Federated learning (FL) allows multiple devices to collaboratively train models while preserving data privacy. Recently, personalized federated learning (pFL) has attracted significant attentions, due to its ability to effectively address the issue of statistical heterogeneity in FL. However, in heterogeneous environments, local feature extractors often produce data-specific drift, causing that clients are hard to balance local personalization with effective global collaboration. To address this problem, we propose a pFL method called FedAPR, which allows each client to learn global information while preserving personalized information by utilizing additional representations locally. To evaluate the effectiveness of our method, we simulate various heterogeneous scenarios across multiple benchmark datasets, and conduct extensive comparisons with nine state-of-the-art methods. The experiment results show that our method achieves the best performance among the tested methods.

Traditional numerical prediction of multiple environmental parameters in marine systems relies on complex physical numerical simulations. In recent years, the emergence of deep learning in marine environmental forecasting has challenged conventional physics-based approaches. Previous deep learning prediction models typically employ a single architecture to forecast multiple marine environmental indicators simultaneously, assuming homogeneous data distributions while neglecting two critical issues: 1) temporal inconsistencies in data collection timestamps across variables, and 2) distributional shifts caused by extreme weather events. Additionally, single-model frameworks suffer from prediction lag and associated temporal errors. To address these limitations, this study proposes DA-HAM, a novel hybrid model for marine environmental forecasting. The model implements data inversion tailored to individual marine variables to resolve timestamp misalignment in multi-source data collection, enabling variable-centric learning of intrinsic inter-variable dependencies. A distribution-aware attention mechanism dynamically adjusts attention scoring based on global data distribution patterns learned by the model, thereby compensating for over-unified distribution assumptions induced by normalization. Concurrently, a linear component captures cross-variable dependencies and disentangles future seasonal trends from general trend patterns. Final predictions are generated through adaptive integration of these components via learnable weighting factors. Experimental results demonstrate that DA-HAM achieves significant improvements in accuracy, stability , and trend fidelity compared to state-of-the-art Transformer-based models when processing multi-indicator datasets from designated marine regions. Notably, it exhibits enhanced robustness against data fluctuations induced by complex climatic variations and superior performance in long-term forecasting. These findings not only validate DA-HAM's potential in multi-indicator marine environmental prediction but also establish a methodological foundation for future research in marine multivariate systems.

Personalized federated learning (PFL) has received a lot of attention, owing to its significant advantages in addressing the statistical heterogeneity problem in federated learning (FL). Existing PFL methods typically partition model parameters by layers into two parts: shared parameters, which participate in global collaboration for learning shared knowledge among clients, and personalized parameters, which are retained locally to facilitate local personalization. However, during local training, parameters inevitably absorb both personalized and shared knowledge, preventing the shared and personalized parameters from effectively fulfilling their intended roles, weakening the effectiveness of global collaboration and local personalization. To address this issue, we propose a new PFL method called FedECP. FedECP stores global and personalized knowledge in separate models, preventing the interference and achieving a clearer separation of knowledge. Furthermore, we optimize the model learning strategy at both the feature representation and model parameter levels so that shared parameters learn shared knowledge, and the personalized parameters learn client-specific personalized knowledge. We conduct extensive experiments on four benchmark datasets, comparing FedECP with twelve state-of-the-art methods. The results demonstrate that FedECP performs well in various heterogeneous scenarios.

To address the challenges of traditional marine meteorological prediction methods, which struggle to effectively capture intervariable correlations in multivariate time series data and suffer from insufficient prediction accuracy, this article proposes a multivariate short-term marine meteorological prediction model. First, an intelligent marine prediction fusion architecture is constructed, which is well-suited to artificial intelligence (AI) technologies. This architecture optimizes the process of marine meteorological data collection, processing, and analysis, providing a flexible and efficient infrastructure for short-term marine prediction. Second, an influence-based importance attention mechanism for meteorological variables is designed. By exploiting the differences in interactions among meteorological variables, it selects significant attention heads for computation, effectively reducing the model’s computational complexity and enhancing its response speed. Finally, a multivariate dimension prediction method for marine meteorology is proposed. By independently processing the time series of each variable, it enhances the capability to capture interactions among meteorological variables, thus improving the model’s understanding of and predictions for dynamic changes in marine meteorology. The experimental results show that the model can fully capture and analyze the complex relationship between variables in a multivariable marine meteorological environment, effectively improve the accuracy and efficiency of the prediction, and verify its application potential in marine meteorological prediction.

