Jiying Liu

1. 1.1. Urban areas face various challenges, including poor thermal conditions and air pollution, which strongly impact the living quality, especially for the people engaging in outdoor activities....

Continuous carbon anode roasting in industrial parks requires a stable high-temperature heat supply and remains highly dependent on grid electricity and natural gas. However, existing energy-system studies rarely coordinate hydrogen production and storage, volumetric hydrogen blending, and temperature-graded waste-heat recovery under continuous production constraints. To address this gap, this study proposes an electricity–heat–gas–hydrogen integrated energy system for carbon anode industrial parks and develops a 24 h multi-objective scheduling model. The model coordinates heat demands at different temperature levels with hourly electricity and hydrogen flows, using surplus photovoltaic power to produce hydrogen for later high-load periods. The selected scheme achieves a daily volumetric hydrogen-blending ratio of 10.79%, with an operating cost of 82,985.75 CNY and carbon emissions of 54,371.53 kg. Relative to an otherwise equivalent non-hydrogen configuration, hydrogen coupling provides additional reductions of 7.2% in operating cost and 2.3% in carbon emissions. Compared with a basic conventional configuration, operating cost and carbon emissions decrease by 27.9% and 26.0%, respectively. Cascade recovery also increases the daily waste-heat utilization rate by approximately 30 percentage points. These results show that the proposed scheduling framework can coordinate hydrogen utilization and graded waste-heat recovery while maintaining continuous carbon anode production.

Heating load is jointly affected by meteorological conditions, system operating states, and historical evolution, exhibiting nonlinear, time-varying, and locally fluctuating characteristics. To improve short-term forecasting accuracy, this study proposes a particle swarm optimization (PSO)-based Trend–convolutional neural network (CNN)–bidirectional long short-term memory (BiLSTM)–Attention model. The model constructs trend-enhanced features from meteorological variables, operating parameters, temporal periodicity, historical lags, rolling statistics, differenced features, and exponentially weighted moving averages. CNN is used to extract local temporal features, BiLSTM captures bidirectional temporal dependencies, and Attention identifies key time steps. PSO further optimizes key hyperparameters. Two datasets are constructed from hourly heating-season operating data, and the proposed model is compared with BiLSTM, CNN-BiLSTM, CNN-BiLSTM-Attention, and Trend-CNN-BiLSTM-Attention models. The proposed model achieves the best performance on both datasets. For Dataset 1, the mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R²) are 0.628 GJ, 0.928 GJ, 9.308%, and 0.851, respectively; for Dataset 2, they are 0.3987 GJ, 0.5954 GJ, 10.32%, and 0.8709. These results indicate that trend-enhanced features and PSO improve forecasting performance and can support heating system operation scheduling.

Addressing the deficiencies of data-driven heating, ventilation, and air conditioning (HVAC) models in multi-objective joint prediction, long-horizon prediction accuracy, and uncertainty quantification, this study proposes a heterogeneous deep ensemble framework. Through co-simulation technology, a multi-operating-condition operational dataset for a typical variable air volume (VAV)–Reheat system was constructed. By adopting an operating-condition-level partitioning strategy, the input features were strictly decoupled into historical system states, internal loads, and external control commands. On this basis, the framework integrates the advantages of Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and Temporal Convolutional Networks (TCN). Utilizing an inverse-variance weighting mechanism, it achieves the synchronous and accurate prediction of 11-dimensional targets, encompassing total system power, five-zone temperatures, and five-zone CO₂ concentrations. Simultaneously, the prediction divergence among the ensemble models is utilized to quantify epistemic uncertainty, and a variance scanning mechanism is introduced to calibrate the prediction confidence intervals. The results indicate that within a 6 h prediction horizon, the absolute errors of the model in power, temperature, and CO₂ are reduced by 80.17%, 63–72%, and 75–80.62%, respectively, compared to the physical baseline. On the independent test set, the actual coverage rate of the calibrated prediction intervals approaches 90%, exhibiting an adaptive enveloping variation characterized by tightening during steady states and widening during transients. The proposed heterogeneous ensemble framework demonstrates superior prediction accuracy and long-horizon prediction stability, providing reliable model support for multi-objective optimal operation and robust control of buildings.

Office buildings are significant contributors to energy consumption and carbon emissions due to high occupancy density and prolonged operation. To balance decarbonization with indoor environmental quality, this study proposes a simulation-driven multi-strategy optimization framework for a three-story office building in Jinan. This study integrates EnergyPlus 23.2, jEPlus+EA 2.3.2, and the NSGA-II algorithm to co-optimize building performance. We evaluate the synergistic effects of roof photovoltaic coverage ratio, night ventilation turn-on temperature difference, and HVAC control strategies on carbon emissions and thermal comfort, while ensuring that CO₂ concentrations remain within health thresholds. The results indicate that the night ventilation temperature turn-on temperature difference is the most influential parameter. It yields standardized regression coefficients (SRCs) of 0.7456 for carbon emissions and 0.5325 for thermal discomfort. The Pareto-optimal solution achieves a carbon footprint of approximately 477 tCO₂, with only 8.8% indoor discomfort hours. This framework provides a robust, practical approach for the low-carbon and healthy operation of office buildings.

Accurate forecasting of energy demand in commercial retail buildings remains challenging due to complex operational and occupancy-driven patterns that are not fully explained by weather variables alone. This study investigates dynamic energy consumption prediction using artificial neural network (ANN)–based spatiotemporal models, focusing on CNN-LSTM and Transformer architectures. Electricity consumption data from three to ten commercial retail stores in the Oslo region of Norway are analyzed using time-series modeling techniques. A novel forecasting framework is proposed that incorporates energy-use interactions between a target store and its surrounding commercial buildings. The approach systematically evaluates neighboring-store datasets to identify the most informative inputs for each ANN model. By leveraging shared consumption dynamics among nearby stores, the proposed method captures behavioral factors such as customer flow, shopping schedules, and occupancy patterns, leading to improved prediction accuracy and stability. The results show that models trained on weather data exhibit limited predictive capability for dynamic commercial retail energy demand. Transformer models demonstrate superior performance under limited training data conditions, while CNN-LSTM models achieve higher accuracy when larger datasets from surrounding stores are available. Overall, the findings confirm that both CNN-LSTM and Transformer architectures are effective for commercial energy demand forecasting and highlight the importance of incorporating surrounding buildings’ energy consumption data to enhance prediction performance.