Skill-based games offer an exceptional avenue for entertainment, fostering self-esteem, relaxation, and social satisfaction. Engagement in online skill gaming platforms is however heavily dependent on the outcomes and experience (e.g., wins/losses). Understanding the factors driving increased engagement is crucial within skill gaming platforms. In this study, we aim to address two key questions: (1) "What factors are driving users to increase their engagement?" and (2) "How can we personalize users journey accordingly to further optimize their engagement?". In skill gaming platforms, the impact of causal relationships often manifests with a delay, which varies significantly as users? personas evolve. Without a detailed information on treatments (such as timing and frequency), estimating the impact of a causal-treatment-effect in a highly volatile game-play data becomes exceedingly challenging. This work proposes a framework called EFfECT-RL that establishes causal discovery by integrating change-point detection and explainable K-means clustering, while leveraging users' game-play and transactional-data. Unlike existing methods which were unable to detect causal-effects in extremely volatile-data, EFfECT-RL generates threshold-trees (~ 79% accuracy) elucidating causal-relationships. Once the causal relationship is established, we personalize treatments by developing a novel offline deep reinforcement learning-based approach. Our online recommendations show a 3% improvement in user engagement (platform-centric) with 70% relevancy (user-centric).

Multi-variate Time Series (MTS) forecasting has made large strides (with very negligible errors) through recent advancements in neural networks, e.g., Transformers. However, in critical situations like predicting gaming overindulgence that affects one's mental well-being; an accurate forecast without a contributing evidence (explanation) is irrelevant. Hence, it becomes important that the forecasts are Interpretable - intermediate representation of the forecasted trajectory is comprehensible; as well as Explainable - attentive input features and events are accessible for a personalized and timely intervention of players at risk. While the contributing state of the art research on interpretability primarily focuses on temporally-smooth single-process driven time series data, our online multi-player gameplay data demonstrates intractable temporal randomness due to intrinsic orthogonality between player's game outcome and their intent to engage further. We introduce a novel deep Actionable Forecasting Network (AFN), which addresses the inter-dependent challenges associated with three exclusive objectives - 1) forecasting accuracy; 2) smooth comprehensible trajectory and 3) explanations via multi-dimensional input features while tackling the challenges introduced by our non-smooth temporal data, together in one single solution. AFN establishes a new benchmark via: (i) achieving 25% improvement on the MSE of the forecasts on player data in comparison to the SOM-VAE based SOTA networks; (ii) attributing unfavourable progression of a player's time series to a specific future time step(s), with the premise of eliminating near-future overindulgent player volume by over 18% with player specific actionable inputs feature(s) and (iii) proactively detecting over 23% (100% jump from SOTA) of the to-be overindulgent, players on an average, 4 weeks in advance.

Games are one of the safest source of realizing self-esteem and relaxation at the same time. An online gaming platform typically has massive data coming in, e.g., in-game actions, player moves, clickstreams, transactions etc. It is rather interesting, as something as simple as data on gaming moves can help create a psychological imprint of the user at that moment, based on her impulsive reactions and response to a situation in the game. Mining this knowledge can: (a) immediately help better explain observed and predicted player behavior; and (b) consequently propel deeper understanding towards players' experience, growth and protection.

This paper introduces ScarceGAN which focuses on identification of extremely rare or scarce samples from multi-dimensional longitudinal telemetry data with small and weak label prior. We specifically address: (i) severe scarcity in positive class, stemming from both underlying organic skew in the data, as well as extremely limited labels; (ii) multi-class nature of the negative samples, with uneven density distributions and partially overlapping feature distributions; and (iii) massively unlabelled data leading to tiny and weak prior on both positive and negative classes, and possibility of unseen or unknown behavior in the unlabelled set, especially in the negative class. Although related to PU learning problems, we contend that knowledge (or lack of it) on the negative class can be leveraged to learn the compliment of it (i.e., the positive class) better in a semi-supervised manner. To this effect, ScarceGAN re-formulates semi-supervised GAN by accommodating weakly labelled multi- class negative samples and the available positive samples. It relaxes the supervised discriminator's constraint on exact differentiation be- tween negative samples by introducing a 'leeway' term for samples with noisy prior. We propose modifications to the cost objectives of discriminator, in supervised and unsupervised path as well as that of the generator. For identifying risky players in skill gaming, this formulation in whole gives us a recall of over 85% (~60% jump over vanilla semi-supervised GAN) on our scarce class with very minimal verbosity in the unknown space. Further ScarceGAN out- performs the recall benchmarks established by recent GAN based specialized models for the positive imbalanced class identification and establishes a new benchmark in identifying one of rare attack classes (0.09%) in the intrusion dataset from the KDDCUP99 challenge. We establish ScarceGAN to be one of new competitive benchmark frameworks in the rare class identification for longitudinal telemetry data.