Process-in-Memory (PIM) based accelerator becomes one of the best solutions for the execution of convolution neural networks (CNN). Resistive random access memory (ReRAM) is a classic type of non-volatile random-access memory, which is very suitable for implementing PIM architectures. However, existing ReRAM-based accelerators mainly consider to improve the calculation efficiency, but ignore the fact that the digital-analog signal conversion process spends a lot of energy and executing time. In this paper, we propose a novel ReRAM-based accelerator named Receptive-Field and Switch-Matrices based CNN Accelerator (RFSM). In RFSM, we first propose a receptive-field based convolution strategy to analyze the data relationships, and then gives a dynamic and configurable crossbar combination method to reduce the digital-analog conversion operations. The evaluation result shows that, compared to existing works, RFSM gains up to 6.7x higher speedup and 7.1x lower energy consumption.

Erasure coding is a storage-efficient means to guarantee data reliability in today's commodity storage systems, yet its repair performance is seriously hindered by the substantial repair traffic. Repair in clustered storage systems is even complicated because of the scarcity of the cross-cluster bandwidth. We present${\sf ClusterSR}$, a cluster-aware scattered repair approach.${\sf ClusterSR}$minimizes the cross-cluster repair traffic by carefully choosing the clusters for reading and repairing chunks. It further balances the cross-cluster repair traffic by scheduling the repair of multiple chunks. Large-scale simulation and Alibaba Cloud ECS experiments show that${\sf ClusterSR}$can reduce 5.6-52.7 percent of the cross-cluster repair traffic and improve 14.4–68.8 percent of the repair throughput.

Intrusion detection system (IDS) is an active defense mechanism implemented by the Internet of Things (IoT), which can identify the intrusion behavior and initiate alarms. However, there are concerns regarding the sustainability and feasibility to existing schemes when facing the increasing of threats in IoT. In particular, these concerns in terms of the increasing levels of adaptive performance and the insufficient levels of detection accuracy. In this paper, we present a novel deep learning method to address the aforementioned concerns. We detail the proposed convolution neural network model based on the developed feature fusion mechanism. Furthermore, we also propose a Symmetric logarithmic loss function based on categorical cross entropy. In addition, the proposed detection framework has been applied to GPU-enabled TensorFlow, and evaluated using the benchmark of NSL-KDD datasets. Extensive experimental results indicate that the developed model outperforms traditional approaches and has great potential to be applied for attacks detection in IoTs.

Quantum computing has been gradually developed from a theory to practice in recent years. The desire for more powerful computational capability keeps promoting the scaling up of quantum computers. For quantum machines with large scales, limited coherence time and bloated instruction bandwidth may obstruct the continuous scaling up. In this paper, we propose a new quantum computing architecture named QuPAA, which leverages multiple layers of arbitrary waveform generator (AWG) units to exploit the parallelism among quantum operations. QuPAA provides a series of mechanisms, including parallelism exploitation, microcode streaming, and a quantum flexible instruction set (QuFIS). These mechanisms assist QuPAA to generate instructions adaptively and reduce the requirement for coherence time and instruction bandwidth. The evaluation results show that, compared to the baseline quantum computer with a single AWG unit, QuPAA reduces 25.9% to 97.4% coherence time requirement, and saves 26.9% to 79.1 % instruction bandwidth. The improvement effectively breaks the limitations and provides strong support for the extension of the scale for quantum computers.

