ZigBee and LoRa are communication technologies widely used in the application of the Internet of things (IoT), especially in the field of smart building environmental monitoring. The main purpose of this study is to compare and analyze the transmission performance of ZigBee and LoRa wireless communication networks in the building. Through two indicators of packet loss rate (PLR) and round-trip time (RTT), this paper discusses in detail the transmission performance of ZigBee and LoRa technologies in whole buildings under the same working conditions. We set up three experimental scenarios of line-of-sight, horizontal and vertical to evaluate the communication performance of these two networks by changing the baud rate and packet length, and cost and power consumption were considered. Experiments have shown that LoRa networks outperform ZigBee networks in most cases and are the best choice for building communication networks. The experimental results provide basic data support and engineering reference for the application of these two technologies in buildings, especially for the deployment of communication networks throughout buildings. The innovation and contribution of this paper are to discuss the effect of packet length, baud rate, distance, and different locations within a building on the performance of ZigBee and LoRa transmissions, using RTT and PLR as metrics through three experimental scenarios.
Accurate forecasting of residential heating loads is crucial for guiding heating system control strategies and improving energy efficiency. In recent years, research on heating load forecasting has primarily focused on continuous district heating systems, and it often struggles to cope with the abrupt load fluctuations and irregular on/off schedules encountered in intermittent heating scenarios. To address these challenges, this study proposes a hybrid convolutional long short-term memory (ConvLSTM) model that replaces the conventional batch normalization layer with a Dynamic Tanh (DyT) activation function, enabling dynamic feature scaling and enhancing responsiveness to sudden load spikes. An improved channel–temporal attention mechanism, CBAM(T), is further incorporated to deeply capture the spatiotemporal relationships in multidimensional data and effectively handle the uncertainty of heating start–stop events. Using data from two heating seasons for households in a residential community in Dalian, China, we validate the performance of ConvLSTM-DyT-CBAM(T). The results show that the proposed model achieves the best predictive accuracy and strong generalization, confirming its effectiveness for intermittent heating load forecasting and highlighting its significance for guiding demand-responsive heating control strategies and for energy saving and emissions reduction.