Towards a Minergie Standard for tropical climates

The Swiss Minergie®-standard is, by the number of labelled buildings (> 20'000) one of the most successful building energy labels in the world. It is obviously a strong incentive for designing comfortable, low energy buildings. This standard is now valid for temperate - cold climates only. There is therefore a need for a similar standard for buildings dominated by cooling loads, as it is common in the tropical and sub-tropical climates of the world. Since the new EPFL campus planned in Ras al Kaimah (United Arab Emirates) should be exemplary, a project was launched by the Dean of EPFL Middle East, together with Minergie®-Association and the Solar Energy and Building Physics Laboratory of EPFL, aiming to set-up such a standard. In order to initiate this project, two buildings (a single family dwelling and an office building) were chosen. The single-family dwelling was simulated at an hourly time step using a detailed dynamic thermal model based on the computer simulation programme Energy plus issued from LBNL. The monthly energy consumption of the dwelling shows a good correlation with the monitored data. In addition to that, both energy consumptions, calculated with the dynamic and the simplified models are close to each other, giving confidence to the predictions of the latter. Therefore, both buildings were assessed using a simplified monthly energy balance method. Starting from the current buildings configurations, several variants implementing various improvements towards energy efficiency were considered. These simulations show that considerable energy saving (up to a factor 5) can be achieved by implementing together several improvements to these buildings. In addition, the building reaches a higher level of users comfort.

Assessing the saving potential of blind controller via multi-objective optimization

David Daum, Nicolas Morel

This paper presents the results of computational experiments where multi-objective algorithms were used to tune a controller for blind movements in a residential building and a room of the LESO (Solar Energy and Building Physics Laboratory) experimental building. The blind controller, which is based on fuzzy logic, was optimized not only in terms of energy consumption but also in terms of thermal comfort. The goal is to show saving potential for intelligent blind controller in a real world example rather than in tailored idealized test rooms. Therefore, a state of the art simulation program with a multi-objective evolutionary algorithm was combined. It was found that with elementary control systems, like schedules for the lighting in a building, almost 40% of the energy could be saved. With the help of more advanced controllers this can be further increased. Also discussed in this paper are the results and the feasibility of implementing such a controller.

Tsinghua Press, Springer2009

Building envelope and solar energy optimization: a new “wizard” for architects

Marja Edelman, Maria Cristina Munari Probst, Christian Roecker

When designing a project, architects are facing more and more constraints on the building’s energy efficiency. Tougher values on insulation and energy consumption are now often combined with compulsory implementation of active solar systems - photovoltaics or solar thermal. With natural lighting, passive and active solar all competing for envelope areas, comparing results of architectural variants becomes more important and at the same time more complex. To help overcome this situation, a renowned “energy balance calculation/certification” software tool has been improved and adapted, proposing a wizard developed to meet a growing demand: obtain a quick feedback on building envelope, energy efficiency and solar strategies, especially in the early design stage, when strategies are defined. The wizard helps fulfilling various norms of different European countries, allowing architects to compare variants during this crucial phase. By simplifying data entry using smart default values derived from appropriate general choices, and by presenting a clear and intuitive user’s interface, this new tool offers practicing architects an easy access to building envelope and solar energy use optimization.

Université Catholique de Louvain-la-Neuve2011

Fusing TensorFlow with building energy simulation for intelligent energy management in smart cities

Jérôme Henri Kämpf

Buildings account for 35% of the global final energy demand. Efficiency improvements and advanced control strategies have a significant impact in the reduction of energy costs and CO2 emissions. Building energy simulation is widely used to help planners, contractors, and building owners analyse diverse options regarding the planning and management of energy consumption in buildings. Furthermore, recent advances in data processing and computing have led to the development of sophisticated machine learning algorithms that can learn from large datasets, e.g., sensor data from buildings, and use them to develop building-specific adaptive and automatic energy controllers. Control algorithms, such as deep reinforcement learning can tune themselves, are model-free, and economical to implement. In this paper, we introduce an integrated simulation environment that combines CitySim, a fast building energy simulator, and TensorFlow, a platform for efficient implementation of advanced machine learning algorithms. The integration is achieved via Keras—an API for TensorFlow—and a set of text and csv files for data transfer between the applications. This new environment will allow researchers to investigate novel learning control algorithms, and demonstrate their robustness and potential for diverse applications in the built environment. We present two case studies for energy savings and demand response, respectively.

2019