Javier M. Aguiar

A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings

Recently there has been a significant proliferation in the use of forecasting techniques, mainly due to the increased availability and power of computation systems and, in particular, to the usage of personal computers. This is also true for power network systems, where energy demand forecasting has been an important field in order to allow generation planning and adaptation. Apart from the quantitative progression, there has also been a change in the type of models proposed and used. In the `70s, the usage of non-linear techniques was generally not popular among scientists and engineers. However, in the last two decades they have become very important techniques in solving complex problems which would be very difficult to tackle otherwise. With the recent emergence of smart grids, new environments have appeared capable of integrating demand, generation, and storage. These employ intelligent and adaptive elements that require more advanced techniques for accurate and precise demand and generation forecasting in order to work optimally. This review discusses the most relevant studies on electric demand prediction over the last 40 years, and presents the different models used as well as the future trends. Additionally, it analyzes the latest studies on demand forecasting in the future environments that emerge from the usage of smart grids.

A multi-agent system architecture for smart grid management and forecasting of energy demand in virtual power plants

Recent technological advances in the power generation and information technologies areas are helping to change the modern electricity supply system in order to comply with higher energy efficiency and sustainability standards. Smart grids are an emerging trend that introduce intelligence in the power grid to optimize resource usage. In order for this intelligence to be effective, it is necessary to retrieve enough information about the grid operation together with other context data such as environmental variables, and intelligently modify the behavior of the network elements accordingly. This article presents a multi-agent system model for virtual power plants, a new power plant concept in which generation no longer occurs in big installations, but is the result of the cooperation of smaller and more intelligent elements. The proposed model is not only focused on the management of the different elements, but includes a set of agents embedded with artificial neural networks for collaborative forecasting of disaggregated energy demand of domestic end users, the results of which are also shown in this article.

A Study of the Relationship between Weather Variables and Electric Power Demand inside a Smart Grid/Smart World Framework

One of the main challenges of todays society is the need to fulfill at the same time the two sides of the dichotomy between the growing energy demand and the need to look after the environment. Smart Grids are one of the answers: intelligent energy grids which retrieve data about the environment through extensive sensor networks and react accordingly to optimize resource consumption. In order to do this, the Smart Grids need to understand the existing relationship between energy demand and a set of relevant climatic variables. All smart “systems” (buildings, cities, homes, consumers, etc.) have the potential to employ their intelligence for self-adaptation to climate conditions. After introducing the Smart World, a global framework for the collaboration of these smart systems, this paper presents the relationship found at experimental level between a range of relevant weather variables and electric power demand patterns, presenting a case study using an agent-based system, and emphasizing the need to consider this relationship in certain Smart World (and specifically Smart Grid and microgrid) applications.

Framework for intelligent service adaptation to user's context in next generation networks

Context-aware applications aim at providing personalized services to end users. Sensors and context sources are able to provide enormous amounts of valuable information about individuals that can be used to drive the behavior of services and applications, and adapt them to the specific conditions and preferences of each user. Thanks to advances in mobility, convergence and integration, increasingly larger amounts of these data are available in the Internet. However, this context information is usually fragmented, and traditionally applications have had to take care of context management themselves. This work presents a solution for a converged context management framework and how it can be employed in a future Internet to integrate data from all context sources and serve it to client applications in a seamless and transparent manner. This framework takes advantage of the intelligent and convergent features of next-generation networks, allowing seamless integration, monitoring, and control of heterogeneous sensors and devices under a single context-aware service layer. This layer is centered on a context intelligence module, capable of combining clustering algorithms and semantics to learn from user usage history and take advantage of that information to infer missing or high-level context data.

A Semantic Autonomous Video Surveillance System for Dense Camera Networks in Smart Cities

This paper presents a proposal of an intelligent video surveillance system able to detect and identify abnormal and alarming situations by analyzing object movement. The system is designed to minimize video processing and transmission, thus allowing a large number of cameras to be deployed on the system, and therefore making it suitable for its usage as an integrated safety and security solution in Smart Cities. Alarm detection is performed on the basis of parameters of the moving objects and their trajectories, and is performed using semantic reasoning and ontologies. This means that the system employs a high-level conceptual language easy to understand for human operators, capable of raising enriched alarms with descriptions of what is happening on the image, and to automate reactions to them such as alerting the appropriate emergency services using the Smart City safety network.

Underwater Wireless Communications in Freshwater at 2.4 GHz

There are few equations for underwater communications in the related literature. They show that the speed propagation and absorption coefficient in freshwater are independent of the working frequency of the transmitted signals. However, some studies demonstrate that electromagnetic waves present lower losses when they are working at certain frequencies. In this paper, we perform a set of measurements of electromagnetic (EM) waves at 2.4 GHz in the underwater environment. In our study case, we fix the water conditions and we measure the behavior of EM as a function of several network parameters such as the working frequency, data transfer rates and modulations. Our results will show that higher frequencies do not mean worse network performance. We will also compare our conclusion with some statements extracted from other works.

Performance study of the application of Artificial Neural Networks to the completion and prediction of data retrieved by underwater sensors.

This paper presents a proposal for an Artificial Neural Network (ANN)-based architecture for completion and prediction of data retrieved by underwater sensors. Due to the specific conditions under which these sensors operate, it is not uncommon for them to fail, and maintenance operations are difficult and costly. Therefore, completion and prediction of the missing data can greatly improve the quality of the underwater datasets. A performance study using real data is presented to validate the approach, concluding that the proposed architecture is able to provide very low errors. The numbers show as well that the solution is especially suitable for cases where large portions of data are missing, while in situations where the missing values are isolated the improvement over other simple interpolation methods is limited.

Integrating User-Generated Content and Pervasive Communications

User-generated services (UGSs) are the next step in the user-generated content (UGC) trend. UGSs let end users create their own personalized services using simple graphical tools, such as Microsoft Popfly or Yahoo Pipes. This work aims to design a system to automate the requirement identification and service discovery task for UGSs. The system will analyze context, user profile, and user history to find suitable services, combining semantic characterization and metrics with AI and pattern recognition algorithms, such as neural networks, to identify user requirements in real time and match them with existing services.

IEEE 802.11a/b/g/n short scale indoor wireless sensor placement

Wireless signals present particular behaviour in indoor environments. Walls, roofs and floors generate reflections and refractions that conduce to constructive and destructive interferences due to the multipath effect. In this paper, we perform an analytical study based on the signal strength generated by an access point (AP) inside a building. The evolution of the signal strength allows us to move away the sensors from the AP without reducing the signal level and link quality. We study the IEEE 802.11 technology. These results are compared with the theoretical distribution channels to know what should be followed to avoid interferences. Finally, taking as a reference the measures provided, we develop a method for estimating indoor signal strength that will help us determine the best position for wireless sensors. Our method will allow saving 15% of sensors. The reduction in the number of sensors provides us economic and energy savings, allowing us to prolong the network lifetime.

Moisture Content Prediction in the Switchgrass (Panicum virgatum) Drying Process Using Artificial Neural Networks

This article proposes two artificial neural network (ANN)-based models to characterize the switchgrass drying process: The first one models processes with constant air temperature and relative humidity and the second one models processes with variable air conditions and rainfall. The two ANN-based models proposed estimated the moisture content (MC) as a function of temperature, relative humidity, previous MC, time, and precipitation information. The first ANN-based model describes MC evolution data more accurately than six mathematical empirical equations typically proposed in the literature. The second ANN-based model estimated the MC with a correlation coefficient greater than 98.8%.