Search

Multiple visions of 6G networks elicit Artificial Intelligence (AI) as a central, native element. When 6G systems are deployed at a large scale, end-to-end AI-based solutions will necessarily have to encompass both the radio and the fiber-optical domain. This paper introduces the Decentralized Multi-Party, Multi-Network AI (DMMAI) framework for integrating AI into 6G networks deployed at scale. DMMAI harmonizes AI-driven controls across diverse network platforms and thus facilitates networks that autonomously configure, monitor, and repair themselves. This is particularly crucial at the network edge, where advanced applications meet heightened functionality and security demands. The radio/optical integration is vital due to the current compartmentalization of AI research within these domains, which lacks a comprehensive understanding of their interaction. Our approach explores multi-network orchestration and AI control integration, filling a critical gap in standardized frameworks for AI-driven coordination in 6G networks. The DMMAI framework is a step towards a global standard for AI in 6G, aiming to establish reference use cases, data and model management methods, and benchmarking platforms for future AI/ML solutions.

The recent breakthrough of Transformers in deep learning has drawn significant attention of the time series community due to their ability to capture long-range dependencies. However, like other deep learning models, Transformers face limitations in time series prediction, including insufficient temporal understanding, generalization challenges, and data shift issues for the domains with limited data. Additionally, addressing the issue of catastrophic forgetting, where models forget previously learned information when exposed to new data, is another critical aspect that requires attention in enhancing the robustness of Transformers for time series tasks. To address these limitations, in this paper, we pre-train the time series Transformer model on a source domain with sufficient data and fine-tune it on the target domain with limited data. We introduce the \emph{One-step fine-tuning} approach, adding some percentage of source domain data to the target domains, providing the model with diverse time series instances. We then fine-tune the pre-trained model using a gradual unfreezing technique. This helps enhance the model's performance in time series prediction for domains with limited data. Extensive experimental results on two real-world datasets show that our approach improves over the state-of-the-art baselines by 4.35% and 11.54% for indoor temperature and wind power prediction, respectively., Comment: Accepted at the Fourth Workshop of Artificial Intelligence for Time Series Analysis (AI4TS): Theory, Algorithms, and Applications, AAAI 2024, Vancouver, Canada

Data cubes are used for analyzing large data sets usually contained in data warehouses. The most popular data cube tools use graphical user interfaces (GUI) to do the data analysis. Traditionally this was fine since data analysts were not expected to be technical people. However, in the subsequent decades the data landscape changed dramatically requiring companies to employ large teams of highly technical data scientists in order to manage and use the ever increasing amount of data. These data scientists generally use tools like Python, interactive notebooks, pandas, etc. while modern data cube tools are still GUI based. This paper proposes a Python-based data cube tool called pyCube. pyCube is able to semi-automatically create data cubes for data stored in an RDBMS and manages the data cube metadata. pyCube's programmatic interface enables data scientist to query data cubes by specifying the expected metadata of the result. pyCube is experimentally evaluated on Star Schema Benchmark (SSB). The results show that pyCube vastly outperforms different implementations of SSB queries in pandas in both runtime and memory while being easier to read and write., Comment: Extended version of DOLAP2024 submission

Big time series are increasingly available from an ever wider range of IoT-enabled sensors deployed in various environments. Significant insights can be gained by mining temporal patterns from these time series. Temporal pattern mining (TPM) extends traditional pattern mining by adding event time intervals into extracted patterns, making them more expressive at the expense of increased time and space complexities. Besides frequent temporal patterns (FTPs), which occur frequently in the entire dataset, another useful type of temporal patterns are so-called rare temporal patterns (RTPs), which appear rarely but with high confidence. Mining rare temporal patterns yields additional challenges. For FTP mining, the temporal information and complex relations between events already create an exponential search space. For RTP mining, the support measure is set very low, leading to a further combinatorial explosion and potentially producing too many uninteresting patterns. Thus, there is a need for a generalized approach which can mine both frequent and rare temporal patterns. This paper presents our Generalized Temporal Pattern Mining from Time Series (GTPMfTS) approach with the following specific contributions: (1) The end-to-end GTPMfTS process taking time series as input and producing frequent/rare temporal patterns as output. (2) The efficient Generalized Temporal Pattern Mining (GTPM) algorithm mines frequent and rare temporal patterns using efficient data structures for fast retrieval of events and patterns during the mining process, and employs effective pruning techniques for significantly faster mining. (3) An approximate version of GTPM that uses mutual information, a measure of data correlation, to prune unpromising time series from the search space., Comment: arXiv admin note: text overlap with arXiv:2010.03653

