A Smart Energy Efficiency Service Platform for Barcelona


Through a number of already running R&D projects in the city of Barcelona, the authors of this paper are presenting and integrated approach to interface energy management systems in smart cities.
The adopted vision involves the deployment of an Open Energy Service Platform capable to communicate and extend the functionalities of current public infrastructure. In a context where public bodies and service providers need to cooperate and maximize the efficiency of any public resource, it is necessary to build over the existing solutions and create spaces to exploit synergies. Hence, through the open framework proposed, it will not only be possible for authorities to assess the behavior of a smart city from an energy efficiency point of view, but also to dynamically negotiate with Energy Service Companies and Facility Managers, the quality of the services based on a number of factors, both economic and social.
The authors, in addition to their extensive presence in the city of Barcelona as providers of technology for public services and management of public infrastructure, have invested in the last years an accumulative effort of 30 person years in order to deploy new solutions in the city. New Building Management Systems for emblematic public spaces as the stadium of the Football Club Barcelona, or energy management systems for public schools, or information systems supporting the electrical vehicles of the city are just examples of the solutions investigated and tested in the last years.

A data model for energy decision support systems for smart cities. The case of BESOS Common Information Model


Integrating Energy Management Systems is a necessary task in order to be able to offer a range of services for citizens and public authorities. This task requires integration at the data level in order to expose data coming from different systems in a unified way. In this paper we describe the creation of a Common Information Model to unify disparate Energy Management Systems in the context of the BESOS project. We identify related work, describe design decisions and methodology and give an outline of the data model itself, based on profiling and extending the IEC 61970 standard.

Automating the Generation of Privacy Policies for Context-sharing Applications


Enabling the automated recognition and sharing of a user’s context is a primary motivation for many pervasive computing applications. In the past, a significant amount of research has been focusing on the aspect of effective and efficient recognition. Yet, when context is shared with others, the resulting disclosure of personal information can have undesirable privacy implications. A common solution to this problem is the manual creation of an application-specific privacy policy that defines which information may be shared with whom. However, as the number of applications increases, such a manual approach becomes increasingly cumbersome and over time, it is likely to lead to incomplete or even inconsistent policies. In this paper, we discuss how a privacy policy can be derived automatically by analyzing the user’s sharing behavior when using online collaboration tools. Our approach retrieves shared content and the associated sharing settings, detects context types and automatically derives a privacy policy that reflects the user’s past sharing behavior.
To validate our approach, we have implemented it as an extensible software library for the Android platform and we have developed plug-ins for two popular collaboration tools, namely Google Calendar and Facebook.

Keynote: Establishing Secure Intelligent Environments


An Analog Ensemble-based Similarity Search Technique for Solar Power Forecasting


The power forecasting for renewable energy powe rplants has been a highly active field of research during the last decade. In order to support the operation of the power grid, sophisticated algorithms have to predict the future development of power generation. Algorithms in the class of analog ensembles conduct the process of forecasting by finding historically similar situations (e.g., by comparing weather situations), and merging the historic power generation time series during similar periods to an overall power forecast. However, these algorithms often only use very simple comparison strategies, which in turn do not make optimal use of the historic information available. In this article, we propose and compare advanced search strategies for similarity assessment. These strategies include the assessment of forecasting time periods as a whole and joint time windows of
historic and future weather situations. Also, historic power time series are used directly in the comparison strategy. Furthermore,
we propose a combined scheme to perform automated feature selection and -weighting for individual weather parameters. We evaluate the proposed technique on a solar farm data set consisting of 21 photovoltaic power plants which is made publicly available. In the evaluation we show that advanced comparison strategies not only offer an advantage over simple strategies, but that these techniques also are able to outperform other reference models such as physical models.

Deep Learning for Solar Power Forecasting – An Approach Using Autoencoder and LSTM Neural Networks


Power forecasting of renewable energy power plants is a very active research field, as reliable information about the future power generation allow for a safe operation of the power grid and helps to minimize the operational costs of these energy sources. Deep Learning algorithms have shown to be
very powerful in forecasting tasks, such as economic time series or speech recognition. Up to now, Deep Learning algorithms have only been applied sparsely for forecasting renewable energy power plants. By using different Deep Learning and Artificial Neural Network algorithms, such as MLP, Deep Belief Networks, AutoEncoder, and LSTM, we introduce these powerful algorithms in the field of renewable energy power forecasting. In our
experiments, we used combinations of these algorithms to show their forecast strength compared to physical forecasting model in the prediction of 21 solar power plants. Our results using Deep Learning algorithms show a superior forecasting performance compared to Artificial Neural Networks as well as other reference models such as physical models.

A eficiência vai morar na Baixa lisboeta


Magazine publication by Lisboa e-nova

BESOS: Building Energy Decision Support Systems for Smart cities

NA downloads
Article at GRID Innovation online