The explosive growth of artificial intelligence is exponentially escalating computational demand, inflating data center energy use and carbon emissions, and spurring rapid deployment of green data centers to relieve resource and environmental stress. Achieving sub-minute orchestration of renewables, storage, and loads, while minimizing PUE and lifecycle carbon intensity, hinges on accurate load forecasting. However, existing methods struggle to address small-sample scenarios caused by cold start, load distortion, multi-source data fragmentation, and distribution shifts in green data centers. We introduce HyperLoad, a cross-modality framework that exploits pre-trained large language models (LLMs) to overcome data scarcity. In the Cross-Modality Knowledge Alignment phase, textual priors and time-series attributes are mapped to a common latent space, maximizing the utility of prior knowledge. In the Multi-Scale Feature Modeling phase, domain-aligned priors are injected through adaptive prefix-tuning, enabling rapid scenario adaptation, while an Enhanced Global Interaction Attention mechanism captures cross-device temporal dependencies. The public GreenData dataset is released for benchmarking. Under both data-sufficient and data scarce regimes, HyperLoad consistently surpasses state-of-the-art (SOTA) baselines, demonstrating its practicality for sustainable green data center management.

To secure Intra-Vehicular Networks (IVN) from cyberattacks, we introduce Fed-CMA, a hierarchical federated learning framework that delivers robust personalized Intrusion Detection System (IDS) resilient to data heterogeneity and poisoning attacks. Standard Federated Learning (FL) methods fail in realistic vehicular settings due to non-IID data from diverse Electronic Control Units (ECUs) and driving conditions. Fed-CMA overcomes this by integrating dynamic, context-aware clustering with intra-cluster matched averaging. By grouping clients based on a multi-faceted similarity metric, it isolates anomalous data and potential threats. It then builds specialized models for each cluster using a sophisticated neuron-matching aggregation technique. This synergistic design not only mitigates the negative impacts of data skew but also enhances personalization, leading to a more secure and effective FL deployment in safety-critical automotive systems. Empirically, Fed-CMA proves its robustness, outperforming all baselines with a personalized accuracy of 96.87% under severe data skew.

Driving trajectory data remains vulnerable to privacy breaches despite existing mitigation measures. Traditional methods for detecting driving trajectories typically rely on map-matching the path using Global Positioning System (GPS) data, which is susceptible to GPS data outage. This paper introduces CAN-Trace, a novel privacy attack mechanism that leverages Controller Area Network (CAN) messages to uncover driving trajectories, posing a significant risk to drivers’ long-term privacy. A new trajectory reconstruction algorithm is proposed to transform the CAN messages, specifically vehicle speed and accelerator pedal position, into weighted graphs accommodating various driving statuses. CAN-Trace identifies driving trajectories using graph-matching algorithms applied to the created graphs in comparison to road networks. We also design a new metric to evaluate matched candidates, which allows for potential data gaps and matching inaccuracies. Empirical validation under various real-world conditions, encompassing different vehicles and driving regions, demonstrates the efficacy of CAN-Trace: it achieves an attack success rate of up to 90.59% in the urban region, and 99.41% in the suburban region.

Short-term water demand prediction is essential for optimizing residential and industrial water management. Several studies have demonstrated the usefulness of water usage demand forecasting in making smart cities sustainable. However, the real-world translation of such forecasting systems still needs to be exploited. In this research, we have developed +10 days short-term demand forecasting framework that utilizes the existing state-of-the-art statistical and deep learning models. The designed framework has been integrated into the utility company's legacy water usage demand forecasting process to promote digitization and sustainability. The research outcomes have demonstrated that the designed framework has improved the forecast accuracy upon successful integration with the legacy operational process. Index Terms-Short-term Forecasting, Time Series Modeling, Regression Modeling, Deep Learning Modeling, Water Demand, Water Supply, Weather-based Demand Prediction

As the primary standard protocol for modern cars, the controller area network (CAN) is a critical research target for automotive cybersecurity threats and autonomous applications. As the decoding specification of CAN is a proprietary black-box maintained by original equipment manufacturers (OEMs), conducting related research and industry developments can be challenging without a comprehensive understanding of the meaning of CAN messages. In this article, we propose a fully automated reverse-engineering system, named ByCAN, to reverse engineer CAN messages. ByCAN outperforms the existing research by introducing byte-level clusters and integrating multiple features at both the byte and bit levels. ByCAN employs the clustering and template matching algorithms to automatically decode the specifications of CAN frames without the need for prior knowledge. Experimental results demonstrate that ByCAN achieves high accuracy in slicing and labeling performance, i.e., the identification of CAN signal boundaries and labels. In the experiments, ByCAN achieves slicing accuracy of 80.21%, slicing coverage of 95.21%, and labeling accuracy of 68.72% for the general labels when analysing the real-world CAN frames.