Games of skill are an excellent source of recreation and relaxation. Games are also the safest and readily accessible constructs for social interaction and community affairs which potentially opens up new avenues for realising personal worth, social acceptance, respect & recognition. However, when these games are played with real money, ensuring game prudence, whereby users play real-money skill games only for entertainment purposes, and do so well within their resourceful means, becomes necessary. It becomes paramount for the wellness of players and also to ensure online gaming is only available for sheer entertainment. In this proposal, we present an automated, data driven, AI powered, Responsible Game Play (RGP) framework cum tool which has been integrated in our online skill gaming platform. RGP pipeline is a combination of: a) a couple of anomaly detection Rule Based Engines; b) a Deep Learning Pipeline which models the game play characteristics of healthy and engaged players to identify potentially risky players, and c) a ML based Local Expert which leverages users' longitudinal behavioral patterns and constructs new features using the adjacent AI OPS and Signal Processing Domains. We integrate the psychometric assessment to nudge and coarse correct at-risk players proactively, ahead of time

Operating system (OS) containers enabling the microservice-oriented architecture are becoming popular in the context of Cloud services. Containers provide the ability to create lightweight and portable runtime environments that decouple the application requirements from the characteristics of the underlying system. Services built on containers have a small resource footprint in terms of processing, storage, memory and network, allowing a more dense deployment environment. While the performance of such containers is addressed in few previous studies, understanding the failure-repair behavior of the containers remains unexplored. In this paper, from an availability point of view, we propose and compare different configuration models for deploying a containerized software system. Inspired by Google Kubernetes, a container management system, these configurations are characterized with a failure response and migration service. We develop novel non-state-space (i.e., fault tree) and state-space (i.e., stochastic reward net) analytic models for container availability analysis. Analytical as well as simulative solutions are obtained for the developed models. Our analysis provides insights on k out-of N availability and sensitivity of system availability for key system parameters. Finally, we build an open-source software tool powered by these models. The tool helps a Cloud administrator to assess the availability of a containerized system and to conduct a what-if analysis based on user-provided parameters and configurations.

Games of skill are an excellent source of recreation, entertainment and relaxation. However when these games are played with real money, the important facet of responsible game play must be addressed rigorously and efficiently by game providers. Ensuring game prudence, whereby users play real-money skill games only for entertainment purposes, and do so well within their resourceful means, necessary for the wellness of players, and also for the sustained engagement and retention of players in the system. To this end, in this work we present a deep learning model that helps identify players who are on the verge of displaying irresponsible or addictive game play in a fully unsupervised manner. We use a combination of long short-term memory and adversarial auto-encoder networks to analyze game play along three tell-tale dimensions of immoderation, namely, money, time and despair. Our model provides a state of the art solution for identifying a precise set of problem gamers in skill-based cash games well ahead of time, effectively addressing the challenges of (i) extreme class imbalance, (ii) sparse and incomplete ground truth, (iii) overlapping behavioral patterns between risky and non-risky but highly engaged players.

