Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Internet of Things (IoT) is an emerging domain that promises ubiquitous connection to the Internet, turning common objects into connected devices. The IoT paradigm is changing the way people interact with things around them. It paves the way for creating pervasively connected infrastructures to support innovative services and promises better flexibility and efficiency. Such advantages are attractive not only for consumer applications, but also for the industrial domain. Over the last few years, we have been witnessing the IoT paradigm making its way into the industry marketplace with purposely designed solutions. In this paper, we clarify the concepts of IoT, Industrial IoT, and Industry 4.0. We highlight the opportunities brought in by this paradigm shift as well as the challenges for its realization. In particular, we focus on the challenges associated with the need of energy efficiency, real-time performance, coexistence, interoperability, and security and privacy. We also provide a systematic overview of the state-of-the-art research efforts and potential research directions to solve Industrial IoT challenges.

Industrial Internet of Things: Challenges, Opportunities, and Directions

The Internet of Things (IoT) is entering the daily operation of many industries; applications include but are not limited to smart cities, smart grids, smart homes, physical security, e-health, asset management, and logistics. For example, the concept of smart cities is emerging in multiple continents, where enhanced street lighting controls, infrastructure monitoring, public safety and surveillance, physical security, gunshot detection, meter reading, and transportation analysis and optimization systems are being deployed on a city-wide scale. A related and cost-effective user-level IoT application is the support of IoT-enabled smart buildings. Commercial space has substantial requirements in terms of comfort, usability, security, and energy management. IoT-based systems can support these requirements in an organic manner. In particular, power over Ethernet, as part of an IoT-based solution, offers disruptive opportunities in revolutionizing the in-building connectivity of a large swath of devices. However, a number of deployment-limiting issues currently impact the scope of IoT utilization, including lack of comprehensive end-to-end standards, fragmented cybersecurity solutions, and a relative dearth of fully-developed vertical applications. This paper reviews some of the technical opportunities offered and the technical challenges faced by the IoT in the smart building arena.

IoT Considerations, Requirements, and Architectures for Smart Buildings—Energy Optimization and Next-Generation Building Management Systems

The smart metering and communication methods used in smart grid are being extensively studied owing to widespread applications of smart grid. Although the monitoring and control processes are widely used in industrial systems, the energy management requirements at both service supplier and consumer side for individuals promoted the evolution of smart grid. In this paper, it is aimed to disclose in a clear and clean way that what smart grid is and what kind of communication methods are used. All components of a smart grid are introduced in a logical way to facilitate the understanding, and communication methods are presented regarding to their improvements, advantages, and lacking feature. The developing generation, transmission, distribution and customer appliances are surveyed in terms of smart grid integration. The communication technologies are introduced as wireline and wireless classification where the key features are also tabulated. The security requirements of hardware and software in a smart grid are presented according to their cyber and physical structures.

A survey on smart metering and smart grid communication

Wearable salivary uric acid mouthguard biosensor with integrated wireless electronics

In the last years, Wireless Sensor Networks experienced a great success in the research community and also the interest of the industrial world seems increasing, as demonstrated by the definition of several standards (e.g. WirelessHART and ISA100.11a). Up to now, network robustness and optimization of the power consumption are the key point of a sensors network. However, the recent technology improvements offer a plenty of processing power and, in this scenario, some background aspects (e.g. advanced networking and time synchronization) cannot be ignored. This paper focuses its attention on synchronization on Wireless Sensor Network based on IPv6 protocol. The integration of IEEE 1588 protocol into this scenario has been analyzed. The synchronization stack has been implemented over a performing platform, which achieves a timestamping accuracy in the order of ±500 ns. However, the synchronization capabilities of the overall system is in the order of 1 ms.

Time distribution in IPv6 Wireless Sensor Networks

The Internet of Things (IoT) paradigm is gaining interest in several application fields, from medical devices to smart building and industrial automation. Such a success is due to the flexibility and interoperability between different application domains: the possibility to vertically share data among applications is the winning point of this technology. IoT sensors installed on the field generate a large amount of data, which have to be stored somewhere for subsequent analysis. Database technologies are experiencing a deep transformation to be able to handle these data streams. The recent trend is a transition from relational to non-relational databases. Among the latter, the Time Series Databases (TSDBs) seem to be the solution for storing large amount of time series data generated by IoT applications. Although these solutions are optimized to handle thousands of parallel data streams from IoT sensors, the performance of data extraction could not be compatible with some applications. The target of the paper is to investigate the impact that different metadata could have over the data extraction performance in TSDBs. A dedicated testing procedure has been configured for evaluating InfluxDB, one of the most effective and widespread TSDBs. The performance analysis, carried out on a specific use case, demonstrated that the database write and read performance can be significantly affected by the used data model, with queries executed on the same data requiring times from hundreds of ms to seconds in the worst cases.

