Heating, ventilation, and air-conditioning (HVAC) systems consume approximately 60% of the total energy consumption in public buildings, and an effective way to reduce HVAC energy consumption is to provide accurate load forecasting. This paper proposes a load forecasting model CEEMDAN-Conv1D-BiLSTM-AM which combines empirical mode decomposition and neural networks. The load data are decomposed into fifteen sub-sequences using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The neural network inputs consist of the decomposition results and five exogenous variables. The neural networks contain a one-dimensional convolutional layer, a BiLSTM layer, and an attention mechanism layer. The Conv1D is employed to extract deep features from each input variable, while BiLSTM and the attention mechanism layer are used to learn the characteristics of the load time series. The five exogenous variables are selected based on the correlation analysis between external factors and load series, and the number of input steps for the model is determined through autocorrelation analysis of the load series. The performance of CEEMDAN-Conv1D-BiLSTM-AM is compared with that of five other models and the results show that the proposed model has a higher prediction accuracy than other models.

The effectiveness of a cruise ship’s emergency evacuation is greatly influenced by the way people interact; this paper uses the social force model to simulate two different evacuation scenarios considering the impact of small groups. It uses an agent to simulate the behavior of a single occupant, and leverages the social force model to quantify the effect of group behavior on the group members. According to the influence of the group on the members, this paper corrects the expected speed of the members to determine the speed of crowd evacuation. It uses the SAFEGUARD cruise ship as the evacuation platform to simulate the process of evacuating the passengers to the boarding station and assembly station, respectively, and calculates the evacuation time, congestion area, and congestion duration of passengers under the action of groups. The simulation results of the two scenarios show that the group effect increases the average evacuation time by 15.29% and 21.79%, and increases the average detour distance by 24.54% and 17.89%, respectively.

The energy consumption of air conditioning systems is an important part of the energy consumption of buildings, and is particularly important today when energy efficiency in buildings is a major worldwide trend and trend. This paper uses river water as the system cooling source for the building cooling to save energy. In this paper, energy consumption models for chillers, heat pump units, pumps and energy storage tanks are first developed. The energy consumption of the pumps is fitted for optimization, using a penalty function to ensure that the optimization parameters are within the constraints. The energy consumption of the heat pump system is then optimized using a two-layer particle swarm algorithm. Finally, the optimization is carried out with a typical day-by-day hourly cooling load. The experimental results show that the method proposed in this paper not only reduces the energy consumption of the heat pump system and achieves peak shifting and valley filling, but also reduces the operating costs of the air conditioning system, which has good economic benefits.

The multi-station integrated system (MSIS) integrates traditional substations with renewable sources such as photovoltaics, wind power, energy storage, and electric vehicle (EV) charging to enhance energy efficiency and economics. However, the challenge remains on how to efficiently integrate and utilize these resources while ensuring a stable and reliable power supply. This paper proposes a primal-dual interior-point-based scheduling method for a small-scale multi-energy system in a 220 kV substation integrating electricity, solar, wind, and geothermal energy. The MSIS within this substation solely supplies power to the EV charging station, hydrogen production station, ground source heat pump system, and internal lighting loads. Mathematical models are established in this paper for various energy sources and loads to describe their characteristics. An optimization scheduling model for the MSIS within the substation is constructed, aiming to maximize system profits. Constraint conditions include energy balance, charging and discharging power, water storage volume, gas tank capacity, and energy storage battery capacity. This model employs a combination of the primal-dual interior-point method and rolling optimization to seek the globally optimal energy scheduling strategy. Simulation results based on a system configuration reflective of real-world deployment in Wuhan demonstrate that, compared with the grid-only baseline, the proposed strategy reduces electricity purchase cost by 20.4%, achieving the lowest net energy cost of 970.05 Chinese Yuan and the highest carbon reduction benefit of 1993.80 kg. Moreover, the optimization helps reduce peak demand, fill valleys, and improve the load-balancing capability of the power grid.