Hard Disk Drive (HDD) failures are a persistent and costly problem in data centers, making the accurate prediction of Remaining Useful Life (RUL) essential for mitigating downtime and data loss. While machine learning models, particularly LSTMs, have been widely applied to this task using Self-Monitoring, Analysis, and Reporting Technology (SMART) data, their effectiveness is largely confined to short-term predictions (e.g., 30 days), lacking the ability to accurately forecast RUL over longer horizons, such as one year. To address these limitations, this paper proposes a novel methodology. First, we create a Binary Classification Model that discriminates input data as healthy or faulty. Then, we use its output to generate failure likelihood features to append to the original dataset. We evaluate our approach on a real-world dataset from Backblaze, comparing its performance against baseline models to demonstrate that incorporating the auxiliary features improves the MSE score of the RUL predictions up to 38%.

Differentially private selection mechanisms offer strong privacy guarantees for queries aiming to identify the top-scoring element$r$from a finite set$\mathfrak{R}$, based on a dataset-dependent utility function. While selection queries are fundamental in data science, few mechanisms effectively ensure their privacy. Furthermore, most approaches rely on global sensitivity to achieve differential privacy (DP), which can introduce excessive noise and impair downstream inferences. To address this limitation, we propose the Smooth Noisy Max (SNM) mechanism, which leverages smooth sensitivity to yield provably tighter (upper bounds on) expected errors compared to global sensitivity-based methods. Empirical results demonstrate that SNM is more accurate than state-of-the-art differentially private selection methods in three applications: percentile selection, greedy decision trees, and random forests.

Many complex natural and technological systems are commonly modeled as count-weighted graphs, where nodes represent entities, edges model relationships between them, and edge weights define some counting statistics associated with each relationship. As graph data usually contain sensitive information about entities, preserving privacy when releasing this type of data becomes an important issue. In this context, differential privacy (DP) has become the de facto standard for data release under strong privacy guarantees. When dealing with DP for weighted graphs, most state-of-the-art works assume that the graph topology is known. However, in several real-world applications, the privacy of the graph topology also needs to be ensured. In this paper, we aim to bridge the gap between DP and count-weighted graph data release, considering both graph structure and edge weights as private information. We first adapt the weighted graph DP definition to take into account the privacy of the graph structure. We then develop two novel approaches to privately releasing count-weighted graphs under the notions of global and local DP. We also leverage the post-processing property of DP to improve the accuracy of the proposed techniques considering graph domain constraints. Experiments using real-world graph data demonstrate the superiority of our approaches in terms of utility over existing techniques, enabling subsequent computation of a variety of statistics on the released graph with high utility, in some cases comparable to the non-private results.

Being able to estimate a test execution time is of fundamental importance when you need to prioritize tests.Furthermore, it is also important that an estimation algorithm do not underestimate the execution time, since time can be a hard constraint in many problems.If a test take longer than expected, some test that is planned to be executed in the future may have to be cancelled.Under such scenario, in this paper, we developed two simple variants of the Random Forest regression algorithm to predict test execution times in storage diagnostics tests.The proposed methods are compared to a baseline time estimation method (already available in a commercial product) and other machine learning based models.On the basis of our experiments we can state that the proposed variants achieved promising results when considering an asymmetric error metric.

Identifying Customer Induced Damage (CID) is a key part in warranty programs of electronics manufacturers. CID is defined as any damage in the unit performed by an unauthorized person including the customer. In such cases, damaged units are not covered by warranty. An important aspect of CID inspection activities is that, in most industries, the task is performed manually. Since such task demands high attention to details, human mistakes occur very often. For such reasons, CID detection can be considered as a good candidate to be handled by automatic detection methods with computer vision tools. In this work, we evaluate modern computer vision methods based on deep neural networks (SwinSoft Teacher and Mask-RCNN as prediction networks with swin and resnet backbones) for automatic CID detection in motherboard images. All images were originated from private company repair centers around the globe. We highlight the following results for Average Precision (AP) and Average Recall (AR):$AP{@}0.5 =\mathbf{80.2}$and$AR^{m}=\mathbf{57.9}$, for Mask-RCNN with Swin-S backbone, where the variant$m$means medium, and$AP{@}0.5 =\mathbf{74.2}$and$AR^{m}=\mathbf{45.4}$, for Mask-RCNN Swin-T backbone. Our results demonstrate that Swin-based methods had the best overall results and exhibit interesting characteristics for our application.

