Building performance software is evolving to help facility owners and managers analyse data in order to optimise building processes to maximise efficiency. Machine learning and artificial intelligence (AI) is evolving to optimise building processes to maximise efficiency all on its own. These two elements of the smart buildings movement are developing side by side towards the same goal, but how will they support and/or cancel each other out?
In our recent report we estimate that the market for Building Performance Software in Smart Buildings generated $12.72Bn in 2015, and we expect this value to rise to $18.78Bn by 2020, representing a CAGR of 8.1% per annum. Over the course of the last 5 years we have tracked a total of 167 funding announcements relating to 106 building performance software providers, creating investments totalling $2,385 million.
Machine Learning meanwhile grew into a major research topic in the mid 2000s, computer scientists and tech corporations began applying these ideas to a wide array of problems. Machine Learning became an integral part of robotics, recognition software and was soon one of the most desired and versatile computing skills in the business.
Now, alongside the developments of the Internet of Things (IoT) and Big Data, machine learning has moved into the era of “deep learning” or AI. This evolution has been enabled, in large part, by access to faster computing and vast amounts of data, which is necessary for system training. Deep learning, or AI, has successfully addressed many problems that machine learning struggled with, such as image classification, voice recognition and language translation.
“Whereas in the rule-based system world (pattern recognition and machine learning) the system engineer needed exhaustive information about the domain in order to build a good system, in the Deep Learning world this is no longer necessary”, explained Jonathan Laserson, PointGrab Machine Learning Expert, in a recent white paper.
“In this era of the IoT where new kinds of data are becoming available at a rapid clip, Deep Learning allows us to faster iterate on new data sources and use them to our best advantage without requiring intimate knowledge of them”.
As is often the case, the building automation industry lags behind larger industries in terms of cutting-edge technology. Sectors like military and defence, consumer electronics and telecommunications tend to lead the pack. However, to be fair to building automation, systems like lighting, fire, electrical distribution and access control are not the best candidates for AI. That’s because their behaviour is fairly well defined.
In contrast, consider HVAC systems. They are significantly more complex than other building systems. HVAC systems are often non-linear, poorly behaved, noisy and very unpredictable under real-world circumstances. What’s misleading about HVAC systems is that many engineers think of them as being very well defined. However, well defined behaviour is only true within a single piece of equipment from a single manufacturer given ideal parameters.
Developing this type of machine learning for buildings has been unexpectedly challenging, according to Dr. Sophie Loire, research and technology fellow at Ecorithm. Buildings are subject to a number of variables like weather, occupancy, as well as other external factors on a range of time scales. Over time engineers generally develop an instinctive understanding of their buildings, giving them the ability to identify issues quickly.
Humans have the capacity to recognise patterns, then categorise and catalogue experiences. In any new situation we can refer back to similar experiences in order to determine the appropriate response. We naturally draw in all our relevant information, be that from the current data or from previous experiences and education, and we do it without a great deal of effort, suggested Loire in an article for Automated Buildings.
From the previous example, the well-defined behaviour of HVAC equipment becomes less true when equipment is installed outside of design criteria, or as it starts to age. In such cases, it becomes more difficult for technicians to know the best way to control such equipment. This is all too often the case in real-world environments. In these less-than-ideal circumstances, machine learning can supplement classically scripted programming to learn about the “unpredictable” behaviour of equipment.
“Companies are focusing on optimising building performance via real-time data analytics, predictive analysis, automated fault detection, machine learning and even rudimentary artificial intelligence”, explains our recent report The Market for Building Performance Software 2016 to 2020.
In this early stage of AI development it is essential to produce data through building performance software to be analysed by human experts. However, this data, and the consequent reactions from human experts, are also being fed into AI systems to improve their capacity to automate building systems.
It has long been clear that AI technology represents the future in building automation and beyond, but in the present, building performance software is helping humans improve automation while also nurturing its eventual successor – AI.
[contact-form-7 id="3204" title="memoori-newsletter"]