Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Gregor P. Henze"'
Publikováno v:
Journal of Building Performance Simulation. 14:203-225
Fully defined physics-based building energy models can accurately represent building systems; however, generating models based on high-level parameters is time consuming and simulation time of comp...
Publikováno v:
IFAC-PapersOnLine. 53:524-529
Clustering is an unsupervised learning technique that is useful when working with a large volume of unlabeled data. Complex dynamical systems in real life often entail data streaming from a large number of sources. Although it is desirable to use all
Publikováno v:
Energy Conversion and Management. 196:705-716
Fifth generation district heating and cooling networks are characterized by supply temperatures in the ambient range of 15–25 °C, which not only reduces heat loss but also allows for integrating various kinds of low-temperature waste heat sources.
Publikováno v:
BuildSys@SenSys
We present the results of The CityLearn Challenge 2021. Five teams competed over six months to design the best multi-agent reinforcement learning agent for the energy management of a microgrid of nine buildings.
Publikováno v:
Scientific Data, Vol 8, Iss 1, Pp 1-14 (2021)
Scientific Data
Scientific Data
This paper describes development of a data acquisition system used to capture a range of occupancy related modalities from single-family residences, along with the dataset that was generated. The publicly available dataset includes: grayscale images
Publikováno v:
Energies, Vol 14, Iss 3513, p 3513 (2021)
Energies; Volume 14; Issue 12; Pages: 3513
Energies; Volume 14; Issue 12; Pages: 3513
Occupant behavior can significantly influence the operation and performance of buildings. Many occupant-centric key performance indicators (KPIs) rely on having accurate counts of the number of occupants in a building, which is very different to how
Autor:
John O. Nelson, Gregor P. Henze
Publikováno v:
Journal of Architectural Engineering. 27
Typical commercial construction inherently contains large surface areas of relatively thin mass located in the floor slabs. This research asks how effective this mass could be for passive ...
Autor:
Adam R. McKittrick, Gregor P. Henze
Publikováno v:
Journal of Architectural Engineering. 27
As the United States continues its progress toward sustainable construction, net zero building design is becoming an increasingly important and popular topic. Two definitions of net zero e...
Publikováno v:
BuildSys@SenSys
We demonstrate that multi-agent reinforcement learning (RL) controllers can cooperate to provide more effective load shaping in a model-free, decentralized, and scalable way with very limited sharing of anonymous information. Rapid urbanization, incr
Publikováno v:
BuildSys@SenSys
This poster shows the results of The CityLearn Challenge 2020. 4 teams competed over 6 months to design the best reinforcement learning agent for the energy management of a microgrid.