: SBE23-Thessaloniki: Sustainable built environments: Paving the way for achieving the targets of 2030 and beyond, Institute of Physics (IOP), 2023, article id 012005Conference paper, Published paper (Refereed)
Abstract [en]

In Europe, the buildings sector is responsible for 40% of energy use and more than 30% of buildings are older than 50 years. Due to ageing, a large number of houses require energy-efficient renovation to meet building energy performance standards and the national energy efficiency target. Although Swedish house owners are willing to improve energy efficiency, there is a need for a dedicated platform providing decision-making knowledge for house owners to benchmark their buildings. This paper proposes a data-driven framework for building energy renovation benchmarking as part of an energy advisory service development for the Vasterbotten region, Sweden. This benchmark model facilitates regional homeowners to benchmark their building energy performance relative to the national target and similar neighbourhood buildings. Specifically, based on user input data such as energy use, location, construction year, floor area, etc., this model benchmarks the user's building performance using two benchmark references i.e., 1) Sweden's target to reduce buildings by 50% energy use intensity (EUI) by 50% by 2050 compared to the average EUI in 1995, 2) comparing user building with the most relevant peer group of buildings, using energy performance certificates (EPC) big data. Several building groups will be classified based on influential factors that affect building energy use. Hence, this benchmark provides decision-making supportive knowledge to homeowners e.g., whether they need to perform an energy-efficient renovation. In the future, this methodology will be extended and implemented in the digital platform to provide helpful insights to decide on suitable EEMs. This work is an integral part of project AURORAL aims to deliver an interoperable, open, and integrated digital platform, demonstrated by cross-domain applications through large-scale pilots in 8 regions in Europe, including Vasterbotten.

Place, publisher, year, edition, pages
Institute of Physics (IOP), 2023
Series
IOP Conference Series: Earth and Environmental Science, ISSN 1755-1307, E-ISSN 1755-1315 ; 1196
National Category
Energy Engineering
Identifiers
urn:nbn:se:umu:diva-212813 (URN)10.1088/1755-1315/1196/1/012005 (DOI)2-s2.0-85166560520 (Scopus ID)
Conference
2023 Sustainable Built Environments: Paving the Way for Achieving the Targets of 2030 and Beyond, SBE23-Thessaloniki, Online, March 22-24, 2023
Funder
EU, Horizon 2020, 101016854Swedish Research Council Formas, 2020-02085
Available from: 2023-08-16 Created: 2023-08-16 Last updated: 2024-07-02Bibliographically approved
Lu, C., Li, S., Gu, J., Lu, W., Olofsson, T. & Ma, J. (2023). A hybrid ensemble learning framework for zero-energy potential prediction of photovoltaic direct-driven air conditioners. Journal of Building Engineering, 64, Article ID 105602.
Open this publication in new window or tab >>A hybrid ensemble learning framework for zero-energy potential prediction of photovoltaic direct-driven air conditioners
Show others...
2023 (English)In: Journal of Building Engineering, E-ISSN 2352-7102, Vol. 64, article id 105602Article in journal (Refereed) Published
Abstract [en]

Integrating renewable energy is a promising solution for buildings to achieve the net-zero-energy goal. Expanding real-time matching between renewable energy generation and building energy demand can help realize more enormous zero-energy potential in practice. However, there are few studies to investigate the real-time energy matching in renewable energy building design. Therefore, in this study, a hybrid ensemble learning framework is proposed for analyzing and predicting zero-energy potential in the real-time matching of photovoltaic direct-driven air conditioner (PVAC) systems. First, the datasets of zero-energy probability (ZEP) are generated under the three main climate regions in China, which are with consideration of the load flexibility of air conditioners and based on six important design variables. Second, a novel ensemble learning method named Extreme Gradient Boosting (XGBoost) is selected to predict ZEP and the Bayesian Optimization (BO) is adopted to identify the optimal hyperparameters and further improve the prediction performance. The statistical analysis shows that ZEP distributions are very different from one region to another one and the PVAC systems in Beijing are the easiest to achieve the zero-energy goal. Among all the variables, PV capacity is the most significant and positively related to ZEP. The prediction results show BO-XGBoost achieves more than 99% accuracy and outperforms other benchmark models in the ZEP prediction of three cities. In a word, this paper reveals BO-XGBoost is the most effective model for ZEP prediction and provides the framework for designers to utilize zero-energy potential analysis and prediction for the first time.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Bayesian optimization, Machine learning, Photovoltaic direct-driven air conditioners, Thermal comfort, Zero energy potential
National Category
Energy Systems
Identifiers
urn:nbn:se:umu:diva-201454 (URN)10.1016/j.jobe.2022.105602 (DOI)000997281000001 ()2-s2.0-85142748107 (Scopus ID)
Available from: 2022-12-06 Created: 2022-12-06 Last updated: 2023-09-05Bibliographically approved
Liu, B., Vu-Bac, N., Zhuang, X., Lu, W., Fu, X. & Rabczuk, T. (2023). Al-DeMat: A web-based expert system platform for computationally expensive models in materials design. Advances in Engineering Software, 176, Article ID 103398.
Open this publication in new window or tab >>Al-DeMat: A web-based expert system platform for computationally expensive models in materials design
Show others...
2023 (English)In: Advances in Engineering Software, ISSN 0965-9978, E-ISSN 1873-5339, Vol. 176, article id 103398Article in journal (Refereed) Published
Abstract [en]

