Buildings and Cities: Difference between revisions
no edit summary
Krisrs1128 (talk | contribs) No edit summary |
|||
Line 10:
=== Optimizing buildings ===
*'''Modeling building energy''': A better understanding of how energy is used within buildings can help inform efficiency-promoting interventions. For example, there are opportunities to improve energy demand forecasts, disaggregation of appliance energy consumption, and characterization of efficiency measures.
*'''Smart buildings''': Machine learning can inform optimal control for systems within buildings, allowing reductions in energy use. For example, model-predictive control can increase the efficiency of HVAC systems.
=== Urban planning ===
*'''Modeling energy use across buildings''': District-level modeling of building energy use can lead to even greater efficiency improvements, compared to modeling of individual buildings, because they can support district heating and cooling as well as target retrofit campaigns.
*'''Gathering infrastructure data''': Machine learning can support data generation of relevant infrastructure data, transforming raw street-view or satellite imagery into estimates of climate-critical metrics, like prevalence of photovoltaic adoption or change in building footprints.
=== The future of cities ===
*'''Data for smart cities''': A variety of city services are now guided by data streams coming from dedicated sensors (e.g., traffic cameras) or indirectly through sources like mobile phones. These services can help inform actions to reduce energy footprints and increase resilience.
*'''Low-emissions infrastructure''': Machine learning can strengthen the ties between the different components of urban infrastructure, like public transportation and building developments, in a way that reduces overall carbon footprints.
== Background Readings ==
|