Predicting failures in Hard Disk Drives (HDD) is a major challenge that has been faced by both industry and academy in recent years. Being able to predict failure events may incur in avoiding data losses and also improve service availability. Among all failure prediction strategies, the health degree prediction is one of the most popular. The task of health degree prediction consists of, given a finite set of health states that are related to the degradation of the equipment, estimate which state reflects the actual degradation of the equipment. This problem is usually modeled as a classification task. Although many health degree prediction methods have been proposed, some practical details regarding this prediction task have been neglected in previous works. In this work we tackle two of these aspects: the ordinal nature of the problem and the different costs associated with miss-classifications. The problem can be considered as ordinal since classifying a HDD in a health level that is far from is true health level shall be more penalized than classifying in a near health level, thus a classical classification framework is not recommended. The different costs associated with mis-classifications are related to the fact that early predictions are preferred than late prediction since the later can result in failures. Such aspects are considered in a framework based on Deep Recurrent Neural Networks (DRNN). The choice of DRNN is given its remarkable performances in many applications including HDDs failure prediction. The resulting methods outperformed state-of-the-art approaches in a metric that consider the new aspects that motivated our proposal.

Nowadays, predicting failures in Hard Disk Drives (HDD) is of key importance for storage service providers and end users. Being able to detect in advance that a disk is going to fail may enable maintenance actions that can avoid severe data losses. For that reason, many researchers had devoted attention to this research topic. Recently, several authors have reported promising results by using attributes collected by the SMART (Self-Monitoring, Analysis and Reporting Technology) system along with machine learning methods. Although the best results were obtained by supervised machine learning methods, it is important to notice that data from degraded HDDs is scarce. Hence, anomaly detection methods arise a promising solution. Among such methods, recent works reported that reconstruction based anomaly detection algorithms had the best performance on HDDs fault detection. In line with such results, in this paper we aim to further investigate the performance of such methods. We conducted tests with classical PCA based methods and neural autoencoder based methods. In addition to testing with the popular reconstruction based autoencoder method we also evaluated a method that analyzes the distribution of the latent space. Additionally we propose a simple formulation to combine both methods. On the basis of our experiments, we verified that autoencoder based methods had the best performances according to the two evaluation metrics. Among such methods, the combination approach had the best overall performance.

Summary The use of distributed key‐value stores (KVS) has experienced fast adoption by various applications in recent years due to key advantages such as hypertext transfer protocol‐based RESTful application programming interface, high availability and elasticity. Due to great scalability characteristics, KVS systems commonly use consistent hashing as data placement mechanism. Although KVS systems offer many advantages, they were not designed to dynamically adapt to changing workloads which often include data access skew. Furthermore, the underlying physical storage nodes may be heterogeneous and do not expose their performance capabilities to higher level data placement layers. In this paper, we address those issues and propose an essential step toward a dynamic autonomous solution by leveraging deep reinforcement learning. We design a self‐learning approach that incrementally changes the data placement, improving the load balancing. Our approach is dynamic in the sense that is capable of avoiding hot spots, that is, overloaded storage nodes when facing different workloads. Also, we design our solution to be pluggable. It assumes no previous knowledge of the storage nodes capabilities, thus different KVS deployments may make use of it. Our experiments show that our method performs well on changing workloads including data access skew aspects. We demonstrate the effectiveness of our approach through experiments in a distributed KVS deployment.

Differential privacy is the state-of-the-art formal definition for data release under strong privacy guarantees. A variety of mechanisms have been proposed in the literature for releasing the noisy output of numeric queries (e.g., using the Laplace mechanism), based on the notions of global sensitivity and local sensitivity. However, although there has been some work on generic mechanisms for releasing the output of non-numeric queries using global sensitivity (e.g., the Exponential mechanism), the literature lacks generic mechanisms for releasing the output of non-numeric queries using local sensitivity to reduce the noise in the query output. In this work, we remedy this shortcoming and present the local dampening mechanism. We adapt the notion of local sensitivity for the non-numeric setting and leverage it to design a generic non-numeric mechanism. We illustrate the effectiveness of the local dampening mechanism by applying it to two diverse problems: (i) Influential node analysis. Given an influence metric, we release the top-k most influential nodes while preserving the privacy of the relationship between nodes in the network; (ii) Decision tree induction. We provide a private adaptation to the ID3 algorithm to build decision trees from a given tabular dataset. Experimental results show that we could reduce the use of privacy budget by 3 to 4 orders of magnitude for Influential node analysis and increase accuracy up to 12% for Decision tree induction when compared to global sensitivity based approaches.

