Short-term residential load forecasting is the precondition of the day-ahead and intra-day scheduling strategy of the household microgrid. Existing short-term electric load forecasting methods are mainly used to obtain regional power load for system-level power dispatch. Due to the high volatility, strong randomness, and weak regularity of the residential load of a single household, the mean absolute percentage error (MAPE) of the traditional methods forecasting results would be too big to be used for home energy management. With the increase in the total number of households, the aggregated load becomes more and more stable, and the cyclical pattern of the aggregated load becomes more and more distinct. In the meantime, the maximum daily load does not increase linearly with the increase in households in a small area. Therefore, in our proposed short-term residential load forecasting method, an optimal number of households would be selected adaptively, and the total aggregated residential load of the selected households is used for load prediction. In addition, ordering points to identify the clustering structure (OPTICS) algorithm are also selected to cluster households with similar power consumption patterns adaptively. It can be used to enhance the periodic regularity of the aggregated load in alternative. The aggregated residential load and encoded external factors are then used to predict the load in the next half an hour. The long short-term memory (LSTM) deep learning algorithm is used in the prediction because of its inherited ability to maintain historical data regularity in the forecasting process. The experimental data have verified the effectiveness and accuracy of our proposed method.

A damage location method for the autocorrelation peak value change rate based on the vibration response of a random vibration structure is established. To calculate the autocorrelation function of the vibration response of each measurement point, we transformed the maximum values into an autocorrelation peak vector. Under a good condition, the autocorrelation peak vector has a fixed shape; hence, it can be used as a basis for structural damage identification. The two adjacent measurement points with the largest change corresponding to the two nodes of the damage unit and the damage location are determined to calculate the change rate of the autocorrelation peak values between damaged and intact structures. When the degree of damage is 5%, the autocorrelation peak value change rate of the acceleration response on the two nodes of the damage unit is significantly greater than that of the other points, which can accurately determine the damage location, indicating that the damage location index constructed has good damage sensitivity. The damage location index can determine a single damage, as well as a double damage. The antinoise capability of the damage location index gradually improves with an increase in the degree of damage. At 45% degree of damage and signal-to-noise ratio (SNR) of 0 dB, the damage location index can still accurately determine the damage location, which has good antinoise interference capability. The Xi’an Bell Tower is used as a case study, and the feasibility of this method is verified, which provides a new method for the study of damage location of ancient timber structures.