We present a deep learning framework for game action modeling, which enables fine-grained analyses of player behavior. We develop CNN-based supervised models that effectively learn the critical game play decisions from skilled players, and use these models to assess player characteristics in the system, such as their retention, engagement, deposit buckets, etc. We show that with a carefully constructed input format, that efficiently represents the game state and history as a multi-dimensional image, along with a custom architecture the model learns the strategies of the game accurately. It is further enhanced with look-ahead achieved by self-play simulation to better estimate the game state, and this information is used in a new loss function. Next, we show that analyzing the players with these models as reference has immense benefit in understanding player potential in terms of engagement and revenue. We also use the model to understand the various contexts under which players tend to make mistakes, and use these insights to up-skill players.

Making design choices for big data systems is not trivial. If not planned out efficiently, keeping in mind the practical requirements, there's a possibility that the deployed system can lack important features to match up the application or it may contain over-sophisticated methods that incurs a large cost, but little increase in the efficiency, output. To equip the end user towards wise design choices, we have proposed a decision support framework for big data systems that can evaluate the suitability over numerous design combinations and outputs the one most efficient for the end-user requirement.

Mining and profiling intent of players is an important facet in today's online games for the gaming companies to take targeted actions and provide personalized services. While analyzing and predicting player behavior have been studied in the online gaming domain, investigating intent behind those behaviors from the data has not been studied. We introduce the problem of player intent mining. With the example of online Rummy, a popular card game in India, we show how specific behavior aspects of player over time plays a key role in identifying their intent. Through both supervised and unsupervised techniques we achieve reasonable accuracy in identifying the intent.

In an increasingly digital urban setting, connected & concerned Citizens typically voice their opinions on various civic topics via social media. Efficient and scalable analysis of these citizen voices on social media to derive actionable insights is essential to the development of smart cities. The very nature of the data: heterogeneity and dynamism, the scarcity of gold standard annotated corpora, and the need for multi-dimensional analysis across space, time and semantics, makes urban social media analytics challenging. This workshop is dedicated to the theme of social media analytics for smart cities, with the aim of focusing the interest of CIKM research community on the challenges in mining social media data for urban informatics. The workshop hopes to foster collaboration between researchers working in information retrieval, social media analytics, linguistics; social scientists, and civic authorities, to develop scalable and practical systems for capturing and acting upon real world issues of cities as voiced by their citizens in social media. The aim of this workshop is to encourage researchers to develop techniques for urban analytics of social media data, with specific focus on applying these techniques to practical urban informatics applications for smart cities.

Docker containers are becoming an attractive implementation choice for next-generation microservices-based applications. When provisioning such an application, container (microservice) instances need to be created from individual container images. Starting a container on a node, where images are locally available, is fast but it may not guarantee the quality of service due to insufficient resources. When a collection of nodes are available, one can select a node with sufficient resources. However, if the selected node does not have the required image, downloading the image from a different registry increases the provisioning time. Motivated by these observations, in this paper, we present CoMICon, a system for co-operative management of Docker images among a set of nodes. The key features of CoMICon are: (1) it enables a co-operative registry among a set of nodes, (2) it can store or delete images partially in the form of layers, (3) it facilitates the transfer of image layers between registries, and (4) it enables distributed pull of an image while starting a container. Using these features, we describe - (i) high availability management of images and (ii) provisioning management of distributed microservices based applications. We extensively evaluate the performance of CoMICon using 142 real, publicly available images from Docker hub. In contrast to state-of-the-art full image based approach, CoMICon can increase the number of highly available images up to 3× while reducing the application provisioning time by 28% on average.

Operating system (OS) containers provide a process level virtualization in a multi-tenant Cloud environment. Such containers are becoming increasingly popular in developer community as they facilitate fast development and delivery of enterprise class Cloud services. Furthermore, these containers share a common OS and hence, they have a low resource foot-print leading to reduced provisioning time. In this paper, we investigate such promise of containers while provisioning large scale 3-tier applications. First, through benchmarking, we observe that at very large scale, several application scaling factors (e.g., number of containers of an application provisioned in parallel, application load) and system state parameters (e.g., number of applications and containers running on a system) introduce variability in application provisioning time because of resource bottleneck in general, and specifically due to the OS process overhead. To address such variability, we propose a provisioning decision management system SCoPe that provides an application partitioning and provisioning strategy where we determine the maximum number of containers of every application that can be provisioned in parallel across physical machines, while meeting the service level agreement (SLA) on provisioning time and Cloud provider specific objectives (e.g., maximize consolidation of applications, minimize operating cost). This joint partitioning and provisioning problem is NP-hard and we propose a greedy heuristic solution. Using real data set and through extensive experiments, we demonstrate the performance of SCoPe for large scale container based application provisioning. Compared to other well-known heuristics, SCoPe can reduce the partitioning by 5x or more, while meeting SLAs.