Taking inspiration from linguistics, the communications theoretical community has recently shown a significant recent interest in pragmatic , or goal-oriented, communication. In this paper, we tackle the problem of pragmatic communication with multiple clients with different, and potentially conflicting, objectives. We capture the goal-oriented aspect through the metric of Value of Information (VoI), which considers the estimation of the remote process as well as the timing constraints. However, the most common definition of VoI is simply the Mean Square Error (MSE) of the whole system state, regardless of the relevance for a specific client. Our work aims to overcome this limitation by including different summary statistics, i.e., value functions of the state, for separate clients, and a diversified query process on the client side, expressed through the fact that different applications may request different functions of the process state at different times. A query-aware Deep Reinforcement Learning (DRL) solution based on statically defined VoI can outperform naive approaches by 15-20%.

The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety. Many recent studies target anomaly detection for time series data. Indeed, area of time series anomaly detection is characterized by diverse data, methods, and evaluation strategies, and comparisons in existing studies consider only part of this diversity, which makes it difficult to select the best method for a particular problem setting. To address this shortcoming, we introduce taxonomies for data, methods, and evaluation strategies, provide a comprehensive overview of unsupervised time series anomaly detection using the taxonomies, and systematically evaluate and compare state-of-the-art traditional as well as deep learning techniques. In the empirical study using nine publicly available datasets, we apply the most commonly-used performance evaluation metrics to typical methods under a fair implementation standard. Based on the structuring offered by the taxonomies, we report on empirical studies and provide guidelines, in the form of comparative tables, for choosing the methods most suitable for particular application settings. Finally, we propose research directions for this dynamic field.

Very large time series are increasingly available from an ever wider range of IoT-enabled sensors, from which significant insights can be obtained through mining temporal patterns from them. A useful type of patterns found in many real-world applications exhibits periodic occurrences, and is thus called seasonal temporal pattern (STP). Compared to regular patterns, mining seasonal temporal patterns is more challenging since traditional measures such as support and confidence do not capture the seasonality characteristics. Further, the anti-monotonicity property does not hold for STPs, and thus, resulting in an exponential search space. This paper presents our Frequent Seasonal Temporal Pattern Mining from Time Series (FreqSTPfTS) solution providing: (1) The first solution for seasonal temporal pattern mining (STPM) from time series that can mine STP at different data granularities. (2) The STPM algorithm that uses efficient data structures and two pruning techniques to reduce the search space and speed up the mining process. (3) An approximate version of STPM that uses mutual information, a measure of data correlation, to prune unpromising time series from the search space. (4) An extensive experimental evaluation showing that STPM outperforms the baseline in runtime and memory consumption, and can scale to big datasets. The approximate STPM is up to an order of magnitude faster and less memory consuming than the baseline, while maintaining high accuracy.