We present a web-based framework based on the R shiny package with functional back-end server in machine learning methods. A 4-tiers architecture is programmed to achieve users’ interactive design and visualization via a web browser. Many data-driven methods are integrated into this framework, namely Random Forest, Gradient Boosting Machine, Artificial and Deep neural networks. Moreover, a robust gradient-free optimization technique, the Particle Swarm Optimization, is used to search optimal values in hyper-parameters tuning. K-fold Cross Validation is applied to avoid over-fitting. R2 and RMSE are considered as two key factors to evaluate the trained models. The contributions to the expert system in materials design are: (1) A systematic framework that can be applied in materials prediction with machine learning approaches, (2) A user-friendly web-based platform that is easy and flexible to use and (3) integrated optimization and visualization into the framework with pre set algorithms. This computational framework is designed for researchers and materials engineers who would like to do the preliminary designs before experimental studies. Finally, we demonstrate the performance of the web-based framework through 2 case studies.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Machine learning, Data-driven modeling, Decision support systems (DSS), R shiny, Web-based platform
National Category
Computer Sciences Other Engineering and Technologies
Research subject
Computer Science; Materials Science; Solid Mechanics; data science
Identifiers
urn:nbn:se:umu:diva-202287 (URN)10.1016/j.advengsoft.2022.103398 (DOI)000920616600001 ()2-s2.0-85145780170 (Scopus ID)
Available from: 2023-01-05 Created: 2023-01-05 Last updated: 2024-07-02Bibliographically approved
Lu, C., Gu, J. & Lu, W. (2023). An improved attention-based deep learning approach for robust cooling load prediction: public building cases under diverse occupancy schedules. Sustainable cities and society, 96, Article ID 104679.
Open this publication in new window or tab >>An improved attention-based deep learning approach for robust cooling load prediction: public building cases under diverse occupancy schedules
2023 (English)In: Sustainable cities and society, ISSN 2210-6707, Vol. 96, article id 104679Article in journal (Refereed) Published
Abstract [en]

Space cooling in buildings is responsible for massive energy consumption and carbon emissions. Accurate cooling load prediction can facilitate the implementation of energy-efficiency cooling control strategies in practice. In this paper, an improved attention-based deep learning approach is proposed for robust ultra-short-term cooling load prediction. First, a novel time representation learning is introduced to extract the periodicity and non-periodicity of cooling loads efficiently. Then, long short-term memory with an attention mechanism extracts properly the time steps by identifying the relevant hidden states and learns high-level temporal dependency. The approach additionally incorporates extreme gradient boosting through the error reciprocal method, enhancing the elimination of prediction errors and improving robustness. The study takes Guangzhou as an example and generates cooling loads using diverse occupancy schedules of five building types based on the Chinese National Standard and Typical Meteorological Year data. The approach is evaluated on datasets comprising the cooling loads, meteorological data, and contextual information. Through results analysis, the approach outperforms other models in terms of prediction accuracy and robustness across all building types. Additionally, model interpretation is provided regarding feature importance and attention matrixes, which enhances the understanding and transparency of the final prediction from the proposed approach.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Cooling load prediction, Deep learning, Model interpretation, Occupancy schedule, Public buildings
National Category
Computer Systems
Identifiers
urn:nbn:se:umu:diva-209543 (URN)10.1016/j.scs.2023.104679 (DOI)001015812200001 ()2-s2.0-85160652153 (Scopus ID)
Funder
J. Gust. Richert stiftelse
Available from: 2023-06-13 Created: 2023-06-13 Last updated: 2023-09-05Bibliographically approved
Yu, H., Feng, K., Penaka, S. R., Man, Q., Lu, W. & Olofsson, T. (2023). Data-driven modelling of building retrofitting with incomplete physics: a generative design and machine learning approach. Paper presented at NSB 2023, 13th Nordic Symposium on building physics, Aalborg, Denmark, June 12-14, 2023. Journal of Physics, Conference Series, 2654, Article ID 012053.
Open this publication in new window or tab >>Data-driven modelling of building retrofitting with incomplete physics: a generative design and machine learning approach
Show others...
2023 (English)In: Journal of Physics, Conference Series, ISSN 1742-6588, E-ISSN 1742-6596, Vol. 2654, article id 012053Article in journal (Refereed) Published
Abstract [en]

