Jul 2026· 2026 2nd International Conference on IOT, Data Science and Advanced Computing (IDSAC)· pp. 128-135· 0 citations· 41 references
Abstract
For urban ride-hailing services, accurate shortterm demand forecasting is essential for improving vehicle dispatching efficiency, reducing passenger waiting times, and supporting sustainable and intelligent urban mobility management. Short-term ride-hailing demand is shaped by complex couplings among historical demand, temporal regularity, and weather, which makes accurate prediction challenging. Unlike most existing ride-hailing forecasters that rely on graph-intensive or task-specific architectures, this paper proposes a concise Transformer-based method whose unique contribution to ridehailing demand prediction lies in two aspects: (i) a compact multifactor feature set tailored to short-term ride-hailing fluctuation, integrating historical demand, fine-grained temporal attributes, and weather variables; and (ii) explicit modelling of the nonlinear and non-monotonic effects of extreme weather and rainfall intensity on demand within a single Transformer encoder. Experiments on the City of Chicago Transportation Network Providers (TNP) dataset show that the proposed method achieves an MAE of 14.8, an RMSE of 20.1, and a MAPE of 12.1%, outperforming LSTM, Bi-LSTM, and GRU on all three metrics, with relative reductions of 20.9% in MAE, 19.3% in RMSE, and 23.4% in MAPE versus LSTM. These results demonstrate that a concise Transformer with carefully designed multi-factor features can serve as an effective, reproducible baseline for short-term ridehailing demand forecasting, supporting smarter vehicle allocation, lower idle mileage, and reduced energy consumption and carbon emissions in intelligent transportation systems.
Accurate short-term load forecasting for EV public charging stations is essential for grid and station operations. However, predictions are challenging because charging loads are non-stationary, spatially heterogeneous, and closely coupled with external factors such as weather and pricing. In this study, we forecast hourly regional charging energy using the open UrbanEV benchmark dataset, which includes hourly charging records from 1362 public charging stations across 275 traffic-analysis zones in Shenzhen from September 2022 to February 2023. We propose ST-Attention, a lightweight and modular forecasting model. It integrates temporal self-attention, spatial self-attention, an adjacency-matrix bias, and a residual prediction head. We compare ST-Attention with five baselines using a leakage-free rolling time-series evaluation protocol. For the 3 h horizon, ST-Attention achieves an MAE of 62.44 kWh, an RMSE of 291.8 kWh, and an MAPE of 5.91%, reducing the MAE by approximately 41% compared with the last-observation baseline. The model also maintains superior MAE performance at the 6 h and 9 h horizons. A modular ablation study shows that temporal attention and the residual head are the most stable sources of improvement, whereas dense spatial attention does not automatically provide benefits at hourly granularity with limited samples; removing it further reduces the 3 h MAE to 59.58 kWh. We present this as a cautionary finding: local temporal inertia dominates dense spatial coupling in hourly forecasting, and spatial model complexity must align with data granularity.
Ride-hailing dispatching with mixed on-demand and advance requests faces several challenges: platforms must respond to immediate requests, preserve flexibility for upcoming advance requests, and consider how each accepted request changes post-drop-off vehicle positions and subsequent service opportunities. Existing studies usually deal with demand forecasting and dispatching separately. Forecasting models mainly optimize order-count errors, and dispatching models usually focus on pickup distance, revenue, and waiting time, with limited consideration of destination opportunity and risk. To alleviate this prediction–dispatch disconnection, this paper proposes a risk-aware online dispatching method. The method develops a closed-loop context-aware spatio-temporal multi-task network (CC-STMT) using a physical-distance graph, a functional–semantic graph, and en-route supply feedback to estimate demand intensity, low-opportunity risk, and demand dispersion. Then, the demand-prediction-guided optimal transport matching (DP-OTM) method, which embeds destination opportunities and risks into the vehicle–request matching cost to generate an executable one-to-one allocation, is designed. Compared with the best-performing non-CC-STMT baseline for each metric, CC-STMT reduces MAE by 1.38%, 1.65%, and 7.65% and RMSE by 2.70%, 3.92%, and 5.14% in NYC, Chicago-A, and Chicago-B, respectively. Compared with Base-UOT, DP-OTM reduces future low-opportunity drop-offs and improves post-drop-off destination opportunity. These results support destination-aware dispatching in public-data simulations.
Zhigang Ji, Jie Wang, Yunkai Hao· Applied Sciences· 0 citations
This work studies multi-horizon taxi demand prediction as the task of learning a mapping from past observations to multiple future demand values under temporal dependence and uncertainty, and suggests that successful multi-horizon forecasting requires global temporal interaction and explicit quantification of uncertainty.
Magesh Rajakumar, C. Markarian, S. Atalla· Proceedings of the 15th Inte...· 0 citations
The accelerating adoption of electric vehicles (EVs) presents significant challenges for maintaining grid stability and optimizing charging infrastructure. Accurate short-term forecasting of EV charging demand is therefore critical to support reliable grid operation and effective energy management in urban environments. However, existing forecasting models often fail to capture the intricate interdependencies among mobility patterns, weather variations, and real-world charging behaviors, which constrains their generalizability and robustness. This study develops a multi-model forecasting framework that leverages Transformer-based deep learning architectures to integrate real-world charging data with traffic flow and meteorological variables for predicting short-term EV charging demand across metropolitan areas. To benchmark performance, two additional machine learning models—CatBoost and convolutional neural networks (CNNs)—are systematically evaluated using datasets from urban EV supply equipment (EVSE) and electric bus systems. The results indicate that Transformer-based models deliver superior predictive accuracy, temporal consistency, and adaptability compared with CNNs and CatBoost. Furthermore, sensitivity analysis reveals that traffic dynamics and user charging behavior exert the strongest influence on forecast performance. The proposed framework offers actionable insights for utilities and urban planners, facilitating resilient grid operation, optimized charging infrastructure deployment, and accelerated integration of EVs into the power system.
Christoph Sommer, Jahangir Hossain, Abbas Tabandeh· Energies· 0 citations
An integrated prediction-and-visualisation pipeline that transforms complex data distributions into actionable visual analytics, such as interpretable station-to-station demand heatmaps via interactive GIS Folium layers is implemented, providing an operationally robust framework to support smart-city transportation management and build more sustainable urban transit systems.
Berna Çalışkan· Journal of Data Analytics an...· 0 citations
Urban water demand forecasting is a critical component of short-term supply planning and real-time operational decision-making in smart city water management. This study presents a scenario-aware machine learning framework designed to predict daily urban water consumption across selected cities in Karnataka, India. The proposed framework integrates meteorological, temporal, and demand-related attributes to model consumption behavior effectively. A robust preprocessing pipeline is implemented, encompassing missing-value imputation, temporal sorting, lag and rolling feature construction, categorical encoding, and correlation-based feature selection. Three predictive models—XGBoost, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—are developed and compared. The optimal model is deployed via a Flask-based web application featuring SQLite storage, real-time weather data retrieval through Open-Meteo APIs, public holiday detection, prediction history management, and interactive scenario simulation capabilities for rainfall, heatwave, and holiday demand variations. The integrated framework offers water utilities a practical decision-support tool for proactive resource allocation and contingency planning. By enabling what-if analysis under extreme weather events and special calendar days, the system enhances municipal preparedness and contributes to sustainable urban water resource management. This work demonstrates the operational viability of combining machine learning with scenario-based planning to address the complexities of water supply systems in developing urban regions.
Mithil.M, Prof. H L Shilpa, Dhanush K et al.· International Research Journ...· 0 citations