The wide deployment of IoT sensors has enabled the collection of very big time series across different domains, from which advanced analytics can be performed to find unknown relationships, most importantly the correlations between them. However, current approaches for correlation search on time series are limited to only a single temporal scale and simple types of relations, and cannot handle noise effectively. This paper presents the integrated SYnchronous COrrelation Search (iSYCOS) framework to find multi-scale correlations in big time series. Specifically, iSYCOS integrates top-down and bottom-up approaches into a single auto-configured framework capable of efficiently extracting complex window-based correlations from big time series using mutual information (MI). Moreover, iSYCOS includes a novel MI-based theory to identify noise in the data, and is used to perform pruning to improve iSYCOS performance. Besides, we design a distributed version of iSYCOS that can scale out in a Spark cluster to handle big time series. Our extensive experimental evaluation on synthetic and real-world datasets shows that iSYCOS can auto-configure on a given dataset to find complex multi-scale correlations. The pruning and optimisations can improve iSYCOS performance up to an order of magnitude, and the distributed iSYCOS can scale out linearly on a computing cluster., Comment: 18 pages

With the increasing use of IoT-enabled sensors, it is important to have effective methods for querying the sensors. For example, in a dense network of battery-driven temperature sensors, it is often possible to query (sample) just a subset of the sensors at any given time, since the values of the non-sampled sensors can be estimated from the sampled values. If we can divide the set of sensors into disjoint so-called representative sampling subsets that each represent the other sensors sufficiently well, we can alternate the sampling between the sampling subsets and thus, increase battery life significantly. In this paper, we formulate the problem of finding representative sampling subsets as a graph problem on a so-called sensor graph with the sensors as nodes. Our proposed solution, SubGraphSample, consists of two phases. In Phase-I, we create edges in the sensor graph based on the similarities between the time series of sensor values, analyzing six different techniques based on proven time series similarity metrics. In Phase-II, we propose two new techniques and extend four existing ones to find the maximal number of representative sampling subsets. Finally, we propose AutoSubGraphSample which auto-selects the best technique for Phase-I and Phase-II for a given dataset. Our extensive experimental evaluation shows that our approach can yield significant battery life improvements within realistic error bounds.

The widespread deployment of smartphones and location-enabled, networked in-vehicle devices renders it increasingly feasible to collect streaming trajectory data of moving objects. The continuous clustering of such data can enable a variety of real-time services, such as identifying representative paths or common moving trends among objects in real-time. However, little attention has so far been given to the quality of clusters -- for example, it is beneficial to smooth short-term fluctuations in clusters to achieve robustness to exceptional data. We propose the notion of evolutionary clustering of streaming trajectories, abbreviated ECO, that enhances streaming-trajectory clustering quality by means of temporal smoothing that prevents abrupt changes in clusters across successive timestamps. Employing the notions of snapshot and historical trajectory costs, we formalize ECO and then formulate ECO as an optimization problem and prove that ECO can be performed approximately in linear time, thus eliminating the iterative processes employed in previous studies. Further, we propose a minimal-group structure and a seed point shifting strategy to facilitate temporal smoothing. Finally, we present all algorithms underlying ECO along with a set of optimization techniques. Extensive experiments with two real-life datasets offer insight into ECO and show that it outperforms state-of-the-art solutions in terms of both clustering quality and efficiency.

Age of Information (AoI) has become an important concept in communications, as it allows system designers to measure the freshness of the information available to remote monitoring or control processes. However, its definition tacitly assumes that new information is used at any time, which is not always the case: the instants at which information is collected and used are dependent on a certain query process. We propose a model that accounts for the discrete time nature of many monitoring processes, considering a pull-based communication model in which the freshness of information is only important when the receiver generates a query: if the monitoring process is not using the value, the age of the last update is irrelevant. We then define the Age of Information at Query (QAoI), a more general metric that fits the pull-based scenario, and show how its optimization can lead to very different choices from traditional push-based AoI optimization when using a Packet Erasure Channel (PEC) and with limited link availability. Our results show that QAoI-aware optimization can significantly reduce the average and worst-case perceived age for both periodic and stochastic queries., Comment: Accepted for publication in IEEE Transactions on Communications (preprint version). Extended version of conference paper arXiv:2011.00917