Building performance simulation (BPS) based on physical models is a popular method for estimating the expected energy savings from energy-efficient building retrofitting. However, for many buildings, especially older buildings, built several decades ago, an operator do not have full access to the complete information for the BPS method. Incomplete information comes from the lack of detailed building physics, such as the thermal transmittance of some building components due to the deterioration of components over time. To address this challenge, this paper proposed a data-driven approach to support the decision-making of building retrofitting selections under incomplete information conditions. The data-driven approach integrates the backpropagation neural networks (BRBNN), fuzzy C-means clustering (FCM), and generative design (GD). It generates the required big database of building performance through generative design, which can overcome the problem of incomplete information during building performance simulation and energy-efficient retrofitting. The case study is based on old residential buildings in severe cold regions of China, using the proposed approach to predict energy-efficient retrofitting performance. The results indicated that the proposed approach can model the performance of residential buildings with more than 90% confidence, and show the variation of results. The core contribution of the proposed approach is to provide a way of performance prediction of individual buildings resulting from different retrofitting measures under the incomplete physics condition.

Place, publisher, year, edition, pages
Institute of Physics (IOP), 2023
National Category
Building Technologies
Identifiers
urn:nbn:se:umu:diva-220010 (URN)10.1088/1742-6596/2654/1/012053 (DOI)2-s2.0-85181172898 (Scopus ID)
Conference
NSB 2023, 13th Nordic Symposium on building physics, Aalborg, Denmark, June 12-14, 2023
Funder
Swedish Research Council Formas, 2020-02085EU, Horizon 2020, AURORAL
Available from: 2024-02-02 Created: 2024-02-02 Last updated: 2024-07-02Bibliographically approved
Liu, B., Penaka, S. R., Lu, W., Feng, K., Rebbling, A. & Olofsson, T. (2023). Data-driven quantitative analysis of an integrated open digital ecosystems platform for user-centric energy retrofits: A case study in northern Sweden. Technology in society, 75, Article ID 102347.
Open this publication in new window or tab >>Data-driven quantitative analysis of an integrated open digital ecosystems platform for user-centric energy retrofits: A case study in northern Sweden
Show others...
2023 (English)In: Technology in society, ISSN 0160-791X, E-ISSN 1879-3274, Vol. 75, article id 102347Article in journal (Refereed) Published
Abstract [en]

This paper presents an open digital ecosystem based on a web-framework with a functional back-end server for user-centric energy retrofits. This data-driven web framework is proposed for building energy renovation benchmarking as part of an energy advisory service development for the Västerbotten region, Sweden. A 4-tier architecture is developed and programmed to achieve users’ interactive design and visualization via a web browser. Six data-driven methods are integrated into this framework as backend server functions. Based on these functions, users can be supported by this decision-making system when they want to know if a renovation is needed or not. Meanwhile, influential factors (input values) from the database that affect energy usage in buildings are to be analyzed via quantitative analysis, i.e., sensitivity analysis. The contributions to this open ecosystem platform in energy renovation are: 1) A systematic framework that can be applied to energy efficiency with data-driven approaches, 2) A user-friendly web-based platform that is easy and flexible to use, and 3) integrated quantitative analysis into the framework to obtain the importance among all the relevant factors. This computational framework is designed for stakeholders who would like to get preliminary information in energy advisory. The improved energy advisor service enabled by the developed platform can significantly reduce the cost of decision-making, enabling decision-makers to participate in such professional knowledge-required decisions in a deliberate and efficient manner. This work is funded by the AURORAL project, which integrates an open and interoperable digital platform, demonstrated through regional large-scale pilots in different countries of Europe by interdisciplinary applications.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Energy retrofits, Data-driven modeling, Decision support systems (DSS), Quantitative analysis, Open ecosystem platform
National Category
Electrical Engineering, Electronic Engineering, Information Engineering Energy Engineering
Identifiers
urn:nbn:se:umu:diva-214835 (URN)10.1016/j.techsoc.2023.102347 (DOI)2-s2.0-85172316454 (Scopus ID)
Funder
The Kempe Foundations, JCK-2136EU, Horizon 2020, 101016854J. Gust. Richert stiftelse, 2023-00884Swedish Research Council, 2018-05973Swedish Research Council, 2022-06725
Available from: 2023-10-02 Created: 2023-10-02 Last updated: 2024-07-02Bibliographically approved
Organisations

Search in DiVA

Show all publications