A key challenge in participatory sensing systems has been the design of incentive mechanisms that motivate individuals to contribute data to consuming applications. Emerging trends in urban development and smart city planning indicate the use of citizen reports to gather insights and identify areas for transformation. Consumers of these reports (e.g. city agencies) typically associate non-uniform utility (or values) to different reports based on the spatio-temporal context of the reports. For example, a report indicating traffic congestion near an airport, in early morning hours, would tend to have much higher utility than a similar report from a sparse residential area. In such cases, the design of an incentive mechanism must motivate participants, via appropriate rewards (or payments), to provide higher utility reports when compared to less valued ones. The main challenge in designing such an incentive scheme is two-fold: (i) lack of prior knowledge of participants in terms of their availability (i.e. who are in the vicinity) and reporting behaviour (i.e. what are the rewards expected); and (ii) minimizing payments to the reporters while ensuring that the desired number of reports are collected. In this paper, we propose STOC-PISCES, an algorithm that guarantees a stochastic optimal solution in the generalized setting of an unknown set of participants, with non-deterministic availabilities and stochastically rational reporting behaviour. The superior performance of STOC-PISCES in experimental settings, based on real-world data, endorses its adoption as an incentive strategy in participatory sensing applications like smart city management.

The prevalence of mobile devices and applications strongly motivate mobile crowdsourcing for facilitating location-dependent services. We propose LoRUS, a Location-based Relevant User determination System for efficiently retrieving the top-k relevant mobile users in a given spatial window.

Discovering and matching services is an area that has been extensively explored. In this paper we envision services that advertise not only their functional parameters, but also highlight the Quality of Service(QoS) guarantees (or non-functional parameters) they can provide. As a result users can also incorporate QoS requirements along with the service request. Given the vast pool of services available today, leading to complex ontologies, the search space becomes extremely large, increasing the complexity of the search. We construct an overlay reflecting the relationships between the services, which facilitates the pruning of the entire search space. Additionally our system takes into consideration the user context which provides information pertaining to the users preferences. (eg: A user could be performance-savvy or functionally-cautious etc) We propose an algorithm CCD (Context based Complex service Discovery), which utilizes the inputs provided by the users and determines the similarity quotient for the functional and QoS parameters. Our experiments show that CCD significantly improves the scalability of the search by aggressively pruning the search space, achieved by visiting only relevant nodes. CCD further uses the requester context to improve the recommendations provided to the requester. We also compare CCD with two baseline approaches based on the depth-first search algorithm on a travel ontology, which was created using real service definitions from the Open Travel Alliance (OTA).

