With the development of autonomous vehicular technologies, the execution tasks become more memory-consuming and computation-intensive. Simultaneously, a certain portion of tasks are latency-sensitive, such as collaborative perception, path planning, collaborative simultaneous localization and mapping, real-time pedestrian detection, etc. Because of the limited computation resources inside vehicles and restricted transmission bandwidth, edge computing can be an effective way to assist with the tasks execution. Considering from the perspective of business, the reservation or subscription cost is cheaper than real time requests. In order to minimize the expense of consuming edge services, the desirable situation is to reserve the resources as much as needed. However, the configuration of vehicular network is variational in practice due to the diversity of road maps, different time range like peak time and off-peak time, and the various task types, which makes it challenging to figure out a general machine learning model that is suitable for any case. Therefore, to predict the resource consumption in edge nodes accurately in different scenarios, we propose a two-stage meta-learning based approach to adaptively choose the appropriate machine learning algorithms based on the meta-features extracted on database. Besides, due to the deficiency of dataset for edge resource consumption, we program in game engine unity to generate the 3D model of Manhattan area. Meanwhile, we change the factors like different road maps and number of vehicles so as to get closer to practices. In the evaluation part, we adopt root mean square error, mean absolute percentage, and mean GEH as evaluation metrics to assess the performance of each model. Also, a quantitative analysis for the total cost and waste is also conducted. Eventually, we can find that the proposed meta-learning based method outperforms the non-meta ones.

Edge Computing Resources Reservation in Vehicular Networks: A Meta-Learning Approach

Cloud computing has been widely adopted to support various computation services. A fundamental problem faced by cloud providers is how to efficiently allocate resources upon user requests and price the resource usage, in order to maximize resource efficiency and hence provider profit. Existing studies establish detailed performance models of cloud resource usage, and propose offline or online algorithms to decide allocation and pricing. Differently, we adopt a blackbox approach, and leverage model-free Deep Reinforcement Learning (DRL) to capture dynamics of cloud users and better characterize inherent connections between an optimal allocation/pricing policy and the states of the dynamic cloud system. The goal is to learn a policy that maximizes net profit of the cloud provider through trial and error, which is better than decisions made on explicit performance models. We combine long short-term memory (LSTM) units with fully-connected neural networks in our DRL to deal with online user arrivals, and adjust the output and update methods of basic DRL algorithms to address both resource allocation and pricing. Evaluation based on real-world datasets shows that our DRL approach outperforms basic DRL algorithms and state-of-theart white-box online cloud resource allocation/pricing algorithms significantly, in terms of both profit and the number of accepted users.

/pdf/learning-resource-allocation-and-pricing-for-cloud-profit-379vaz3u87.pdf

Learning Resource Allocation and Pricing for Cloud Profit Maximization.

Sensors are distributed across the globe leading to an avalanche of data about our environment. It is possible today to utilize networks of sensors to detect and identify a multitude of observations, from simple phenomena to complex events and situations. The lack of integration and communication between these networks, however, often isolates important data streams and intensifies the existing problem of too much data and not enough knowledge. With a view to addressing this problem, the semantic sensor Web (SSW) proposes that sensor data be annotated with semantic metadata that will both increase interoperability and provide contextual information essential for situational knowledge.

Semantic Sensor Web

The internet of things (IoT) as an evolving technology represents an active scientific research field in recognizing research challenges associated with its application in various domains, ranging from consumer convenience, smart energy, and resource saving to IoT enterprises. Sensors are crucial components of IoT that relay the collected data in the form of the data stream for further processing. Interoperability of various connected digital resources is a key challenge in IoT environments. The enrichment of raw sensor data with semantic annotations using concept definitions from ontologies enables more expressive data representation that supports knowledge discovery. In this paper, a systematic review of integration of semantics into sensor data for the IoT is provided. The conducted review is focused on analyzing the main solutions of adding semantic annotations to the sensor data, standards that enable all types of sensor data via the web, existing models of stream data annotation, and the IoT trend domains that use semantics.