Code Smell can be defined as any feature in the source code of a software that may indicate possible problems. In database languages, the term Bad Smell has been used as a generalization of Code Smell, once some features that are not directly related to code also can indicate problems, such as, for instance, the inappropriate type of an index structure or a SQL query written inefficiently. Bearing in mind the recurrence of different Bad Smell, they were catalogued. Along with these catalogs, tools were developed to automatically identify Bad Smell occurrences in a given code. With the help of these tools, it has become possible to perform quick and effective analysis. In this context, this paper proposes an exploratory study about Bad Smell in PL/SQL codes, from free software projects, published on GitHub. We analyzed 20 open-source PL/SQL projects and empirically study the prevalence of bad smells. Our results showed that some smells occur together. Besides, some smells are more frequent than others. Based on this principle, this paper has the potential to aid professionals from the databases area to avoid future problems during the development of a PL/SQL project.

The ability to predict failures in Hard Disk Drives (HDD) is a major objective of HDD manufacturers since avoiding unexpected failures may prevent data loss. As a consequence, failure prediction in HDDs became a topic that attracted much attention in recent years. Nowadays, most HDDs are equipped with a threshold-based monitoring system named Self-Monitoring, Analysis and Reporting Technology (SMART). The system collects several performance parameters and detects anomalies that may indicate incipient failures. Although the SMART system is very popular, it achieves failure detection rates of 3% to 10%. Moreover, SMART works as an incipient failure detection method and does not provide an estimate of the remaining life of the HDD. In this paper, we propose a failure prediction method using SMART attributes and a Bayesian Network. The proposed method, named Bayesian network based Method for Failure prediction in HDDs (BNFH) uses a subset of the SMART attributes and a set of SMART trend related attributes to provide remaining life estimates of HDDs. To demonstrate practical usefulness, this method was applied to a dataset consisting of 49,056 hard drives from Backblaze's data centers.

Nowadays Hard Disk Drives (HDDs) are essential storage devices in most large-scale storage systems. As a consequence, HDD failures have severe effects that may range from data loss to service unavailability. Considering such scenario, academy and industry have driven its attention to HDDs failure prognostics solutions. In this work, we evaluate two of the most common deep learning architecture in the task of HDD failure prediction. Our tests were conducted on real-world datasets and the proposals were compared to a recurrent neural network. The results of this study showed that deep learning models are a valid alternative to solve this problem since they achieved good results and a significant amount of data is available.

Summary Cloud computing is a trend of technology aimed at providing on‐demand services with payment based on usage. In order to improve the use of resources, cloud providers adopt multi‐tenant approaches, reducing the operation cost of services. Moreover, tenants have irregular workload patterns, which impacts in guarantees of quality of service, mainly due to interference among tenants. This paper proposes PredRep, a predictive approach to characterize the cloud database system workload and automatically provide or reduce resources by replication techniques. In order to evaluate PredRep, some experiments that measure the quality of service and elasticity are presented. Our experiment results confirm that PredRep reduces cost and SLA violations.

Differential privacy is a model which gives strong privacy guarantees. It was designed to make difficult to distinguish individuals' records on statistical databases while maximizing data utility. Differential privacy approaches usually assume that database records are sampled independently, i.e., each record of this database is independent of the rest. However, this assumption is not always true in the context of real-world applications. In this paper we propose DiPCoDing, a novel approach to calculate the correlation between records in statistical databases using clusterization. For this matter, we have considered Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Gaussian Mixture Model (GMM). Our method aims to group similar records, which are more likely to be correlated, to reduce the sensitivity of differential privacy and consequently the amount of noise added to the query answer, increasing data utility while providing privacy for correlated data. The experimental results of our approach showed that relative errors and noisy answers are significantly lower than those from existing works.

