Digital Cities Roadmap. Группа авторов

Чтение книги онлайн.

      1

      The Use of Machine Learning for Sustainable and Resilient Buildings

Kuldeep Singh Kaswan ¹ * and Jagjit Singh Dhatterwal ²

¹ School of Computing Science and Engineering, Galgotias University, Greater Noida, India

² Department of Computer Science & Applications, PDM University, Bahadurgarh, India

       Abstract

      The use of Artificial Intelligence to ensure that intelligent and resilient buildings are sustainably developed. The intelligence displayed in buildings by electronic devices and software operated systems is artificial intelligence which perceives the building environment and takes actions aimed at optimizing output in a given context or constraint. A complex, sensitive infrastructure that ensures efficient, cost-effective and environmentally acceptable conditions for every occupant by constantly communicating with its four basic elements: locations (components, frameworks, facilities); processes (automation, control systems), staff (services, users) and management (maintaining, performance) and processes (controlling, systems); and they separate current technologies into two major groups, occupantcentered and energy-centered facilities. The first level approaches that use ML for occupant dimensions, including (1) occupancy and identity estimations, (2) behavior recognition and (3) choice and enforcement estimates. The approach in the second-class category used ML to approximate energy or device-related aspects. It is divided into three categories, (1) estimating the energy profiling and demand, (2) profiling and detection of faults of devices, and (3) sensor inferiority. In this chapter, we focus on guided study, unrestricted learning and improving learning. The main variants, implications of specific parameter choices are explored and we generate standard algorithms. Finally, discuss some of the challenges and opportunities in the built environment to apply machine learning.

Keywords: Machine learning, big data analytics, Internet of Things, smart building, resilient building, sustainable building

1.1 Introduction of ML Sustainable Resilient Building

      The hyperconnectivity generated by IoT will enhance the assurance of Smart Sustainable Resilient Building (SSRB) as all basic construction facilities and goods from your home electronics to your plant vessels have now been connected [1–5]. Nevertheless, this hyperconnectivity could hinder the control of SSRBs at the same time. In particular, massive quantities of streaming data are required from SSRB and its residents. The management of large data streams is becoming more and more relevant with ML, testing, compaction, learning and filtration technologies. In order to obtain a greater interpretation of human beings than their environment computers, the amount of sensory data obtained by sensors and devices needs to be processed by algorithms, converted into details and derived expertise [6–8]. This awareness can also contribute, and most significantly, innovative goods and services that change our lives drastically. For starters, smart meter readings may be used to help estimate and control power usage. To optimize this convenience, reduce expenses adapting to requirements of its residents, the SSRB requires sophisticated tools to understand, anticipate and make intelligent decisions. SSRB must also provide a variety of wearable sensor data linked to its patients and produce new remote sensors. SSRB algorithms include estimation, decision analysis, robots, smart devices, wireless sensor networks, interactive, web computing and cloud computing and include several other developments. Cognitive maintenance of offices is necessary in several SSRB programs for starters, fitness, safety, energy management, illumination, repair, the elderly and digital entertainment through these technologies.

1.2 Related Works

      While several SB-focused survey papers have been released, none focuses on the role of data analysis and ML within SBs. All the relevant survey papers are comprehensively presented in Table 1.1.

      Table 1.1 Report data of a survey.