Electricity theft poses serious risks to utility revenue and distribution grid stability, making robust Electricity Theft Detection (ETD) a critical priority for modern smart grids. Existing ETD methods often smooth out consumption behaviors during data recovery and show unstable performance under imbalanced and shifted deployment conditions. To address these challenges, this paper proposes an integrated Multi Metric Adaptive Recovery and Meta-Learned Fisher Discriminant (MMAR–MLFD) framework tailored for practical smart grid deployments. First, the Multi-Metric Adaptive Recovery (MMAR) module integrates multiple complementary autoencoder objectives and adaptively fuses multiple reconstruction outputs to preserve theft related load irregularities while suppressing noise under missing measurements. Second, the Meta-Learned Fisher Discriminant (MLFD) performs episodic meta learning to learn a shared encoder. Each task then derives a Fisher decision boundary in closed form from a few labeled users, avoiding inner-loop updates. Validated on a national scale smart grid dataset, MMAR–MLFD reduces recovery error by up to 55.3% and improves detection accuracy by 7–14%. The proposed method also lowers false-positive rates by more than one-third, reducing unnecessary field inspections and enhancing the reliability of revenue-protection operations.

Incomplete data in smart grid measurement tools (SGMT) poses significant challenges for accurate monitoring and decision making. Traditional autoencoders with fixed loss functions struggle to handle heterogeneous corruption patterns—dense, low-amplitude noise and sparse, high-impact anomalies. This paper presents a multi-metric adaptive autoencoder designed for recovering incomplete SGMT data (MMAS). By combining diverse Lp-norm autoencoders with an adaptive weighting mechanism and nonnegative, density-aware optimization, MMAS effectively captures both noise and anomaly patterns. Experimental results on real-world data show that MMAS consistently outperforms baseline methods in both recovery accuracy and downstream tasks. The proposed framework offers a robust and practical solution for SGMT data recovery under varying sparsity conditions.

As a well known machine learning model, Gradient Boosting Decision Tree (GBDT) is widely used in many real-world scenes such as online marketing, risk management, fraud detection and recommendation systems. Due to limited data resources, two data owners may collaborate with each other to jointly train a high-quality model. As privacy regulations such as HIPPA and GDPR come into force, Privacy-Preserving Machine Learning (PPML) has drawn increasingly higher attention. Recently, a line of works [3--6] studies function secret sharing (FSS) schemes in the preprocessing model, where the online stage of secure two-party computation (2PC) is significantly improved. While recent privacy-preserving GDBT frameworks mainly focus on improving the performance of a singular module (e.g. secure bucket aggregation), we propose SiGBDT, a globally silent two-party GBDT framework via function secret sharing on a vertically partitioned dataset. During the training process, we apply FSS schemes to construct efficient modular protocols, such as secure bucket aggregation, argmax computation and a node split approach. We run in-depth experiments and discover that SiGBDT completely outperforms state-of-the-art frameworks. The experiment results show that SiGBDT is at least 3.32 X faster in LAN and at least 6.4 X faster in WAN.

Data I/O poses a significant bottleneck for distributed deep learning applications. Utilizing computing-node attached storage as a cache has become a prevalent solution to this problem. Given the large size of training datasets and the limited capacity of a single-node local storage, training samples are loaded in shards across computing nodes, requiring a deep learning job on one node to access samples from neighboring nodes. Compared to local node access, these neighboring accesses are highly inefficient for small samples. To mitigate this issue, we propose a node-aware prefetch algorithm that greedily fetches samples from neighboring nodes. Evaluation results show that our approach improves neighboring access performance by 60x for small samples of 64B size. For large samples of 1MB size, our approach still exhibits a 26% improvement.

This paper presents a novel quality assessment approach for the prediction of the subjective haptic experience in time-delayed teleoperation. With the rapid development of haptic technology in remote robot control and virtual reality, new control schemes and hardware systems are developed to provide high quality human-in-the-loop teleoperation service. Our subjective experiments indicate that the existing objective quality assessment metrics do not sufficiently correlate with the subjective haptic experience of the users. This gap requires expensive and time-consuming subjective experiments to be conducted. To avoid time-consuming experiments and provide a fast and accurate subjective experience prediction, we make an attempt to analyze and explain the mismatch between the subjective and objective haptic signal quality metrics. To this end, extensive subjective experiments and case studies have been conducted for teleoperation with time delay and haptic data reduction. Based on our experimental results, we propose a quality assessment approach that predicts the subjective quality of experience using multiple objective metrics. For the one-dimensional spring model, the Spearman’s rank-order, Kendall’s rank-order and Pearson’s Linearity correlation coefficient (SROCC, KLOCC and PLCC) between the predictions of our model and the results of subjective experiment show remarkable improvement on the correlation between subjective and objective quality assessment.