This paper presents a framework for Robust Infrastructure over Shared Computing resource (RISC), which can offer Organizations with Small-scale Computing infrastructures (OSCs) a way to share their unused resources in an ad-hoc manner for suitable monetary incentives. Such a framework provides dual benefits to an OSC: it enables sharing of unused resource during periods of low computing load while allowing execution of any long-term computation on public or anonym zed data at a very low cost during periods of high load. The ad-hoc and heterogeneous nature of the shared infrastructure make the resource management problem inRISC non-trivial -- a resource manager needs to: (i) maximize profit while determining incentives for resource owners and prices for resource users in an integrated manner, and (ii)emulate large-scale cloud-like robustness and capabilities out of unreliable, small-scale and intermittently available resources at a low cost. This leads to a constrained market situation where offered prices and incentives should lead to a desired level of SLA and reliability for the consumers. Existing approaches of incentive based scheduling for market-like grids assume an open market, based only on demand response, and thus are inapplicable for the constrained market situation in shared resources infrastructure. Specifically, RISC framework has two main components: (i) a first-of-a-kind Dynamic Pricing and Incentivization (DPI) strategy that computes the incentives and the prices while maximizing profit for RISC, using an epoch-by-epoch pricing feedback loop, and (ii) a DPI dependent Reliability, Cost and Seaware(RCS) scheduler that takes the resource reservation requests as input and assigns replicas of these requests tone or more shared resources for guaranteeing performanceSLAs and reliability, while minimizing the cost of resource reservations. Moreover, to handle the communication overhead of computing over geographically distributed resources, the scheduler strives to reduce the network cost of resource allocation. Results from extensive trace-driven experimentation show that our approach can indeed provide appropriate incentives for resource providers, and robust cost-efficient infrastructure solution for resource users.

Information about resident involvement in reporting various city-related events (e.g., Potholes, traffic jams) via mobile apps is critical to key stakeholders for effective city management. While existing efforts have primarily focused on event data collection in space, they are not capable of performing efficient retrieval of information about resident involvement in event reporting across different spatial regions and at different spatial granularities. Hence, this work makes the following contributions. First, we present CRIS, a scalable system for efficient retrieval of resident involvement and event information across different spatial regions and at varying spatial granularities. Second, we propose the euR-tree, a novel R-tree-based index augmented with (a) a hash-based array for indexing events in space, and (b) fixed-length arrays for indexing resident involvement information in reporting events in space. The euR-tree is integrated into CRIS to realize efficient retrieval. Third, our performance study indicates that the euR-tree is indeed effective in performing such retrieval with reduced query response times and disk I/Os.

This paper presents C-CLOUD, a democratic cloud infrastructure for renting computing resources includingnon-cloud resources (i.e. computing equipment not part of any cloud infrastructure, such as, PCs, laptops, enterprise servers and clusters). C-CLOUD enables enormous amount of surplus computing resources, in the range of hundreds of millions, to be rented out to cloud users. Such a sharing of resources allows resource owners to earn from idle resources, and cloud users to have a cost-efficient alternative to large cloud providers. Compared to existing approaches to sharing surplus resources, C-CLOUD has two key challenges: ensuring Service Level Agreement (SLA) and reliability of reservations made over heterogeneous resources, and providing appropriate mechanism to encourage sharing of resources. In this context, C-CLOUD introduces novel incentive mechanism that determines resourcerents parametrically based on their reliability and capability.

This is a tutorial paper covering issues associated dynamic management of information as well as content in wireless networks of different types such as Mobile Peer-to-Peer (MP2P), Vehicle-to-Vehicle (V2V) and Delay-Tolerant Networks (DTNs).

Cities typically face a wide gamut of management and maintenance problems. Existing automated sensor based solutions are prohibitively expensive to deploy. Furthermore, these solutions need to be complemented by incorporating human judgment for accurate, timely and cost-effective city-related event identification. To this end, this work proposes City Zen, which is a novel platform for event reporting and analytics to engage residents towards city management through incentives. Key contributions include: (a) the City Zen platform with an app for enabling authenticated residents to report events in a city for end-to-end integrated smart city management, (b) Differentiated incentive management based on types and priorities of events, quality and timeliness of event reports as well as resident intent, and (c) a social dashboard for searching events and subscribing for event alerts with additional ability to provide feedback on the event reports. Ongoing pilots and our performance study indicate that the platform indeed performs city management cost-effectively depending on the incentive mechanisms used for engaging residents.

