This paper presents the development of a decision support system (DSS) for a low-voltage grid with renewable energy sources (photovoltaic panels and wind turbine) which aims at achieving energy balance in a pilot microgrid with less energy consumed from the network. The DSS is based on a procedural decision algorithm that is applied on a pilot microgrid, with energy produced from renewable energy sources, but it can be easily generalized for any microgrid. To underline the benefits of the developed DSS two case scenarios (a household and an office building with different energy consumptions) were analyzed. The results and throw added value of the paper is the description of an implemented microgrid, the development and testing of the decision support system on real measured data. Experimental results have demonstrated the validity of the approach in rule-based decision switching.

The paper presents a solar-tracking method for control of photovoltaic panel movement in order to improve the conversion efficiency of the system. The designed algorithm is implemented on a solar-tracking experimental platform using a tri-positional control strategy. It makes use of measured values for radiation from appropriate sensors and assures command of the platform's two positioning motors. The solution was developed as a virtual instrument, using the graphical programming environment, LabVIEW. This allows for fast deployment, versatility and scalability

Buildings play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large-scale energy-management strategies from the supply side to the consumer side. When buildings integrate local renewable-energy generation in the form of renewable-energy resources, they become prosumers, and this adds more complexity to the operation of interconnected complex energy systems. A class of methods of modelling the energy-consumption patterns of the building have recently emerged as black-box input–output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produced by nondeterministic processes underlying energy consumption. We present an application of a class of neural networks, namely, deep-learning techniques for time-series sequence modelling, with the goal of accurate and reliable building energy-load forecasting. Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects, and are considered suitable for further use in future in situ energy management at the building and neighborhood levels.

Considering the advances in building monitoring and control through networks of interconnected devices, effective handling of the associated rich data streams is becoming an important challenge. In many situations, the application of conventional system identification or approximate grey-box models, partly theoretic and partly data driven, is either unfeasible or unsuitable. The paper discusses and illustrates an application of black-box modelling achieved using data mining techniques with the purpose of smart building ventilation subsystem control. We present the implementation and evaluation of a data mining methodology on collected data from over one year of operation. The case study is carried out on four air handling units of a modern campus building for preliminary decision support for facility managers. The data processing and learning framework is based on two steps: raw data streams are compressed using the Symbolic Aggregate Approximation method, followed by the resulting segments being input into a Support Vector Machine algorithm. The results are useful for deriving the behaviour of each equipment in various modi of operation and can be built upon for fault detection or energy efficiency applications. Challenges related to online operation within a commercial Building Management System are also discussed as the approach shows promise for deployment.

The paper discusses the advantages and challenges for a cloud-based system architecture for process monitoring and statistical analysis of network performance. The focus is on integrating industrial wireless sensor networks (IWSN), composed of low-power wireless field devices for sensing and actuation, with cloud infrastructures, enabling remote access over secure real-time communication channels. The proposed cloud integration solution implements RESTful services at a coordinator node level of the WSN, allowing the implementation of a scalable and more performant communication infrastructure. The overall system allows functionality for visualization, data storage and processing and distributed algorithms that can run across heterogeneous multi-level monitoring and control systems. We present a modeling and simulation approach for scalable IPv6-based industrial wireless sensor networks, highlight effective mechanisms for cloud interoperability and argument the feasibility of the proposed system.

Wireless sensor networks are currently being deployed over a vast array of applications to collect, process and reliably transmit data from a source event to a data sink. This in turn requires reliable power supply, mainly in the form of primary or secondary batteries storing energy to supply the various functional discrete components along with accurate prediction of sensor node life time, based on estimated state of charge of the energy source. The paper presents two approaches for energy modeling of sensor node life time in ambient monitoring scenarios concerned with periodical sampling of measurable parameters from the indoor environment. The analytical approach involves modeling the individual components of a sensor node and carrying out simulations in different duty-cycling regimes to obtain an expected life time. Experimental modeling has also been carried out over short and medium term repeatable deployments in order to gather meaningful sets of data suitable for statistical interpretation. Battery discharge characteristics are determined in order to extract high level information used in system design for indoor ambient monitoring. final goal is to incorporate validated experimental results back into simulation approaches and enable a prediction framework for the Memsic IRIS XM2110 motes in order to approach the direct and inverse problem: accurately determine node life time for various sampling and communication regimes or choose optimal configuration parameters for an imposed node life time.