The Internet of Things contributes to energy systems by expanding manufacturing processes with modern devices and intelligent systems. Nowadays, the heating sector is in a race to increase the insertion of technologies in supply chain and production activities. For this, a modeling method is proposed based on the Internet of Things of smart systems. Compared with the conventional roadmap, the smart heating system’s center is a framework comprising a physical equipment layer, sensing and dispatch layer, data transmission layer, and decision-making layer. This method can improve the accuracy of modeling and contribute to in-depth optimization. This study intends to explore and discuss the critical technologies of smart heating systems and their applications.

The Internet of Things (IoT) has gained lots of attention in the past decade and has shown huge potential in the integration of power systems to build a smart grid architecture and to achieve a paradigm transformation. This paper first proposed a typical architecture of IoT in power systems. To reveal the research status, literature development, cooperative relationship, hotspots of techniques, and the research trend, a bibliometric analysis from 1196 papers in the WoS database was done. Finally, several research trends were concluded based on the bibliometric analysis. This paper, for the first time, provided a systematic review of the hotspots in the field of IoT in power systems for more than a decade. Additionally, this paper provided a clear understanding of the history and outlook of the development of the IoT in power systems.

The Internet of Things technology is gradually being used in district heating systems. However, China’s heating systems have varying hardware and software levels, Informatization, and intelligence. The coarse time granularity and the missing data brings significant challenges to system analysis and diagnosis. This paper proposes to study heating systems’ sample completion load data based on denoising diffusion probabilistic models. The method is validated based on the field data from 2021 to 2022 of a district heating system in Changzhou. Besides, the key features affecting the completion quality are discussed, the results show that climate data dominate the quality of the generated data. When comparing the real data under the same conditions, the best-performing models have errors in 1.1485°C. The study provides a new data analysis method for theoretical and technical studies under data deficiency scenarios for heating systems.

A smart energy platform for the large-space stadium based on Internet of Things (IoT) is proposed. The platform could realize the safe and stable operation of the energy system in various scenarios and promote low-carbon, efficient and sustainable development. In this paper, the smart energy platform is constructed based on IoT device data collection, time series data storage, front-end smart energy platform, and back-end optimization modules. The architecture and framework of the platform are explained in details. This study takes a large-space building in Hangzhou as an example to explain how the smart energy platform works in the real site. The real-time monitoring map of carbon emissions module and load prediction module of air-conditioning system are presented. The developed smart energy platform based on IoT could support the digital twin-based operation management of various types of low-carbon buildings in the future.

The undisclosed Controller Area Network (CAN) decoding specification is important to the in-vehicle network (IVN) research for both industry and academia. Researchers have developed several CAN reverse engineering systems to predict signal boundaries and labels in order to map out CAN signal decoding specifications. Existing works mainly use one parameter (i.e., bit flip rate) to determine CAN signals boundary, which results in biased slicing and labelling of CAN signals. In this paper, we propose a multi-layer CAN reverse engineering system to cluster signal boundary at byte-level and label sliced CAN signal blocks at bit-level. The proposed system avoids biased signal slicing and labelling by introducing multiple parameters in signal classification, while existing works only use the bit flip rate and the number of unique value. The feasibility and adaptability of the proposed system is assessed by deploying it into a web application as a functionality module. We evaluate the proposed system with CAN messages from real cars. Compared with existing reverse engineering models, the proposed system introduces multi-layer signal processing to avoid over-slicing and over-labelling problem.

The legacy design of the Controller Area Network (CAN) weakens the encryption and authentication of the In-Vehicle Networks (IVN). Anomaly detection systems, e.g. the Long-Short Term Memory (LSTM) based Intrusion Detection System (IDS), are employed to remedy the defection of CAN. Existing works feed the LSTM-based IDS with the byte values of the data payload of CAN to train and test the LSTM model. In this paper, we propose an LSTM-based IDS leveraging byte-level features, i.e., byte flip rate, byte-level change rage, and byte-level distinct value rate, to augment the sensitivity of proposed LSTM-based IDS when distinguishing malicious CAN messages. By using the byte-level signal features, the proposed system achieves high accuracy with a small size of the training dataset. The experiment results show that the model with the byte-level features can achieve a performance gain of the$F$1Score up to 20% over the model without the byte-level features.

The development of location-based services (LBS) leads to the rapid growth of location data, potentially increasing the threat to location privacy. Existing location obfuscation techniques focus on two-dimensional (2D) planar areas and overlook the features of road networks. In this paper, we leverage differential privacy and propose a new notion of Road Network-Indistinguishability (RN-Indistinguishability) to measure the indistinguishability of locations in road networks. With the RN-Indistinguishability, we design a Cloaking Region Obfuscation (CRO) mechanism to protect the location privacy of vehicles on roads. With the CRO mechanism, vehicle locations in a cloaking region are obfuscated following the same obfuscation distribution. The proposed CRO mechanism is proved to achieve RN-Indistinguishability and can be generalized with road network features holding the triangle inequality. Comprehensive experiments show that the CRO mechanism outperforms existing 2D obfuscation mechanisms in real-world road networks.