A rank clustering system, CloudRank, is proposed that takes into account cloud user preference data to characterize cloud user behaviour and also identify (an initially unknown set of) groups of users with similar behaviour in an unsupervised manner. The user groups are determined based on fitting mixture models on the cloud user preference observations. A preference can be anything that a system designer would like to include to characterize high-level user requirements such as demands on performance, cost, security, availability, etc. CloudRank can be useful for: (i) cloud providers to target their service offerings according to the user groups (i.e. customer segments) through appropriate customization of services pertaining to the user groups typical requirements; (ii) recommendation systems or a marketplace (that enables inter-operability among different providers) to determine which offerings best suit certain user groups; and (iii) prediction of any new users behaviour based on their preference information. Results on realistic feedbacks from internal cloud service providers show an average of 80% accuracy of the proposed unsupervised technique. When compared with a supervised technique, i.e. when the number of user groups are known beforehand, the error is within 15%, thus making it a promising technique for realistic deployments, particularly when there is no prior knowledge regarding the clusters.

The article presents an access control model called Criticality Aware Access Control (CAAC) for criticality (emergency) management in smart infrastructures. Criticalities are consequences of events which take a system (in our case, a smart infrastructure) into an unstable state. They require the execution of specific response actions in order to bring them under control. The principal aim of CAAC is to grant the right set of access privileges (to facilitate response action execution), at the right time, to the right set of subjects, for the right duration, in order to control the criticalities within the system. In this regard, the CAAC model uses a stochastic model called the Action Generation Model to determine the required response actions for the combination of criticalities present within the system. It then facilitates response actions by adaptively altering the privileges to specific subjects, in a proactive manner, without the need for any explicit access requests. In this article, we formalize the CAAC model and validate it based on two design goals - proactivity and adaptiveness. Finally, we present a case study demonstrating CAAC’s operation on an oil-rig platform in order to aid in the response to health- and fire-related criticalities.

As cloud computing has become popular and the number of cloud providers has proliferated over time, the first barrier to cloud users will be how to accurately estimate performance capabilities of many different clouds and then, select a right one for given complex workload based on estimates. Such cloud capability estimation and selection can be a big challenge since most clouds can be considered as black-boxes to cloud users by abstracting underlying infrastructures and technologies. This paper describes a cloud recommender system to recommend an optimal cloud configuration to users based on accurate estimates. To achieve this, our system generates the capability vector that consists of relative performance scores of resource types (e.g., CPU, memory, and disk) estimated for given user workload using benchmarks. Then, a search algorithm has been developed to identify an optimal cloud configuration based on these collected capability vectors. Experiments show our approach accurately estimate the performance capability (less than 10% error) while scalable in large search space.

We present a mobility simulation framework that simulates the movement behaviors of people to generate spatiotemporal movement data. There is a growing interest in applications that make use of patterns mined from spatio-temporal data. However, since the availability of actual spatio-temporal movement data in the public domain is limited, it is useful to have simulation frameworks that generate data close to the real life behavior of people, so that data mining techniques can be tested. We argue that modeling group behavior effectively is a key element of any real-life simulation framework, because there are many applications that require the knowledge of groups and events. In this work, we propose generic models to represent individual and group movement behaviors. We present an algorithm that takes various behaviors created using the proposed models, and generates spatio-temporal movement data for as many individuals as needed. Experimental analysis shows the efficacy of the proposed framework handling a broad spectrum of behaviors with high scalability.

The proliferation of cloud computing can imply a barrier to cloud users. When deploying their complex workloads into clouds, cloud users are typically overwhelmed by too many technical choices. Moreover, underlying technologies and pricing mechanisms of clouds vary and are not transparent to them. Consequently, it is hard for cloud users to capture the monetary and performance implications of their workload deployments. This paper introduces a cloud recommendation platform, referred to as Cloud Advisor. It allows cloud users to explore various cloud configurations recommended based on user preferences such as budget, performance expectation, and energy saving for given workload. Then, it allows cloud users to compare offered price and performance with other clouds' offerings for the workload. By providing transparent comparisons, it can also support cloud provider to develop a competitive pricing strategy such as price reduction driven by energy efficiency. We have applied the proposed platform for recommendation from a real data center and some external clouds.

