The increasing complexity of urban building energy systems necessitates advanced prediction methods for efficient energy management. Urban buildings account for approximately 40% of global energy consumption, making accurate prediction crucial for sustainability goals. This research develops a novel transformer-based deep learning framework for multi-building energy consumption forecasting. Despite recent advances in energy prediction techniques, existing models struggle with multi-building scenarios due to limited ability to capture cross-building correlations, inadequate integration of diverse data streams, and poor scalability when deployed at urban scale—gaps this research specifically addresses. The study implemented a modified transformer architecture with hierarchical attention mechanisms, processing data from 100 commercial buildings across three climate zones over three years (2020–2023). The framework incorporated weather parameters, occupancy patterns, and historical energy consumption data through multi-head attention layers, employing a 4000-step warm-up period and adaptive regularization techniques. The evaluation included a comparison with the baseline models (ARIMA, LSTM, GRU) and robustness testing. The framework achieved a 23.7% improvement in prediction accuracy compared to traditional methods, with a mean absolute percentage error of 3.2%. Performance remained stable across building types, with office complexes showing the highest accuracy (MAPE = 2.8%) and healthcare facilities showing acceptable variance (MAPE = 3.5%). The model-maintained prediction stability under severe data perturbations while demonstrating near-linear computational scaling. The transformer-based approach significantly enhances building energy prediction capabilities, enabling more effective demand-side management strategies, though future research should address long-term adaptability.

Recent research has examined the possibility of recovering energy from mechanical vibration induced by a vehicle shock absorber using piezoelectric and electromagnetic transducers. In terms of automotive applications, piezoelectric vibration energy harvesting shows promise for recapturing some (even if small) amounts of vehicle vibration energy, which would otherwise be wasted through the vehicle dampers. Functional materials, such as piezoelectric materials, are capable of converting mechanical energy into useful electrical energy and vice versa. In this paper, an innovative rotational piezoelectric vibration-energy-harvesting device is presented that employs a magnetic coupling mechanism and provides robust performance over a range of frequencies. The piezoelectric energy harvester is driven by a unidirectional suspension system. An experimental investigation was carried out to study the performance of the manufactured prototype. We observed no damage to the prototype after operating continuously at a vibration amplitude of 5 mm at a frequency of 2.5 Hz for over 10,000 cycles. In addition, the presented regenerative suspension system is capable of producing high and relatively steady open-circuit voltages, irrespective of excitation frequencies. The results demonstrate that regenerative shock absorber is robust and has a broad frequency range.

While existing building energy prediction methods have advanced significantly, they face fundamental challenges in simultaneously modeling complex spatial–temporal relationships between buildings and integrating dynamic weather patterns, particularly in dense urban environments where building interactions significantly impact energy consumption patterns. This study presents an advanced deep learning system combining temporal graph neural networks with weather data parameters to enhance prediction accuracy across diverse building types through innovative spatial–temporal modeling. This approach integrates LSTM layers with graph convolutional networks, trained using energy consumption data from 150 commercial buildings over three years. The system incorporates spatial relationships through a weighted adjacency matrix considering building proximity and operational similarities, while weather parameters are integrated via a specialized neural network component. Performance evaluation examined normal operations, data gaps, and seasonal variations. The results demonstrated a 3.2% mean absolute percentage error (MAPE) for 15 min predictions and a 4.2% MAPE for 24 h forecasts. The system showed robust data recovery, maintaining 95.8% effectiveness even with 30% missing values. Seasonal analysis revealed consistent performance across weather conditions (MAPE: 3.1–3.4%). The approach achieved 33.3% better prediction accuracy compared to conventional methods, with 75% efficiency across four GPUs. These findings demonstrate the effectiveness of combining spatial relationships and weather parameters for building energy prediction, providing valuable insights for energy management systems and urban planning. The system’s performance and scalability make it particularly suitable for practical applications in smart building management and urban sustainability.

Smart energy solutions are critical to the development of smart cities, aligning with Saudi Arabia’s Vision 2030, which aims to transform urban centers through sustainable technologies. This transformation, driven by the widespread use of smart sensors for traffic regulation, parking systems, and environmental monitoring, requires efficient, eco‐friendly energy sources to reduce reliance on conventional batteries. In the city of Hail, wind energy presents a promising opportunity to generate clean power for low‐energy sensors. This paper introduces a compact small wind energy harvesting system (SWEHS) that integrates piezoelectric and electromagnetic mechanisms designed specifically for powering sensors in low‐wind environments. The harvester consists of two concentric rings: an inner rotator ring containing four equally spaced permanent magnetic plates arranged in a symmetrical pole configuration to minimize starting torque and improve power generation at low wind speeds. The outer ring incorporates four piezoelectric benders coupled with magnetic plates, converting mechanical energy into electrical power. Experimental results show that the Savonius rotor design outperforms Helical Savonius and Cup rotors, achieving a peak power output of 0.767 mW at a resistive load of 15 k Ω and wind speed of 6.5 m/s. This design demonstrates superior efficiency in decentralized energy production, making it a viable solution for sustainable, low‐power energy harvesting in smart city infrastructure.