In the current context of Big Data, a multitude of new NoSQL solutions for storing, managing, and extracting information and patterns from semi-structured data have been proposed and implemented. These solutions were developed to relieve the issue of rigid data structures present in relational databases, by introducing semi-structured and flexible schema design. As current data generated by different sources and devices, especially from IoT sensors and actuators, use either XML or JSON format, depending on the application, database technologies that store and query semi-structured data in XML format are needed. Thus, Native XML Databases, which were initially designed to manipulate XML data using standardized querying languages, i.e., XQuery and XPath, were rebranded as NoSQL Document-Oriented Databases Systems. Currently, the majority of these solutions have been replaced with the more modern JSON based Database Management Systems. However, we believe that XML-based solutions can still deliver performance in executing complex queries on heterogeneous collections. Unfortunately nowadays, research lacks a clear comparison of the scalability and performance for database technologies that store and query documents in XML versus the more modern JSON format. Moreover, to the best of our knowledge, there are no Big Data-compliant benchmarks for such database technologies. In this paper, we present a comparison for selected Document-Oriented Database Systems that either use the XML format to encode documents, i.e., BaseX, eXist-db, and Sedna, or the JSON format, i.e., MongoDB, CouchDB, and Couchbase. To underline the performance differences we also propose a benchmark that uses a heterogeneous complex schema on a large DBLP corpus., Comment: 28 pages, 6 figures, 7 tables

Age of Information (AoI) has become an important concept in communications, as it allows system designers to measure the freshness of the information available to remote monitoring or control processes. However, its definition tacitly assumed that new information is used at any time, which is not always the case and the instants at which information is collected and used are dependent on a certain query process. We propose a model that accounts for the discrete time nature of many monitoring processes, considering a pull-based communication model in which the freshness of information is only important when the receiver generates a query. We then define the Age of Information at Query (QAoI), a more general metric that fits the pull-based scenario, and show how its optimization can lead to very different choices from traditional push-based AoI optimization when using a Packet Erasure Channel (PEC)., Comment: Submitted for publication

The proliferation of advanced mobile terminals opened up a new crowdsourcing avenue, spatial crowdsourcing, to utilize the crowd potential to perform real-world tasks. In this work, we study a new type of spatial crowdsourcing, called time-continuous spatial crowdsourcing (TCSC in short). It supports broad applications for long-term continuous spatial data acquisition, ranging from environmental monitoring to traffic surveillance in citizen science and crowdsourcing projects. However, due to limited budgets and limited availability of workers in practice, the data collected is often incomplete, incurring data deficiency problem. To tackle that, in this work, we first propose an entropy-based quality metric, which captures the joint effects of incompletion in data acquisition and the imprecision in data interpolation. Based on that, we investigate quality-aware task assignment methods for both single- and multi-task scenarios. We show the NP-hardness of the single-task case, and design polynomial-time algorithms with guaranteed approximation ratios. We study novel indexing and pruning techniques for further enhancing the performance in practice. Then, we extend the solution to multi-task scenarios and devise a parallel framework for speeding up the process of optimization. We conduct extensive experiments on both real and synthetic datasets to show the effectiveness of our proposals.

Very large time series are increasingly available from an ever wider range of IoT-enabled sensors deployed in different environments. Significant insights can be gained by mining temporal patterns from these time series. Unlike traditional pattern mining, temporal pattern mining (TPM) adds event time intervals into extracted patterns, making them more expressive at the expense of increased mining time complexity. Existing TPM methods either cannot scale to large datasets, or work only on pre-processed temporal events rather than on time series. This paper presents our Frequent Temporal Pattern Mining from Time Series (FTPMf TS) approach which provides: (1) The end-to-end FTPMf TS process taking time series as input and producing frequent temporal patterns as output. (2) The efficient Hierarchical Temporal Pattern Graph Mining (HTPGM) algorithm that uses efficient data structures for fast support and confidence computation, and employs effective pruning techniques for significantly faster mining. (3) An approximate version of HTPGM that uses mutual information, a measure of data correlation known from information theory, to prune unpromising time series from the search space. (4) An extensive experimental evaluation showing that HTPGM outperforms the baselines in runtime and memory consumption, and can scale to big datasets. The approximate HTPGM is up to two orders of magnitude faster and less memory consuming than the baselines, while retaining high accuracy.

