Buildings and Cities: Difference between revisions
high level text optimizing buildings subsections
(Added two-sentence summary for pattern analysis.) |
Jan.drgona (talk | contribs) (high level text optimizing buildings subsections) |
||
Line 12:
*'''[[Energy Demand Forecasting|Forecasting energy loads]]:''' The supply and demand of electric and thermal loads must be forecast ahead of time to inform electricity planning and scheduling. ML can help make these forecasts more accurate, improve temporal resolution, and quantify uncertainty.
*'''[[Device usage patterns analysis]]:''' A better understanding of the own energy consumption can lead to better energy efficiency by changing one's behavior or exchanging inefficient devices. ML can help to disaggregate a household's smart meter data and attribute energy consumption to individual devices for increased transparency.
*'''[[Controlling HVAC and lighting systems]]:''' Current building energy management systems are manually designed by human operators, which leads to energy inefficient operations. ML can help develop predictive models of building energy systems, leading to efficient building operation via advanced model-based optimal control methods.
*'''Fault detection and [[Predictive Maintenance|predictive maintenance]] in building systems:''' Buildings are embedded with complex engineering systems in dynamic interplay. Component's malfunctions are a constant threat to the building operations economics and comfort and safety of human occupants. ML can help to transfer from reactive maintenance to predictive maintenance and cut the maintenance cost by prolonging the remaining useful life of building engineering systems.
*'''[[Demand response]] and [[energy social games]]:'''
*'''[[AI-guided building design and planning]]:''' Current building designs are drawn by the joined hands of the architect, mechanical, electrical, and control engineers using various computer-aided design tools. ML can help to navigate and optimize complex design landscapes, often balancing conflicting requirements such as energy efficiency, comfort, and cost.
*'''[[Sector-coupled districts and district heating systems]]''': To achieve decarbonization across the heating, electricity, and mobility sectors, they are increasingly coupled within districts in a joint spatial and organizational context. ML can help by providing surrogate models of thermal processes and quantify uncertainties of loads, supply, and mobility behavior.
*'''[[Surrogate modelling]]''': Building energy simulation (BES) programs are software tools that simulate the complex physics of buildings and are key enabling tools for R&D in the building's domain. However, detailed BES models are notoriously difficult to design, tune and typically have high computational demands. ML, in conjunction with physics, can help to build accurate yet computationally efficient surrogate models for faster simulations.
=== Urban planning ===
| |||