Home  >  Article  >  Technology peripherals  >  How to properly use artificial intelligence in building management?

How to properly use artificial intelligence in building management?

WBOY
WBOYforward
2023-05-02 09:07:061460browse

How to properly use artificial intelligence in building management?

Building managers don’t always feel comfortable introducing advanced automation systems into the facilities for which they are responsible. But advances in computer technology, pandemic-driven tasks and changing user expectations, particularly around public health and workplace experiences, are driving the industry to embrace new technologies at an unprecedented rate.

While building managers recognize the opportunity to achieve unprecedented efficiencies, the technology decisions involved are far beyond their capabilities. Their expertise is usually in HVAC, lighting controls and refrigeration, not IoT, networking...artificial intelligence.

Artificial intelligence is an especially game-changing technology, but it can also be particularly intimidating due to its complexity and lack of visibility into how it makes decisions. The first challenge in adopting artificial intelligence for building automation is often answering a basic question: Where will it go? Today, artificial intelligence is used to make buildings more energy efficient, healthier, more autonomous, and safer. and respond to the needs of its occupants, a technology that began life as cloud computing. The machine learning algorithms behind these systems require significant computing power, both to train the algorithms and to invoke them to provide insights—a process called inference. Until recently, indoor infrastructure rarely had the resources to do these things efficiently.

However, running smart building applications outside of remote data centers has its own limitations. Connectivity, bandwidth costs, security and latency (the time it takes to send data to the cloud and back) can all impact the efficiency of the system. If a machine, or the entire building automation system, is about to fail, alarms and automated responses need to be as timely as possible.

A new generation of edge computing technology alleviates this problem to a large extent: the infrastructure is installed in facilities with the processing power required for compute-intensive workloads.

Companies like FogHorn, founded seven years ago, have developed an Edge AI technology that creates new possibilities for the digital transformation of construction operations. Johnson Controls acquired FogHorn in early 2022 and has now integrated edge technology into its OpenBlue building automation platform.

By bridging local capability gaps, these edge devices provide an architectural component important to the goal of running a building as efficiently as possible. With their availability, building managers considering implementing smart automation technologies are now almost inevitably faced with the question: whether to deploy AI on-premises or in the cloud. For those facing this problem, there are some simple rules of thumb to consider.

As we've already mentioned, operations that need to be performed in real time or near real time are common edge use cases. Intelligent automation systems that can detect operational issues and automatically alert or respond tend to work best when delays are as small as possible.

Any time you want local control of a system, it's best to do it at the edge; shutting down machines or adjusting control systems from the cloud often comes with security and latency challenges.

Then there are also data transmission and storage costs to consider. Take, for example, a video surveillance system that uses computer vision AI models to analyze high-fidelity images from multiple cameras, a popular AI application. Sending all your data to and storing it in the cloud can quickly become expensive.

Other use cases are not so clear cut. Often, construction managers want to gain a deeper understanding of how they operate based on AI analytics, or run simulation exercises on “digital twin” versions of their facilities. This kind of rigorous data analysis typically doesn't need to be done in real time, so it's best performed in the cloud, where customers can leverage the most powerful hardware and software tools to do the job at any scale.

Running AI at the edge may also not be the best option if you are responsible for running multiple buildings and need to correlate information between them. In this case, the cloud allows for a centralized data clearinghouse and command center. In practice, a hybrid approach is often adopted, where some initial processing is done in a single building via Edge AI, and then cloud AI is run on aggregated data from multiple buildings, possibly combined with other data sources.

It’s important to remember that these are decisions that construction managers don’t need to make alone—your technology provider should work with you to ensure AI is deployed where it best meets your unique needs. And construction managers certainly don’t need to be exposed to the intricacies of AI and its underlying machine learning algorithms, but rather let it do its thing behind the scenes.

Like many organizations that are launching "back to work" policies at scale, Oracle sees the aftermath of the pandemic as a unique moment to introduce smart building systems. After several years of pandemic-induced closures, employees are insisting on working in a physical workplace within reach, where amenities are readily available, collaboration tools are ubiquitous, air quality is monitored, crowding is limited, and their The company is meeting sustainability goals in terms of energy and water use and waste reduction. With building occupancy still at an all-time low, shutting down systems that don’t need to be running can help significantly improve efficiency.

These changing workplace dynamics and expectations may be an opportunity to evaluate new investments in Internet of Things (IoT) technologies, the advanced networks that connect them, and the artificial intelligence systems that control them - based on occupancy rates, employee Make decisions based on experience needs, location of ownership, and its importance (e.g., research lab vs. office space).

Unlike in the past, building managers are prioritizing utilization metrics over schedules as a key consideration in their investments in automated control systems. They can't take it for granted that everyone will come back: many companies are adopting hybrid working policies, and for the first time the office needs to compete with home as an attractive and productive work environment.

Experienced construction managers are scrambling to learn the new skills required for these modern operations. They know that with the support of artificial intelligence, whether running at the edge or in the cloud, they may have an advantage in encouraging employees to return to the office, providing them with a safe and sustainable environment to meet colleagues and customers face-to-face Communicate, gather around the actual water cooler, and have fewer cats and kids making cameo appearances at meetings.

The above is the detailed content of How to properly use artificial intelligence in building management?. For more information, please follow other related articles on the PHP Chinese website!

Statement:
This article is reproduced at:51cto.com. If there is any infringement, please contact admin@php.cn delete