The popularity of the Semantic Web (SW) encourages organizations to organize and publish semantic data using the RDF model. This growth poses new requirements to Business Intelligence (BI) technologies to enable On-Line Analytical Processing (OLAP)-like analysis over semantic data. The incorporation of semantic data into a Data Warehouse (DW) is not supported by the traditional Extract-Transform-Load (ETL) tools because they do not consider semantic issues in the integration process. In this paper, we propose a layer-based integration process and a set of high-level RDF-based ETL constructs required to define, map, extract, process, transform, integrate, update, and load (multidimensional) semantic data. Different to other ETL tools, we automate the ETL data flows by creating metadata at the schema level. Therefore, it relieves ETL developers from the burden of manual mapping at the ETL operation level. We create a prototype, named Semantic ETL Construct (SETLCONSTRUCT), based on the innovative ETL constructs proposed here. To evaluate SETLCONSTRUCT, we create a multidimensional semantic DW by integrating a Danish Business dataset and an EU Subsidy dataset using it and compare it with the previous programmable framework SETLPROG in terms of productivity, development time and performance. The evaluation shows that 1) SETLCONSTRUCT uses 92% fewer Number of Typed Characters (NOTC) than SETLPROG, and SETLAUTO (the extension of SETLCONSTRUCT for generating ETL execution flow automatically) further reduces the Number of Used Concepts (NOUC) by another 25%; 2) using SETLCONSTRUCT, the development time is almost cut in half compared to SETLPROG, and is cut by another 27% using SETLAUTO; 3) SETLCONSTRUCT is scalable and has similar performance compared to SETLPROG., Comment: 44 pages including reference, 13 figures and 4 tables. This paper is submitted to Semantic Web Journal and now it is under review

Large volumes of spatial data and multidimensional data are being published on the Semantic Web, which has led to new opportunities for advanced analysis, such as Spatial Online Analytical Processing (SOLAP). The RDF Data Cube (QB) and QB4OLAP vocabularies have been widely used for annotating and publishing statistical and multidimensional RDF data. Although such statistical data sets might have spatial information, such as coordinates, the lack of spatial semantics and spatial multidimensional concepts in QB4OLAP and QB prevents users from employing SOLAP queries over spatial data using SPARQL. The QB4SOLAP vocabulary, on the other hand, fully supports annotating spatial and multidimensional data on the Semantic Web and enables users to query endpoints with SOLAP operators in SPARQL. To bridge the gap between QB/QB4OLAP and QB4SOLAP, we propose an RDF2SOLAP enrichment model that automatically annotates spatial multidimensional concepts with QB4SOLAP and in doing so enables SOLAP on existing QB and QB4OLAP data on the Semantic Web. Furthermore, we present and evaluate a wide range of enrichment algorithms and apply them on a non-trivial real-world use case involving governmental open data with complex geometry types., Comment: 33 pages, 8 figures, 7 tables, 10 listings, 7 algorithms, under review in Semantic Web Journal, available on http://www.semantic-web-journal.net/content/multidimensional-enrichment-spatial-rdf-data-solap

