Clement Lork

Life Cycle Assessment (LCA) has been widely adopted to identify the Global Warming Potential (GWP) in the construction industry and determine its high environmental impact through Greenhouse Gas (GHG) emissions, energy and resource consumptions. The consideration of LCA in the early stages of design is becoming increasingly important as a means to avoid costly changes at later stages of the project. However, typical LCA-based tools demand very detailed information about structural and material systems and thus become too laborious for designers in the conceptual stages, where such specifications are still loosely defined. In response, this paper presents a workflow for LCA-based evaluation where the selection of the construction system and material is kept open to compare the impacts of alternative design variants. We achieve this through a strict division into support and infill systems and a simplified visualization of a schematic floor layout using a shoebox approach, inspired from the energy modelling domain. The shoeboxes in our case are repeatable modules within a schematic floor plan layout, whose enclosures are defined by parametric 2D surfaces representing total ratios of permanent supports versus infill components. Thus, the assembly of modular surface enclosures simplifies the LCA evaluation process by avoiding the need to accurately specify the physical properties of each building component across the floor plan. The presented workflow facilitates the selection of alternative structural systems and materials for their comparison, and outputs the Global Warming Potential (GWP) in the form of an intuitive visualization output. The workflow for simplified evaluation is illustrated through a case study that compares the GWP for selected combinations of material choice and construction systems.

Effective design of air-conditioner (AC) management system has the potential to reduce the cost of electricity consumption and help users to participate in demand response (DR) program as interruptible loads. However, optimizing the operation of AC is complex and, as a potential solution, computational intelligence (CI) techniques based model predictive algorithms are being explored in the literature. This article aims to provide an overview of the CI techniques that are established in addressing relevant and timely open problems of AC management for residential buildings. To do so, first, we provide a brief background on different DR mechanisms and AC management systems. Second, a review of recent advances in CI-based model prediction and optimal control techniques of AC systems for DR management is presented. The discussion reveals that the interest in CI techniques with adaptive learning algorithms is increasing due to their ability to adjust in varying conditions. Then, we provide a brief description of a testbed, which is used for testing various newly developed CI-based AC management techniques in a residential setting. Finally, key issues related to the coordination of a large number of AC systems, modeling accuracy, and computational tractability are highlighted along with their challenges and future research directions.

Optimal scheduling and robust sequence control of a central chiller system with thermal energy storage may not be a straightforward solution to reduce building cooling load demand (CLD) due to unpredictable thermal comfort requirements and the stochastic nature of occupancy dependent CLD. One potential way to address this challenge is to design and develop an energy management strategy (EMS) for a zone variable air volume unit. This paper proposes an EMS to reduce CLD by deciding the zone reference setpoint temperature based on fuzzy logic strategy (FLS) and zone thermal models. The objective is to reduce zone CLD while maintaining zone temperature and zone thermal comfort margin within the threshold limits. In this context, first, we modeled the zone thermal behavior using an artificial neural network (ANN) approach to predict zone temperature for next time slot, modeled the zone cooling energy behavior using a regression approach to predict zone CLD for the next time slot, and estimated the zone occupancy status using noise data. Second, we implemented zone thermal feedback model and comfort margin based on zone thermal conditions and predicted mean vote index, respectively. Finally, we implemented an EMS that includes both demand supply strategy and cooling load demand reduction strategy based on one time slot ahead prediction. The novelty of the proposed EMS lies within the zone CLD reduction using FLS, predicting zone thermal behaviors using an ANN and a regression approach, estimating zone occupancy using noise data, and maintaining zone thermal comfort margin within the threshold limits.

In this paper, we develop an ontology-based framework for energy management in buildings. We divide the functional architecture of a building energy management system into three interconnected modules that include building management system (BMS), benchmarking (BMK), and evaluation & control (ENC) modules. The BMS module is responsible for measuring several useful environmental parameters, as well as real-time energy consumption of the building. The BMK module provides the necessary information required to understand the context and cause of building energy efficiency or inefficiency, and also the information which can further differentiate normal and abnormal energy consumption in different scenarios. The ENC module evaluates all the information coming from BMS and BMK modules, the information is contextualized, and finally the cause of energy inefficiency/abnormality and mitigating control actions are determined. Methodology to design appropriate ontology and inference rules for various modules is also discussed. With the help of actual data obtained from three different rooms in a commercial building in Singapore, a case study is developed to demonstrate the application and advantages of the proposed framework. By mitigating the appropriate cause of abnormal inefficiency, we can achieve 5.7%, 11.8% and 8.7% energy savings in Room 1, Room 2, and Room 3 respectively, while creating minimum inconvenience for the users.

Due to unpredictable thermal comfort requirements and the stochastic nature of occupancy dependent CLD, it is a challenging task to optimally scheduling and sequence control of a chiller plant with thermal energy storage system. One potential way to address this challenge is to design and develop an energy management and control strategy (EMCS) for zone variable air volume (VAV) unit. This paper proposes an EMCS to reduce zone CLD based on zone thermal parameters. The objective is to reduce zone CLD while maintaining temperature and thermal comfort within the threshold limits. In this context, first we develop zone thermal models. Second, we develop an artificial neural network approach and regression approach to predict zone temperature and CLD by tuning the zone parameters. Third, we implement a thermal feedback model to provide the thermal comfort status based on the zone temperature. Finally, we implement control strategies such as demand supply strategy (DSS) and proposed EMCS. The DSS provides required CLD based on occupancy requirements. Then, we implement the proposed EMCS to reduce the zone CLD by controlling the VAV supply air temperature while keeping the thermal comfort margin within the selected thresholds limits. Numerical case studies are conducted based on real data from a commercial building in Singapore to demonstrate the effectiveness of the proposed scheme.

Due to the significant contribution of air-conditioning load towards total energy consumption in residential buildings, accurate modelling and forecasting of such load is key to effective demand-side energy management programmes. This paper suggests a data driven framework for 15 min-ahead AC load forecasting based on modern machine learning techniques that includes Support Vector Regression, Ensemble Trees, and Artificial Neural Network. To the end, it utilizes a correlation based feature selection method to identify information that is relevant for machine learning modelling. The effect of spatio-temporal features selection on prediction output and the effect of training data quantity on convergence characteristics were analysed and discussed. The effectiveness of the proposed approach is evaluated using a 20-household, half-year data set from an ongoing research testbed set up at the faculty housing units of Singapore University of Technology and Design. An linear combination method was proposed to combine models and the resulting model gave a mean absolute percentage error of 11.27%.