Abstract The development and integration of technologies such as the Internet of Things (IoT) or edge computing devices is contributing to the formation of an increasingly digital, intelligent and connected world. As a result, there is a massive flow of data in different sectors of human activity. One example is intelligent buildings, where thousands of components, devices, systems and suppliers interact. In this context, failures in control and monitoring systems are frequent. To analyze this situation, this paper presents as a case study the problem of fault-tolerant robust adaptive monitoring control with state prediction performance for a class of IoT temperature systems subject to uncertainties of precision states and external disturbances. The authors propose a new control strategy based on consensus game theory and prediction of future precision states to reduce tracking error and improve algorithm efficiency. The authors present the development of a new algorithm that improves the functioning of monitoring and control of parcel networks. This has the purpose of increasing the energy efficiency of the same and ensure the effectiveness of our adaptive temperature control algorithm, compared to existing results. With the simulation presented in this research, it is possible to conclude that a new fault tolerant error tracking algorithm ensures robust monitoring of the reference model. It was shown that the predicted temperature signal is limited by a small range close to the collected temperature data. A case study result is provided to demonstrate the effectiveness of the proposed fault-tolerant adaptive monitoring control algorithm.

中文翻译：

---

智能建筑的边缘计算和自适应容错跟踪控制算法：案例研究

摘要 物联网 (IoT) 或边缘计算设备等技术的发展和集成正在推动形成一个日益数字化、智能化和互联的世界。因此，在人类活动的不同领域存在大量数据流。一个例子是智能建筑，其中数以千计的组件、设备、系统和供应商进行交互。在这种情况下，控制和监测系统经常出现故障。为了分析这种情况，本文以实例研究了一类具有状态预测性能的物联网温度系统的容错鲁棒自适应监控控制问题，该系统受精度状态和外部干扰的不确定性影响。作者提出了一种基于共识博弈论和未来精度状态预测的新控制策略，以减少跟踪误差并提高算法效率。作者介绍了一种新算法的开发，该算法改进了包裹网络监控和控制的功能。与现有结果相比，这样做的目的是提高能源效率并确保我们的自适应温度控制算法的有效性。通过本研究中提供的仿真，可以得出结论，新的容错错误跟踪算法可确保对参考模型的稳健监控。结果表明，预测的温度信号受到接近收集到的温度数据的小范围的限制。