Fires usually occur in homes because of carelessness and changes in environmental conditions. They cause threats to the residential community and may result in human death and property damage. Consequently, house fires must be detected early to prevent these types of threats. The immediate notification of a fire is the most critical issue in domestic fire detection systems. Fire detection systems using wireless sensor networks sometimes do not detect a fire as a consequence of sensor failure. Wireless sensor networks (WSN) consist of tiny, cheap, and low-power sensor devices that have the ability to sense the environment and can provide real-time fire detection with high accuracy. In this paper, we designed and evaluated a wireless sensor network using multiple sensors for early detection of house fires. In addition, we used the Global System for Mobile Communications (GSM) to avoid false alarms. To test the results of our fire detection system, we simulated a fire in a smart home using the Fire Dynamics Simulator and a language program. The simulation results showed that our system is able to detect early fire, even when a sensor is not working, while keeping the energy consumption of the sensors at an acceptable level.

Smart grids provide a unique platform to the participants of energy markets to tweak their offerings based on demand-side management. Responding quickly to the needs of the market can help to improve the reliability of the system, as well as the cost of capital investments. Electric load forecasting is important because it is used to make and run decisions about the power grid. However, people use electricity in nonlinear ways, which makes the electric load profile a complicated signal. Even though there has been a lot of research done in this field, an accurate forecasting model is still needed. In this regard, this article proposed a hybrid cross-channel-communication (C3)-enabled CNN-LSTM model for accurate load forecasting which helps decision making in smart grids. The proposed model is the combination of three different models, i.e., a C3 block to enable channel communication of a CNN (convolutional neural networks) model, two convolutional layers to extract the features and an LSTM (long short-term memory network) model for forecasting. In the proposed hybrid model, Leaky ReLu (rectified linear unit) was used as activation function instead of sigmoid. The channel communication in CNN model makes the proposed model very light and efficient. Extensive experimentation was done on electricity load data. The results show the model’s high efficiency. The proposed model shows 98.3% accuracy and 0.4560 MAPE error.