Parallelization of big-data analytics services over a federation of heterogeneous clouds has been considered to improve performance. However, contrary to common intuition, there is an inherent tradeoff between the level of parallelism and the performance for big-data analytics principally because of a significant delay for big-data to get transferred over the network. The data transfer delay can be comparable or even higher than the time required to compute data. To address the aforementioned tradeoff, this paper determines: (a) how many and which computing nodes in federated clouds should be used for parallel execution of big-data analytics; (b) opportunistic apportioning of big-data to these computing nodes in a way to enable synchronized completion at best-effort performance; and (c) sequence of apportioned, different sizes of big-data chunks to be computed in each node so that transfer of a chunk is overlapped as much as possible with the computation of the previous chunk in the node. In this regard, Maximally Overlapped Bin-packing driven Bursting (MOBB) algorithm is proposed, which improve the performance by up to 60% against existing approaches.

Dynamic Application Hosting Management (DAHM) is proposed for geographically distributed data centers, which decides on the number of active servers and on the workload share of each data center. DAHM achieves cost-efficient application hosting by taking into account: (i) the spatio-temporal variation of energy cost, (ii) the data center computing and cooling energy efficiency, (iii) the live migration cost, and (iv) any SLA violations due to migration overhead or network delay. DAHM is modeled as fixed-charge min-cost flow and mixed integer programming for stateless and stateful applications, respectively, and it is shown NP-hard. We also develop heuristic algorithms and prove, when applications are stateless and servers have an identical power consumption model, that the approximation ratio on the minimum total cost is bounded by the number of data centers. Further, the heuristics are evaluated in a simulation study using realistic parameter data; compared to a performance-oriented application assignment, that is, hosting at the data center with the least delay, the potential cost savings of DAHM reaches 33%. The savings come from reducing the total number of active servers as well as leveraging the cost efficiency of data centers. Through the simulation study, the article further explores how relaxing the delay requirement for a small fraction of users can increase the cost savings of DAHM.

Cyber-physical systems (CPSs) couple their cyber and physical parts to provide mission-critical services, including automated pervasive health care, smart electricity grid, green cloud computing, and surveillance with unmanned aerial vehicles (UAVs). CPSs can use the information available from the physical environment to provide such ubiquitous, energy-efficient and low-cost functionalities. Their operation needs to ensure three key properties, collectively referred to as S3: 1) safety: avoidance of hazards; 2) security: assurance of integrity, authenticity, and confidentiality of information; and 3) sustainability: maintenance of long-term operation of CPSs using green sources of energy. Ensuring S3 properties in a CPS is a challenging task given the spatio-temporal dynamics of the underlying physical environment. In this paper, the formal underpinnings of recent CPS S3 solutions are aligned together in a theoretical framework for cyber-physical interactions, empowering CPS researchers to systematically design solutions for ensuring safety, security, or sustainability. The general applicability of this framework is demonstrated with various exemplar solutions for S3 in diverse CPS domains. Further, insights are provided on some of the open research problems for ensuring S3 in CPSs.

Body area networks (BANs) are networks of medical devices implanted within or worn on the human body. Analysis and verification of BAN designs require (i) early feedback on the BAN design and (ii) high-confidence evaluation of BANs without requiring any hazardous, intrusive, and costly deployment. Any design of BAN further has to ensure (i) the safety of the human body, that is, limiting any undesirable side-effects (e.g., heat dissipation) of BAN operations (involving sensing, computation, and communication among the devices) on the human body, and (ii) the sustainability of the BAN operations, that is, the continuation of the operations under constrained resources (e.g., limited battery power in the devices) without requiring any redeployments. This article uses the Model Based Engineering (MBE) approach to perform design and analysis of BANs. In this regard, first, an abstract cyber-physical model of BANs, called BAN-CPS, is proposed that captures the undesirable side-effects of the medical devices (cyber) on the human body (physical); second, a design and analysis tool, named BAND-AiDe, is developed that allows specification of BAN-CPS using industry standard Abstract Architecture Description Language (AADL) and enables safety and sustainability analysis of BANs; and third, the applicability of BAND-AiDe is shown through a case study using both single and a network of medical devices for health monitoring applications.