Key-value (KV) stores based on multi-stage structures are widely deployed to organize massive amounts of easily searchable user data. However, current KV storage systems inevitably sacrifice at least one of the performance objectives, such as write, read, space efficiency etc., for the optimization of others. To understand the root cause of and ultimately remove such performance disparities among the representative existing KV stores, we analyze their enabling mechanisms and classify them into two fundamental models of data structures facilitating KV operations, namely, the multi-stage tree (MS-tree), and the multi-stage forest (MS-forest). We build SifrDB, a KV store on a novel split forest structure, that achieves the lowest write amplification across all workload patterns and minimizes space reservation for the compaction. To mitigate the read amplification inherent in MS-forest, we introduce a bloom filer mechanism based on Sorted String Tables (SSTs). Furthermore, we also present a highly efficient parallel search approach that fully exploits the access parallelism of modern flash-based storage devices to substantially boost the read performance. Evaluation results show that under both micro and YCSB benchmarks, SifrDB outperforms its closest competitors, i.e., the popular MS-forest implementations, making it a highly desirable choice for the modern KV stores.

Power equipment management, operation and maintenance require a large amount of online monitoring information. At present, from the perspective of overall system intelligence, grid online monitoring technology is still immature. It lacks effective monitoring methods and online monitoring data management and analysis methods, so that it cannot meet the new needs of smart grid development. Combined with the planning of the full-service ubiquitous power Internet of Things (UPIoT) comprehensive construction by State Grid Corporation of China, the application of UPIoT technology in equipment monitoring is proposed. Firstly, the UPIoT basic concept is expounded and its technical architecture is analyzed in detail. Secondly, the key technologies of UPIoT equipment monitoring are discussed from the four aspects of integrated intelligent monitoring device, coding and identification system, communication technology, and security threat.

Key-value stores are increasingly adopting LSM-trees as their enabling data structure in the backend block storage, and persisting their clustered data through a block manager, usually a file system. In general, a file system is expected to not only provide file/directory abstraction to organize data but also retain the key benefits of LSM-trees, namely, sequential and aggregated I/O patterns on the physical device. Unfortunately, our in-depth experimental analysis reveals that some of these benefits of LSM-trees can be completely negated by the underlying file level indexes from the perspectives of both data layout and I/O processing. As a result, the write performance of LSM-trees is kept at a level far below that promised by the sequential bandwidth offered by the storage devices. In this paper, we address this problem and propose LDS, an LSM-tree Direct Storage system that manages the storage space based on the LSM-tree objects and provides simplified consistency control by leveraging the copy-on-write nature of the LSM-tree structure, to fully reap the benefits of LSM-trees. Running LevelDB, a popular LSM-tree based key-value store, on LDS as a baseline, comparing that to LevelDB running on three representative file systems (ext4, f2fs, btrfs) with HDDs and SSDs, respectively, we evaluate and study the performance potentials of LSM-trees. Evaluation results show that the write throughputs of LevelDB can be improved by from 1.8× to 3× on HDDs, and from 1.3× to 2.5× on SSDs, by employing the LSM-tree friendly data layout of LDS.

Key-value (KV) stores based on multi-stage structures are widely deployed in the cloud to ingest massive amounts of easily searchable user data. However, current KV storage systems inevitably sacrifice at least one of the performance objectives, such as write, read, space efficiency etc., for the optimization of others. To understand the root cause of and ultimately remove such performance disparities among the representative existing KV stores, we analyze their enabling mechanisms and classify them into two models of data structures facilitating KV operations, namely, the multi-stage tree (MS-tree) as represented by LevelDB, and the multi-stage forest (MS-forest) as typified by the size-tiered compaction in Cassandra. We then build a KV store on a novel split MS-forest structure, called SifrDB, that achieves the lowest write amplification across all workload patterns and minimizes space reservation for the compaction. In addition, we design a highly efficient parallel search algorithm that fully exploits the access parallelism of modern flash-based storage devices to substantially boost the read performance. Evaluation results show that under both micro and YCSB benchmarks, SifrDB outperforms its closest competitors, i.e., the popular MS-forest implementations, making it a highly desirable choice for the modern large-dataset-driven KV stores.

Key-value stores are increasingly adopting LSM-trees as their enabling data structure in the backend storage, and persisting their clustered data through a file system. A file system is expected to not only provide file/directory abstraction to organize data but also retain the key benefits of LSM-trees, namely, sequential and aggregated I/O patterns on the physical device. Unfortunately, our in-depth experimental analysis reveals that some of these benefits of LSM-trees can be completely negated by the underlying file level indexes from the perspectives of both data layout and I/O processing. As a result, the write performance of LSM-trees is kept at a level far below that promised by the sequential bandwidth offered by the storage devices. In this paper, we address this problem and propose LDS, an LSM-tree based Direct Storage system that manages the storage space and provides simplified consistency control by exploiting the copy-on-write nature of the LSM-tree structure, so as to fully reap the benefits of LSM-trees.