Impact of Data Model on Performance of Time Series Database for Internet of Things Applications

The micro grid is a cluster of electricity generators, energy storage systems, and loads that can operate connected, as well as disconnected, from the distribution grid. In this paper the time related characteristics of Cyber Physical Systems (CPCs) to be used for (IEC 61850-based) automation of micro grids are investigated. Specific constrains are taken into account as, for instance: the use of heterogeneous communication networks; the reuse of any existing wired and wireless network and assets; and the deployment of new renewable power sources or energy storage systems into traditional (old) grids. The proposed approach relies on IEEE 1588 infrastructure placed in the key positions of the Micro grid to build a backbone for precise distribution of time reference to IEC 61850 device, (which are used to guarantee the interoperability with the distribution grid). The proposed solution is installed inside the campus of the University of Brescia in a real micro grid. The experimental results show the feasibility of the proposed approach, with overall latency and jitter in good agreement with the usual requirements of IEC61850: for instance, the total estimated end to end delay (latency) including the backbone (i.e. 3 cascaded Ethernet switches) is below 0.6 ms.

Analysis of IEEE 1588-based Cyber Physical System for micro grid automation

The Smart City (SC) approach involves the integration and correlation of information coming from different areas (e.g. power grid management, water distribution, and more) for the optimization of asset management. The SC is like a pervasive sensors and actuator network, where the nodes exchange information, exploiting the power of Internet of Things technologies. A performing and dynamic communication infrastructure is a key requirement in this scenario. One of the main obstacles to the deployment of SC in real scenario is the lack of an efficient communication infrastructure that can be easily maintained and extended when new services are required. The use a heterogeneous network, which employs various technologies, appears to be the most promising solution. In this paper, a low-cost modular bridge platform for heterogeneous Software Defined Networking (SDN) has been characterized. The results highlight that the considered low cost platform is able to handle, without affecting the performance of the system, more than 600 kp/s (coming from three Gigabit Ethernet ports and one IEEE 802.11n port) and to properly forward more than one hundred of different data streams.

Analisys of modular bridge platform for heterogeneous software defined networking in smart city applications

The increasing presence of Distributed Energy Resources (DERs) in distribution grids is posing relevant challenges to all electricity operators, particularly concerning the unreliability and intermittency of distributed generators based on Renewable Energy Sources (RESs). The use of Distributed Energy Storage Systems (DESSs) has been recently proposed to cope with these issues, along with the implementation of advanced Demand Response (DR) programs and of ancillary services within Smart Grids. The test of these advanced (and experimental) mechanisms in an operating distribution grid is not usually feasible, both for economic as well as for technical reasons, including security and safety aspects. Conversely, the test in simulation or in Hardware In the Loop (HIL) environments may be limiting, due to the difficulty in reproducing the typically unpredictable behavior of the power demand patterns of end-users. For this reason, a testing facility for the characterization of DESSs coupled with RES generators has been designed and deployed in the eLUX laboratory of the University of Brescia. The system is formed by a 25 kWh DESS coupled with a 64 kWp photovoltaic power plant. The testing facility has been equipped with an experimental supervisory system which allows the remote monitoring and control of both the power installations. Such a system can be used to test and validate different control approaches, including DR requests and ancillary services, under working conditions similar to the real deployment of DESSs in modern power grids.

Stefano Rinaldi

Papers

Time distribution in IPv6 Wireless Sensor Networks

Impact of Data Model on Performance of Time Series Database for Internet of Things Applications

Analysis of IEEE 1588-based Cyber Physical System for micro grid automation

Analisys of modular bridge platform for heterogeneous software defined networking in smart city applications

Characterization of Energy Storage Sytems for Renewable Generators: An Experimental Testbed