Smart buildings are increasingly using Internet of Things (IoT)-based
wireless sensing systems to reduce their energy consumption and environmental
impact. As a result of their compact size and ability to sense, measure, and
compute all electrical properties, Internet of Things devices have become
increasingly important in our society. A major contribution of this study is
the development of a comprehensive IoT-based framework for smart city energy
management, incorporating multiple components of IoT architecture and
framework. An IoT framework for intelligent energy management applications that
employ intelligent analysis is an essential system component that collects and
stores information. Additionally, it serves as a platform for the development
of applications by other companies. Furthermore, we have studied intelligent
energy management solutions based on intelligent mechanisms. The depletion of
energy resources and the increase in energy demand have led to an increase in
energy consumption and building maintenance. The data collected is used to
monitor, control, and enhance the efficiency of the system.

本研究提出了一种基于物联网的综合智能能源管理框架，并研究了基于智能机制的能源管理解决方案，使用所收集的数据来监控、控制和提高系统的效率。

智能分析与物联网框架在智慧城市中的能源管理：机器学习方法在复杂网络和系统中的应用

Intelligent Energy Management with IoT Framework in Smart Cities Using  Intelligent Analysis: An Application of Machine Learning Methods for Complex  Networks and Systems

Smart buildings aim to optimize energy consumption by applying artificial
intelligent algorithms. When a smart building is commissioned there is no
historical data that could be used to train these algorithms. On-line
Reinforcement Learning (RL) algorithms have shown significant promise, but
their deployment carries a significant risk, because as the RL agent initially
explores its action space it could cause significant discomfort to the building
residents. In this paper we present ReLBOT, a new technique that uses transfer
learning in conjunction with deep RL to transfer knowledge from an existing,
optimized smart building, to the newly commissioning building, to reduce the
adverse impact of the reinforcement learning agent's warm-up period. We
demonstrate improvements of up to 6.2 times in the duration, and up to 132
times in prediction variance for the reinforcement learning agent's warm-up
period.

本文提出了一种名为 ReLBOT 的新技术，使用深度强化学习中的转移学习，从现有的优化智能建筑中转移知识以降低新委托的建筑中强化学习代理的热身期的不良影响，最大程度地优化了能源消耗效果。

ReLBOT：一种在智能建筑中最小化强化学习风险的迁移学习方法

ReLBOT: A Transfer Learning Approach to Minimize Reinforcement Learning  Risks in Smart Buildings

The pervasive application of artificial intelligence and machine learning
algorithms is transforming many industries and aspects of the human experience.
One very important industry trend is the move to convert existing human
dwellings to smart buildings, and to create new smart buildings. Smart
buildings aim to mitigate climate change by reducing energy consumption and
associated carbon emissions. To accomplish this, they leverage artificial
intelligence, big data, and machine learning algorithms to learn and optimize
system performance. These fields of research are currently very rapidly
evolving and advancing, but there has been very little guidance to help
engineers and architects working on smart buildings apply artificial
intelligence algorithms and technologies in a systematic and effective manner.
In this paper we present B-SMART: the first reference architecture for
autonomic smart buildings. B-SMART facilitates the application of artificial
intelligence techniques and technologies to smart buildings by decoupling
conceptually distinct layers of functionality and organizing them into an
autonomic control loop. We also present a case study illustrating how B-SMART
can be applied to accelerate the introduction of artificial intelligence into
an existing smart building.

本文提出了 B-SMART：用于建筑自主控制的第一种参考架构，以帮助工程师和建筑师系统且有效地应用人工智能算法和技术于智能建筑，以减缓气候变化并减少能源消耗及相关碳排放量，并通过案例研究证明了 B-SMART 如何加速将人工智能引入到现有的智能建筑中。