Dynamic Application Hosting Management (DAHM) allows clouds to dynamically host applications in data centers at different locations based on: (i) spatio-temporal variation of energy price, (ii) data center computing and cooling energy efficiency, (iii) Virtual Machine (VM) migration cost for the applications, and (iv) any SLA violations due to migration overhead or network delay. DAHM is complementary to dynamic workload distribution problem and is modeled as mixed integer programming; online algorithms are developed to solve the problem. The algorithms are evaluated in a simulation study using realistic data and compared with performance-oriented application assignment, i.e., hosting the application at a data center whose delay is the least. Our simulations results indicate that DAHM can potentially save up to 20% cost while incurring only a nominal increase in SLA violations. The savings are obtained by exploiting the cost efficiency variation as well as reducing the total number of VMs employed to host applications.

Power-aware and thermal-aware techniques such as power-throttling and workload manipulation have been developed to counter the increasing power density in the current data centers. The basis for any such power-aware and/or thermal-aware technique, however, depends heavily on the equipment's power consumption model assumed. The goal of this paper is to perform power-profiling of different systems-namely, the Dell PowerEdge 1855 and 1955-based on actual power measurements. Gamut (Generic Application eMUlaTor) benchmark, double-precision matrix multiplication, and convolution of two vectors are used for varying the CPU utilization and Disk I/O.

Dynamic networks, e.g. mobile ad hoc networks (MANETs), call for adaptive protocols that can tolerate topological changes due to nodes' mobility and depletion of battery power. Also proactivity in these protocols is essential to ensure low latency. Self-stabilization techniques for distributed systems provide both adaptivity and proactivity to make it suitable for the MANETs. However, energy-efficiency - a prime concern in MANETs with battery-powered nodes - is not guaranteed by self-stabilization. In this paper, we propose a node-based energy metric that minimizes the energy consumption of the multicast tree by taking into account the overhearing cost. We apply the metric to self-stabilizing shortest path spanning tree (SS-SPST) protocol to obtain energy-aware SS-SPST (SS-SPST-E). Using simulations, we study the energy-latency tradeoff by comparing SS-SPST-E with SS-SPSTand other MANET multicast protocols, such as ODMRP and MAODV.

Many applications, such as disaster response and military applications, call for proactive maintenance of links and routes in Mobile Ad hoc NETworks (MANETs) to ensure low latency during data delivery. The goal of this paper is to minimize the wastage of energy in the network due to high control traffic, which restricts the scalability and applicability of such protocols, without trading-off the low latency. We categorize the proactive protocols based on the periodic route and link maintenance operations performed; and analytically derive the optimum periods for these operations in different protocol classes. The analysis takes into account data traffic intensity, link dynamics, application reliability requirements, and the size of the network. The proposed optimization significantly reduces the control traffic for low data traffic intensity in the network and increases protocol scalability for large networks without compromising the low latency of proactive protocols.

A generic theoretical framework for managing critical events in ubiquitous computing systems is presented. The main idea is to automatically respond to occurrences of critical events in the system and mitigate them in a timely manner. This is different from traditional fault-tolerance schemes, where fault management is performed only after system failures. To model the critical event management, the concept of criticality, which characterizes the effects of critical events in the system, is defined. Each criticality is associated with a timing requirement, called its window-of-opportunity, that needs to be fulfilled in taking mitigative actions to prevent system failures. This is in addition to any application-level timing requirements.The criticality management framework analyzes the concept of criticality in detail and provides conditions which need to be satisfied for a successful multiple criticality management in a system. We have further simulated a criticality aware system and its results conform to the expectations of the framework.

Access control policies define the rules for accessing system resources. Traditionally, these are designed to take a reactive view for providing access, based on explicit user request. This methodology may not be sufficient in the case of critical events (emergencies) where automatic and timely access to resources may be required to facilitate corrective actions. This paper introduces the novel concept of criticality which measures the level of responsiveness for taking such actions. The paper further incorporates criticality in an access control framework for facilitating the management of critical situations. Specific properties and requirements for such criticality aware access control are identified and a sample model is provided along with its verification