Erasure coding is a storage-efficient means to guarantee data reliability in today's commodity storage systems, yet its repair performance is seriously hindered by the substantial repair traffic. Repair in clustered storage systems is even complicated because of the scarcity of the cross-cluster bandwidth. We present ClusterSR, a cluster-aware scattered repair approach. ClusterSR minimizes the cross-cluster repair traffic by carefully choosing the clusters for reading and repairing chunks. It further balances the cross-cluster repair traffic by scheduling the repair of multiple chunks. Large-scale simulation and Alibaba Cloud ECS experiments show that ClusterSR can reduce 6.7-52.7% of the cross-cluster repair traffic and improve 14.1-68.8% of the repair throughput.

Erasure codes are widely used in cloud storage systems, such as in Google File System and Windows Azure. However, most of existing erasure codes focus on homogeneous storage device, but ignore that heterogeneous devices are in majority in cloud storage system. In this paper, we propose a new erasure code framework termed Device Placement Aware Framework (DPAF), to integrate existing erasure codes to generate DPAF-Codes, in order to gain good performance on heterogeneous storage devices. The key insight is to detect the device performance to generate a series of coefficients, and use these coefficients to choose proper devices to construct DPAF-Codes. We utilize simulated annealing algorithm to optimize the selection process, in order to maintain the balance among devices by considering the coefficients. The experiment results show that, our proposed DPAF-Codes gain up to 70.3%, 48.7%, and 48.5% improvements on single failure recovery, normal read, and degraded read speed, compared to RS code and LRC code with different configurations.

As reliability requirements are increasingly important in both clusters and data centers, RAID-6, which can tolerate any two concurrent disk failures, has been widely used in modern storage systems. However, most existing RAID-6 codes cannot provide satisfied performance on both degraded reads and partial stripe writes, which are important performance metrics in storage systems. To address these problems, in this paper we propose a new RAID-6 MDS erasure code called Short Code, in order to optimize the degraded reads and partial stripe writes. In Short Code, we propose a novel short horizontal parity chain, which assures that all disks contribute to degraded reads while the continuous data elements are more likely to share the same horizontal chain for optimizing degraded reads. On the other hand, Short Code distributes all diagonal parities among disks for optimizing partial stripe writes. The proposed Short Code not only owns the optimal storage efficiency, but also keeps the optimal complexity for both encoding/decoding computations and update operations. The experiments show that Short Code achieves much higher speed on degraded reads and partial stripe writes than other popular RAID-6 codes, and provide acceptable performance on single disk failure recoveries and normal reads. Specifically, compared to RDP code, Short Code provides 6.1 to 26.3 percent higher speed on degraded reads and 36.2 to 80.3 percent higher speed on partial stripe writes with the same number of disks.

Erasure coding provides an effective means for storage systems to protect against disk failures with low redundancy. One important objective for erasure-coded storage systems is to speed up single disk failure recovery. Previous approaches reduce the amount of read data for recovery by reading only a small subset of data. However, they often incur high disk seeks, which may negate the resulting recovery performance. We proposeSIOR, a seek-efficient I/O recovery algorithm for improving the performance of single disk failure recovery. SIOR carefully balances the trade-off between the amount of read data and the number of disk seeks by considering the data layout at the multi-stripe level. It then greedily determines the data to read for recovery using Tabu search. Experiments show that SIOR achieves similar performance to the brute-force enumeration method while keeping high search efficiency. Also, SIOR reduces$31.8\sim 65.1$percent of disk seeks during recovery and provides up to 150.0 percent recovery speed improvement, when compared to a state-of-the-art greedy recovery approach.

