Part2: Building Management linking Energy Demand, Distributed Conversion and Storage using Dynamic Modelling and a Pervasive Sensor Infrastructure

无论是在英国还是在全球，商业和住宅建筑都是二氧化碳排放的主要来源。2000年，英国40%的非运输能源用于空间供暖，空间供暖和热水占家庭能源使用的82%，占商业能源使用的64%。因此，减少商业建筑的能源需求可以大大有助于实现英国更广泛的能源消耗目标。与直接为商业办公空间用户提出行为改变干预措施的建议相反，该项目提出解决我们对商业环境中能源消耗的数量和性质的理解中的关键缺陷，以期开发新的整体解决方案，包括优化共享资源使用和能源存储设施。拟议的研究计划通过设计和开发一种传感基础设施来解决这一挑战，该基础设施由网络化的物理传感器（例如存在传感器，功耗传感器）和虚拟传感器（例如日历和房间预订传感器，应用程序使用传感器）组成，这些传感器将提供有关使用了多少能源，用于什么目的以及由谁使用的细粒度信息。通过应用知识工程、活动识别和机器学习（例如贝叶斯分类器）的技术，我们的方法的第一阶段将获得更高层次的信息（例如在特定房间举行的会议），并将使用模式（例如功耗峰值）与现实世界的活动和工作流（例如为会议打印一系列报告）联系起来。在第二阶段，这些信息将用于参数化建筑管理中使用的建筑模型，以更准确地预测能源使用情况，并优化（分散的）能源消耗、发电和储存。基于这些模型，我们将开发一个决策支持工具，将收集到的数据以及节能策略（如组织变革和政策或重新安排活动）的预期影响可视化。这将使决策者能够确定能源浪费的地方（例如，尽管只安排了几次会议，但几个会议室正在加热），并制定和评估减少能源消耗的战略。收集的数据也有利于其他建筑系统使用新的和新兴的ISO标准，通过互联网协议实现建筑物中设备和系统的互操作性。此外，这些数据将使人们更好地了解建筑物的使用方式和热量浪费情况。通过物理和虚拟传感器的结合，可以更准确地测量建筑物居住者的热舒适度，从而有助于解决与建筑物中居住者舒适度的不同需求相关的投诉和潜在冲突，这些需求也会导致不必要的过热。

Commercial and residential buildings are responsible for a large proportion of carbon dioxide emissions both in the UK and globally. In 2000, 40% of the UK's total non-transport energy use was for space heating, and space heating and hot water accounted for 82% of domestic and 64% of commercial use of energy. Energy demand reduction by commercial buildings can therefore significantly contribute towards achieving the UK's broader energy consumption goals. In contrast to proposals that directly propose behaviour change interventions for the users of commercial office space, this project proposes to address a key deficit in our understanding of the quantity and nature of energy consumption in commercial settings with a view to developing novel holistic solutions including the optimisation of shared resource usage and energy storage facilities. The proposed research plans to tackle this challenge by designing and developing a sensing infrastructure that consists of networked physical (e.g. presence sensors, power consumption sensors) and virtual sensors (e.g. calendar and room booking sensors, application usage sensors) that will provide fine-grained information about how much energy is being used, for what purpose and by whom. By applying techniques from knowledge engineering, activity recognition and machine learning (e.g. Bayesian classifiers) the first stage of our approach will derive higher-level information (e.g. a meeting taking place in a particular room) and will link usage patterns (such as spikes in power consumption) to real-world activities and workflows (e.g. printing off a series of reports for a meeting). In the second stage, this information will be used to parameterise building models used in building management to more accurately predict energy usage and to optimise (decentralised) energy consumption, generation and storage. Based on these models, we will develop a decision support tool that visualises the collected data as well as the expected impact of energy saving strategies such as organisational changes and policies or the rescheduling of activities. This will enable decision makers to identify where energy is being wasted (e.g. several meeting rooms being heated despite only a few meetings being scheduled) and to formulate and evaluate strategies to reduce energy consumption. The data collected also benefits other building systems using new and emerging ISO standards for inter-operability of appliances and systems in buildings using Internet Protocols. In addition, the data will enable a better understanding of the way the building is used and how heat wasted. Through a combination of physical and virtual sensors a more accurate measurement of thermal comfort of the building's occupants will be established and thus assist in resolving ever occurring complaints and potential conflicts associated with the diverse needs for occupant comfort in buildings which also results in unnecessary overheating.