Assessing a vehicle’s remaining driving range (RDR) is essential for alleviating range anxiety, improving energy management, and supporting sustainable mobility in public spaces for electric vehicles (EVs). Recent advancements in data-driven modeling have transformed approaches to RDR estimation, moving from conventional rule-based methods for intelligent systems capable of learning complex relationships among driving styles, battery dynamics, and interactions with external environments. Several studies have demonstrated that using real-time sensor data in conjunction with machine learning (ML) and Deep learning (DL) models enhances the accuracy of RDR estimation and captures the multifaceted relationships among driving speed, acceleration, temperature, road topology, and state-of-charge (SoC) variables. In addition to accuracy, interpretability and trustworthiness remain significant challenges, highlighting the need for causal inference and uncertainty quantification as an essential component in the development of future predictive systems.
The increasing penetration of electric vehicles (EVs), renewable energy sources, and uncertain electricity market conditions has created significant challenges for efficient energy management in smart EV parking lots. This paper proposes a hybrid multi-objective optimization framework, termed Hybrid Self-Improved Seagull Optimization Algorithm with Differential Evolution (H-SI-SOA-DE), for short-term energy management of EV parking lot systems under renewable generation, electricity price, and EV mobility uncertainties. The proposed framework simultaneously optimizes four conflicting objectives: total operational cost, voltage deviation, average EV fleet state-of-charge (SOC), and peak grid power dependency. A chance-constrained optimization formulation is developed to incorporate uncertainties associated with wind generation, electricity pricing, and EV arrival patterns while maintaining system operational feasibility. The proposed H-SI-SOA-DE framework integrates adaptive exploration mechanisms from Self-Improved Seagull Optimization Algorithm (SI-SOA) with Differential Evolution (DE)-based refinement to achieve an effective balance between global exploration and local exploitation. The algorithm is evaluated using the IEEE-33 bus distribution system and compared with benchmark optimization techniques, including NSGA-III, MOPSO, and classical SOA. The results obtained from 20 independent simulation trials demonstrate that the proposed framework achieves superior performance by reducing operational cost to ₹5.22 × 103, minimizing voltage deviation to 0.051 p.u. improving average EV fleet SOC to 91.5
Increasing penetration of inverter-based resources is increasing electricity-system dependence on information that extends beyond conventional physical-state observability. This study develops the Decision-Useful Observability Index (DUOI) to assess whether information is adequate for a specified planning, operational or governance decision across six dimensions: technical, data, operational, economic, consumer-risk and adaptive-governance capability. The framework is applied to six Australian electricity-sector applications using publicly available technical, planning and regulatory evidence. An indicator-level evidence-to-score audit produces dimension scores ranging from approximately 0.45 to 0.88 and equal-weight additive DUOI scores from approximately 0.56 to 0.72, demonstrating uneven information capability across applications and dimensions. Since the six-factor product is intrinsically scale-compressed, multiplicative scores are not directly compared with additive scores; bottlenecks are instead identified from the minimum dimension score and interpreted alongside the dimension profiles and scale-comparable geometric mean. The applications show that the dimension most closely associated with an application’s purpose is not necessarily its principal information bottleneck, and that information can be available yet remain decision-inadequate owing to the limitations in timeliness, accessibility, interoperability, attribution or institutional feedback. Therefore, DUOI extends observability from physical-state measurement to decision-specific information capability and provides an auditable basis for tracing documentary evidence through indicator-level scoring to dimension-level diagnosis and targeted improvements in information infrastructure and governance.
Energy management in industrial facilities requires the integration of operational data, utility systems, and enterprise-level decision-making processes. Although ISA-95-based architectures are widely used for enterprise-control integration, practical deployment of energy-focused monitoring frameworks across large industrial environments remains insufficiently documented. This paper presents a hierarchical multilevel smart energy monitoring system developed for industrial energy management based on ISA-95 principles and OT-IT integration. The proposed architecture integrates field instrumentation, PLC/SCADA systems, Manufacturing Execution Systems (MES), and Enterprise Resource Planning (ERP) platforms into a unified energy monitoring environment. The framework was implemented across more than 15 manufacturing facilities and integrated approximately 1,476 electrical analyzers, 214 compressed-air flowmeters, 126 gas correctors, 73 water meters, and nearly 30,000 operational data streams. The architecture enabled centralized monitoring, plant-level benchmarking, utility-system integration, and enterprise-wide visibility of energy performance. Evaluation using energy datasets obtained from 21 glass manufacturing facilities revealed that furnace systems accounted for approximately 73
When designing Air Handling Units (AHUs) and their components for modern buildings, it is not uncommon to use a standard weather file without accounting for the local microclimate. This sometimes causes the air intake to be located in less-than-optimal locations. In this paper, the effect of using the general outdoor air temperature, as well as the actual air intake temperatures, for both shaded and sun-exposed locations on the AHUs’ peak power and annual energy use of the heating and cooling coils has been investigated. The analysis was carried out on a Danish educational building, focusing on the AHUs supplying comfort ventilation, similar to that in an office building. The results showed that placing the air intake on a sun-exposed façade rather than a shaded one reduced the heating coils’ annual energy demand by up to 7