The fast growing of data scale encourages the wide employment of data disks with large storage capacity. However, a mass of data disks' equipment will in turn increase the probability of data loss or damage, because of the appearance of various kinds of disk failures. To ensure the intactness of the hosted data, modern storage systems usually adopt erasure codes, which can recover the lost data by pre-storing a small amount of redundant information. As the most common case among all the recovery mechanisms, the single disk failure recovery has been receiving intensive attentions for the past few years. However, most of existing works still take the stripe-level recovery as their only consideration, and a considerable performance improvement on single failure disk reconstruction in the stack-level (i.e., a group of rotated stripes) is missed. To seize this potential improvement, in this paper we systematically study the problem of single failure recovery in the stack-level. We first propose two recovery mechanism based on greedy algorithm to seek for the near-optimal solution (BP-Scheme and STP-Scheme) for any erasure array code in stack level, and further design a rotated recovery algorithm (RR-Algorithm) to eliminate the size of required memory. Through a rigorous statistic analysis and intensive evaluation on a real system, the results show that BP-Scheme gains 3.4 to 38.9 percent (the average is 21.2 percent) higher recovery speed than Khan's Scheme and 3.4 to 34.8 percent (the average is 19.1 percent) higher recovery speed than Luo's U-Scheme, while STP-Scheme owns 3.4 to 46.9 percent (the average is 25.15 percent) and 3.4 to 41.1 percent (the average is 22.3 percent) higher recovery speed than Khan's Scheme and Luo's U-Scheme, respectively.

The increasing expansion of data scale leads to the widespread deployment of storage systems with larger capacity and further induces the climbing probability of data loss or damage. The Maximum Distance Separable (MDS) code in RAID-6, which tolerates the concurrent failures of any two disks with minimal storage requirement, is one of the best candidates to enhance the data reliability. However, most of the existing works in this literature are more inclined to be specialized and cannot provide a satisfied performance under an all-round evaluation. Aiming at this problem, we propose an all-round MDS code named Horizontal-Vertical Code (HV Code) by taking advantage of horizontal parity and vertical parity. HV Code achieves the perfect I/O balancing and optimizes the operation of partial stripe writes, while preserving the optimal encoding/decoding/update efficiency. Moreover, it owns a shorter parity chain which grants it a more efficient recovery for single disk failure. HV Code also behaves well on degraded read operation and accelerates the reconstruction of double disk failures by executing four recovery chains in parallel. The performance evaluation demonstrates that HV Code well balances the I/O distribution. HV Code also eliminates up to 32.2 percent I/O operations for partial stripe writes in read-modify-write mode, and reduces up to 28.9 percent I/O operations for partial stripe writes in reconstruct-write mode. Moreover, HV Code reduces 5.4~39.8 percent I/O operations per element for the single disk reconstruction, decreases 8.3~39.0 percent I/O operations for degraded read operations, and shortens 47.4~59.7 percent recovery time for double disk recovery.

Erasure codes tolerate disk failures by pre-storing a low degree of data redundancy, and have been commonly adopted in current storage systems. However, the attached requirement on data consistency exaggerates partial stripe write operations and thus seriously downgrades system performance. Previous works to optimize partial stripe writes are relatively limited, and a general mechanism is still absent. In this paper, we propose a Parity-Switched Data Placement (PDP) to optimize partial stripe writes for any XOR-coded storage system. PDP first reduces the write operations by arranging continuous data elements to join a common parity element's generation. To achieve a deeper optimization, PDP further explores the generation orders of parity elements and makes any two continuous data elements associate with a common parity element. Intensive evaluations show that for tested erasure codes, PDP reduces up to 31.9 percent of write operations and further increases the write speed by up to 59.8 percent when compared with two state-of-the-art data placement methods.

With the reliability requirements increasingly important, erasure codes have been widely used in today's cloud storage systems because they achieve both high reliability and low storage overhead. However, the performance for most existing erasure codes can be further improved on both normal reads to user's data without device failures and degraded reads under device failures, which are crucial in cloud storage systems. In this paper, we propose an erasure coding framework named EC-FRM to integrate existing codes in order to improve the read performance. The constructed code over EC-FRM named EC-FRM-Code, which keeps most of wonderful properties of the integrated code and achieves good performance on both normal reads and degraded reads. We transform Reed-Solomon code and LRC code to EC-FRM-RS and EC-FRM-LRC respectively, and then conduct a series of experiments to evaluate their read performance. The results show that EC-FRM-RS code gains 19.2% to 33.9% higher normal read speed and 9.1% to 9.9% higher degraded read speed than standard Reed-Solomon code, while EC-FRM-LRC code owns 23.5% to 46.9% higher normal read speed and 3.3% to 12.8% higher degraded read speed than standard LRC code.