Besides the traditional cartographic data sources, spatial information can also be derived from location-based sources. However, even though different location-based sources refer to the same physical world, each one has only partial coverage of the spatial entities, describe them with different attributes, and sometimes provide contradicting information. Hence, we introduce the spatial entity linkage problem, which finds which pairs of spatial entities belong to the same physical spatial entity. Our proposed solution (QuadSky) starts with a time-efficient spatial blocking technique (QuadFlex), compares pairwise the spatial entities in the same block, ranks the pairs using Pareto optimality with the SkyRank algorithm, and finally, classifies the pairs with our novel SkyEx-* family of algorithms that yield 0.85 precision and 0.85 recall for a manually labeled dataset of 1,500 pairs and 0.87 precision and 0.6 recall for a semi-manually labeled dataset of 777,452 pairs. Moreover, we provide a theoretical guarantee and formalize the SkyEx-FES algorithm that explores only 27% of the skylines without any loss in F-measure. Furthermore, our fully unsupervised algorithm SkyEx-D approximates the optimal result with an F-measure loss of just 0.01. Finally, QuadSky provides the best trade-off between precision and recall, and the best F-measure compared to the existing baselines and clustering techniques, and approximates the results of supervised learning solutions.

Recent development in computing, sensing and crowd-sourced data have resulted in an explosion in the availability of quantitative information. The possibilities of analyzing this so-called Big Data to inform research and the decision-making process are virtually endless. In general, analyses have to be done across multiple data sets in order to bring out the most value of Big Data. A first important step is to identify temporal correlations between data sets. Given the characteristics of Big Data in terms of volume and velocity, techniques that identify correlations not only need to be fast and scalable, but also need to help users in ordering the correlations across temporal scales so that they can focus on important relationships. In this paper, we present AMIC (Adaptive Mutual Information-based Correlation), a method based on mutual information to identify correlations at multiple temporal scales in large time series. Discovered correlations are suggested to users in an order based on the strength of the relationships. Our method supports an adaptive streaming technique that minimizes duplicated computation and is implemented on top of Apache Spark for scalability. We also provide a comprehensive evaluation on the effectiveness and the scalability of AMIC using both synthetic and real-world data sets.

To monitor critical infrastructure, high quality sensors sampled at a high frequency are increasingly used. However, as they produce huge amounts of data, only simple aggregates are stored. This removes outliers and fluctuations that could indicate problems. As a remedy, we present a model-based approach for managing time series with dimensions that exploits correlation in and among time series. Specifically, we propose compressing groups of correlated time series using an extensible set of model types within a user-defined error bound (possibly zero). We name this new category of model-based compression methods for time series Multi-Model Group Compression (MMGC). We present the first MMGC method GOLEMM and extend model types to compress time series groups. We propose primitives for users to effectively define groups for differently sized data sets, and based on these, an automated grouping method using only the time series dimensions. We propose algorithms for executing simple and multi-dimensional aggregate queries on models. Last, we implement our methods in the Time Series Management System (TSMS) ModelarDB (ModelarDB+). Our evaluation shows that compared to widely used formats, ModelarDB+ provides up to 13.7 times faster ingestion due to high compression, 113 times better compression due to the adaptivity of GOLEMM, 630 times faster aggregates by using models, and close to linear scalability. It is also extensible and supports online query processing., Comment: 12 Pages, 28 Figures, and 1 Table

Geo-social data has been an attractive source for a variety of problems such as mining mobility patterns, link prediction, location recommendation, and influence maximization. However, new geo-social data is increasingly unavailable and suffers several limitations. In this paper, we aim to remedy the problem of effective data extraction from geo-social data sources. We first identify and categorize the limitations of extracting geo-social data. In order to overcome the limitations, we propose a novel seed-driven approach that uses the points of one source as the seed to feed as queries for the others. We additionally handle differences between, and dynamics within the sources by proposing three variants for optimizing search radius. Furthermore, we provide an optimization based on recursive clustering to minimize the number of requests and an adaptive procedure to learn the specific data distribution of each source. Our comprehensive experiments with six popular sources show that our seed-driven approach yields 14.3 times more data overall, while our request-optimized algorithm retrieves up to 95% of the data with less than 16% of the requests. Thus, our proposed seed-driven approach set new standards for effective and efficient extraction of geo-social data.