As the amount of collected social network information in RDF format grows, the development of solutions for the privacy of individuals, their attributes and relationships with others becomes an important subject of study. However, data privacy solutions are not well suitable for this specific type of data, mainly because they usually do not consider relationships between individuals, which are crucial to semantic data and social networks. Differential privacy is one of the most suitable techniques for statistical queries and, although it has been extensively studied in many papers, there is still much research to be done in this context. This paper presents two main contributions for privacy preserving statistic queries containing sensitive information about relationships between individuals. The first one is a complete approach to applying ϵ-differential privacy for RDF data and the second one presents an index-like data structure to efficiently compute parameters for the differential privacy mechanism: the query's actual value and data sensitivity for the given query. We conclude by evaluating our contributions over three real social network datasets presenting utility analysis for different values of ϵ. We also show the performance benefit of our index-like data structure for sensitivity calculation.

Hard Disk Drives (HDD) failure prediction is a challenging topic that has attracted much attention in recent years. Predicting failures in HDD may avoid losing data thus improving data reliability. Previous works on failure prediction are based on parametric approaches that model healthy drives with a Gaussian distribution. Although they achieved good results, the Gaussianity assumption may not hold true. The following work proposes a method for fault detection in HDD based on a Gaussian Mixture Model. A self-monitoring, analysis, and reporting technology dataset is used to evaluate the proposed method. Results show that the method outperforms previous works in both fault detection and time before failure.

Cloud computing is a successful, emerging paradigm that supports on-demand services with pay-as-you-go model. With the exponential growth of data, NoSQL databases have been used to manage data in the cloud. In these newly emerging settings, mechanisms to guarantee Quality of Service heavily relies on performance predictability, i.e., the ability to estimate the impact of concurrent query execution on the performance of individual queries in a continuously evolving workload. This paper presents a performance modeling approach for NoSQL databases in terms of performance metrics which is capable of capturing the non-linear effects caused by concurrency and distribution aspects. Experimental results confirm that our performance modeling can accurately predict mean response time measurements under a wide range of workload configurations.

Cloud computing is a recent trend of technology that aims to provide unlimited, on-demand, elastic computing and data storage resources. In this context, cloud services decrease the need for local data storage and the infrastructure costs. However, hosting confidential data at a cloud storage service requires the transfer of control of the data to a semi-trusted external provider. Therefore, data confidentiality is the top concern from the cloud issues list. Recently, three main approaches have been introduced to ensure data confidentiality in cloud services: data encryption; combination of encryption and fragmentation; and fragmentation. Besides, other strategies use a mix of these three main approaches. In this paper, we present i-OBJECT, a new approach to preserve data confidentiality in cloud environments. The proposed mechanism uses information decomposition to split data into unrecognizable parts and store them in different cloud service providers. Experimental results show the potential efficiency of i-OBJECT.

In this paper we present an algorithm for optimal processing of time-dependent sequenced route queries in road networks, i.e., given a road network where the travel time over an edge is time-dependent and a given ordered list of categories of interest, we find the fastest route between an origin and destination that passes through a sequence of points of interest belonging to each of the specified categories of interest. Our approach uses the A* search paradigm equipped with an admissible heuristic function, thus guaranteed to yield the optimal solution, along with a pruning scheme for further reducing the search space. Our experiments using a real data set have shown our proposed solution to be up to two orders of magnitude faster than a previous solution extended to handle time-dependency.

We consider the problem of finding the k nearest points of interest from a given location in time-dependent road networks, i.e., One where travel time along each edge is a function of the departure time, and where the operating times of the points of interest are also taken into consideration. More specifically, we address the following query: find the k points of interest in which a user can start to be served in the minimum amount of time, accounting for both the travel time to the point of interest and the waiting time, if it is closed. Previous works have proposed solutions to answer kNN queries considering the time dependency of the network but not the operating times of the points of interest. We propose and discuss three solutions to this type of query which are based on the previously proposed incremental network expansion and use the A search algorithm equipped with suitable heuristic functions. We also present experimental results comparing the number of disk access required in each solution with respect to a few different parameters.

Dynamic resource provisioning poses a major challenge for infrastructure providers because it is necessary to both forecast resource consumption and react to recent surges on demand for maintaining a tradeoff between quality of service and cost. However, approaches to workload analysis and forecast are affected due to noise in observed data, specially in forecast models. Moreover, most studies do not consider different prediction horizons may be necessary in order to take action before an SLA violation occurs. This paper presents an approach based in the scale-space theory to assist the dynamic resource provisioning. This theory is capable of eliminating the presence of irrelevant information from a signal that can potentially induce wrong or late decision making. In order to evaluate our approach, some experiments are presented considering both reactive and proactive strategies. The results confirm that our approach improves the workload analysis and forecast.