Integration of Semantics Into Sensor Data for the IoT: A Systematic Literature Review

The economics of cloud computing has recently attracted increasing attention. In particular, a topic which is still under debate is how prices charged to customers for cloud resources are formed, since alternative pricing rules could be considered. Based on three pricing schemes inspired by those used by Amazon EC2, the main global cloud service provider, in the paper we address two main issues. First we present a methodology for the relevant parameters of the pricing rules to be determined in an optimal way, that is to maximise the provider’s revenue. Moreover, we discuss reasons for co-existence of three pricing rules, rather than fewer, to access the cloud. Our findings suggest that this may be due to a larger coverage of the potential demand, since customers applying for cloud services vary in their willingness to pay for the job, the time length of the service, the computational power requested etc. Furthermore, the pricing rule in the so-called, spot market, can provide the platform with useful information on the customers willingness to pay for cloud services. This is because in the spot market users offer a price for service, but pay less than that if their request is satisfied.

/pdf/pricing-cloud-iaas-computing-services-4z1mkli0eh.pdf

Pricing cloud IaaS computing services

Cloud Computing is one of the technologies with rapid development in recent years where there is increasing interest in industry and academia. This technology enables many services and resources for end users. With the rise of cloud services number of companies that offer various services in cloud infrastructure is increased, thus creating a competition on prices in the global market. Cloud Computing providers offer more services to their clients ranging from infrastructure as a service (IaaS), platform as a service (PaaS), software as a service (SaaS), storage as a service (STaaS), security as a service (SECaaS), test environment as a service (TEaaS). The purpose of providers is to maximize revenue by their price schemes, while the main goal of customers is to have quality of services (QoS) for a reasonable price. The purpose of this paper is to compare and discuss several models and pricing schemes from different Cloud Computing providers.

/pdf/pricing-schemes-in-cloud-computing-an-overview-3s35vqt8dg.pdf

Pricing Schemes in Cloud Computing: An Overview

A shift in water monitoring approach from traditional grab sampling to novel wireless sensors is gaining in popularity not only among researchers but also in the market. These latest technologies r ...

InWaterSense: An Intelligent Wireless Sensor Network for Monitoring Surface Water Quality to a River in Kosovo

Wireless sensor networks WSNs are aiding water quality monitoring with support for real-time and remote quality measurements in terrain. Environmental monitoring portals receiving data from sensors have been a practice since a while among researchers. However, the Web portal introduced here is essentially an integrated portal since it supports modeling and management of both, the observational stream data on water quality coming from wireless sensors-dynamic data, as well as of the data describing the WSN itself, its devices and the corresponding site allocation data-static data. Access is given to a wide range of individuals, from water experts to WSN engineers, to general public. Experts' module infers statistics about water parameters given the experts' data and rules. The portal is further distinguished for its level of scalability: it allows adding with ease new components, like add certain new regulatory documents for water quality, and directly compare data measured by sensors with corresponding quality standards. The aim is to enrich the portal with semantics in future.

An Integrated Web Portal for Water Quality Monitoring through Wireless Sensor Networks

The Internet of Things (IoT) vision is to connect uniquely identifiable devices that surround us to the Internet, which is best described through ontologies. Thereby, new emerging technologies such as wireless sensor networks (WSN) are recognized as an essential enabling component of the IoT today. Hence, given the increasing interest to provide linked sensor data through the Web either following the Semantic Web Enablement (SWE) standard or the Linked Data approach, there is a need to also explore those data for potential hidden knowledge through data mining techniques utilized by a domain ontology. Following that rationale, a new lightweight IoT architecture SEMDPA has been developed. It supports linking sensors and other devices, as well as people via a single web by mean of a device-person-activity (DPA) crossroad ontology. The architecture is validated by mean of three rich-in-semantic services: contextual data mining over WSN, semantic WSN web enablement, and Linked WSN data. SEMDPA could be easily extensible to capture semantics of input sensor data from other domains as well.

Besmir Sejdiu

Papers

Pricing Schemes in Cloud Computing: An Overview

Integration of Semantics Into Sensor Data for the IoT: A Systematic Literature Review

InWaterSense: An Intelligent Wireless Sensor Network for Monitoring Surface Water Quality to a River in Kosovo

An Integrated Web Portal for Water Quality Monitoring through Wireless Sensor Networks

SEMDPA: A Semantic Web Crossroad Architecture for WSNs in the Internet of Things