Demand Response (DR) schemes are effective tools to maintain a dynamic balance in energy markets with higher integration of fluctuating renewable energy sources. DR schemes can be used to harness residential devices' flexibility and to utilize it to achieve social and financial objectives. However, existing DR schemes suffer from low user participation as they fail at taking into account the users' requirements. First, DR schemes are highly demanding for the users, as users need to provide direct information, e.g. via surveys, on their energy consumption preferences. Second, the user utility models based on these surveys are hard-coded and do not adapt over time. Third, the existing scheduling techniques require the users to input their energy requirements on a daily basis. As an alternative, this paper proposes a DR scheme for user-oriented direct load-control of residential appliances operations. Instead of relying on user surveys to evaluate the user utility, we propose an online data-driven approach for estimating user utility functions, purely based on available load consumption data, that adaptively models the users' preference over time. Our scheme is based on a day-ahead scheduling technique that transparently prescribes the users with optimal device operation schedules that take into account both financial benefits and user-perceived quality of service. To model day-ahead user energy demand and flexibility, we propose a probabilistic approach for generating flexibility models under uncertainty. Results on both real-world and simulated datasets show that our DR scheme can provide significant financial benefits while preserving the user-perceived quality of service., Comment: 10 pages plus 1 page references, 11 figures, conference: ACM e-Energy 2018

Flexibility of small loads, in particular from Electric Vehicles (EVs), has recently attracted a lot of interest due to their possibility of participating in the energy market and the new commercial potentials. Different from existing work, the aggregation techniques proposed in this paper produce flexible aggregated loads from EVs taking into account technical market requirements. They can be further transformed into the so-called flexible orders and be traded in the day-ahead market by a Balance Responsible Party (BRP). As a result, the BRP can achieve at least 20% cost reduction on average in energy purchase compared to traditional charging based on 2017 real electricity prices from the Danish electricity market., Comment: 9 pages, 7 figures, note paper of the full version to appear at ACM e-Energy 2018

The uncertainty in the power supply due to fluctuating Renewable Energy Sources (RES) has severe (financial and other) implications for energy market players. In this paper, we present a device-level Demand Response (DR) scheme that captures the atomic (all available) flexibilities in energy demand and provides the largest possible solution space to generate demand/supply schedules that minimize market imbalances. We evaluate the effectiveness and feasibility of widely used forecasting models for device-level flexibility analysis. In a typical device-level flexibility forecast, a market player is more concerned with the \textit{utility} that the demand flexibility brings to the market, rather than the intrinsic forecast accuracy. In this regard, we provide comprehensive predictive modeling and scheduling of demand flexibility from household appliances to demonstrate the (financial and otherwise) viability of introducing flexibility-based DR in the Danish/Nordic market. Further, we investigate the correlation between the potential utility and the accuracy of the demand forecast model. Furthermore, we perform a number of experiments to determine the data granularity that provides the best financial reward to market players for adopting the proposed DR scheme. A cost-benefit analysis of forecast results shows that even with somewhat low forecast accuracy, market players can achieve regulation cost savings of 54% of the theoretically optimal., Comment: 13 pages

The collection of time series data increases as more monitoring and automation are being deployed. These deployments range in scale from an Internet of things (IoT) device located in a household to enormous distributed Cyber-Physical Systems (CPSs) producing large volumes of data at high velocity. To store and analyze these vast amounts of data, specialized Time Series Management Systems (TSMSs) have been developed to overcome the limitations of general purpose Database Management Systems (DBMSs) for times series management. In this paper, we present a thorough analysis and classification of TSMSs developed through academic or industrial research and documented through publications. Our classification is organized into categories based on the architectures observed during our analysis. In addition, we provide an overview of each system with a focus on the motivational use case that drove the development of the system, the functionality for storage and querying of time series a system implements, the components the system is composed of, and the capabilities of each system with regard to Stream Processing and Approximate Query Processing (AQP). Last, we provide a summary of research directions proposed by other researchers in the field and present our vision for a next generation TSMS., Comment: 20 Pages, 15 Figures, 2 Tables, Accepted for publication in IEEE TKDE