With the reliability requirement increasingly important, RAID-6, which can tolerate any two concurrent disk failures, has been widely used in various storage systems. One class of typical RAID-6 implementations is to use Maximum Distance Separable (MDS) erasure codes. However, most existing RAID-6 MDS codes suffer from unbalanced I/O or high I/O cost, and cannot provide satisfied read performance on both normal mode and degraded mode. All these metrics are important in modern storage systems. In this paper, we propose a new RAID-6 MDS code termed D-Code to address these problems. D-Code uses a new kind of horizontal parities to increase the possibility of continuous data elements sharing the common parities in order to provide low I/O cost and good degraded read performance, while uses deployment parities to assure all parities can be evenly distributed in the last two rows in order to achieve good load balancing and good normal read performance. Our evaluations and experiments show that D-Code not only provides good load balancing and low I/O cost under different workloads, but also achieves good performance on both normal reads and degraded reads. E.g., D-Code achieves up to 21.3% and 13.5% higher read speed than RDP code and H-Code in normal mode, while gains up to 26.0% higher read speed than X-Code in degraded mode.

Erasure coding provides an effective means for storage systems to protect against disk failures with low redundancy. One important objective for erasure-coded storage systems is to speed up single disk failure recovery. Previous studies reduce the amount of data read for recovery by reading only a small subset of data, but their approaches often incur high disk seeks, which may negate the resulting recovery performance. We propose SIOR, a seek-efficient I/O recovery algorithm for single disk failures. SIOR carefully balances the trade-off between the amount of data read and the number of disk seeks by considering the data layout at the multi-stripe level. It then greedily determines the data to read for recovery using Tabu search. Experiments show that SIOR achieves similar performance to the brute-force enumeration method while keeping high search efficiency. Also, SIOR reduces 31.8%~65.1% of disk seeks during recovery and provides up to 186.8% recovery speed improvement, when compared to a state-of-the-art greedy recovery approach.

The fast growing of data scale encourages the wide employment of data disks with large storage capacity. However, a mass of data disks' equipment will in turn increase the probability of data loss or damage, because of the appearance of various kinds of disk failures. To ensure the intactness of the hosted data, modern storage systems usually adopt erasure codes, which can recover the lost data by pre-storing a small amount of redundant information. As the most common case among all the recovery mechanisms, the single disk failure recovery has been receiving intensive attentions for the past few years. However, most of existing works in this literature still take the stripe-level recovery as their only consideration, and a considerable performance improvement on single failure disk reconstruction in the stack-level (i.e., a group of rotated stripes) is missed. To seize this potential improvement, in this paper we systematically study the problem of single failure recovery in the stack-level. We first propose our recovery mechanism based on greedy algorithm to seek for the near-optimal solution (BP-Scheme) for any erasure array code in stack level, and further design a rotated recovery algorithm (RR-Algorithm) to eliminate the size of required memory. Through a rigorous statistic analysis and intensive evaluation on a real system, the results show that BP-Scheme gains at most 38.9% higher recovery speed than Khan's Scheme, and owns up to 34.8% higher recovery speed than Luo's U-Scheme.

With the rapid development of cloud storage, data security in storage receives great attention and becomes the top concern to block the spread development of cloud service. In this paper, we systematically study the security researches in the storage systems. We first present the design criteria that are used to evaluate a secure storage system and summarize the widely adopted key technologies. Then, we further investigate the security research in cloud storage and conclude the new challenges in the cloud environment. Finally, we give a detailed comparison among the selected secure storage systems and draw the relationship between the key technologies and the design criteria.