Samer Schaat

Building energy management and data analytics

Energy efficiency in buildings depends on the way the building is operated. Therefore energy management is the key component for efficient operation. Data analysis of operation data helps to better understand the systems and detect faults and inefficiencies. The facility manager benefits from smart analysis that makes use of machine learning algorithms and innovative visualizations. This analysis is part of a bigger review of the current structure of building automation as it is used in todays buildings. The operation targets in energy efficiency are complex, ambiguous and contradictory: indoor comfort, energy efficiency, high availability and low costs cannot be met at the same time. In order to improve building operation, a novel model of automation is discussed. The foundation of this model is in cognitive automation, since each building is unique in its selection of energy sources, architecture, usage and location, which implies that the buildings control system has to be adapted individually. This paper connects the data-driven analysis of operation data with a cognitive concept to be used for operating the energy systems in a building and regarding goals on how to optimally operate while considering constraints about the limits of operation, using the complex, dynamic data from building automation.

Intelligent streetlight management in a smart city

The intention of a Smart City concept is among other things to increase the energy efficiency of a city. Typically addressed topics are energy management or urban traffic management. Up to now Information and Communication Technology (ICT) measures within a Smart City to increase energy efficiency in public lighting have not been considered in detail. The paper presents an approach of an intelligent streetlight management system being an integral part of a Smart City platform. Field bus technology is used at the field level. Control and monitoring strategies are implemented as web services in the central software. Interoperable interfaces to other parts of the platform are specified. Real-life use cases at test sites in Austria demonstrate the benefits of the system: increased energy efficiency without compromising public safety.

ARS: An AGI Agent Architecture

The computational paradigm in Cognitive Science, which the AGI approach revives, provides a powerful methodology of examining human information processing by testing assumptions in computer simulations, and enables technical applications with human-like capabilities. Nevertheless, intensive interdisciplinary collaboration and the development of a holistic and integrated model remain ongoing challenges. This includes the consideration of the basis of rational cognition, in particular the significance of unconscious and affective processes in the human mind. We take these issues into consideration and integrate them into a holistic and integrated functional model of the human mind, implemented as an agent’s decision unit and evaluated in an Artificial Life simulation using an interdisciplinary methodology.

Examination of foundational AGI-agents in Artificial-Life simulations

The examination of AGI agents is an interdisciplinary challenge. This is particularly the case for their foundations, assumedly (in compliance with Damasio) drives and emotions. We demonstrate how these foundations of a human-like control system are tested using simplified exemplary cases as test-specifications. After showing how we model the required functions of the agents decision unit, we provide details of the incremental steps of our examination. As a first step, we use calibration-specifications, which we concretize with the help of psychoanalysts and neuroscientists and show how a flexible parameterization of the model generates expected behavior. This step enables a deeper model analysis in the second step of our examination, which corresponds to model exploration and provides further information for adaptions of the parameters, model, or assumptions. Overall, this examination methodology allows for a stepwise model development and examination and provides the ground for comparing the simulation data with empirical data, which we plan as a next step.

Emotion in Consumer Simulations for the Development and Testing of Recommendations for Marketing Strategies

To examine the impact factors and mechanisms of the decision to switch to green electricity, we develop a socio-cognitive agent-based simulation. Following seminal research in the field of decision making we focus on emotion and social norms as core mechanisms in consumer decisions. A survey of possible consumers provides the information how to calibrate the simulation, by which means a first validation is reached. Further data analysis supports model validation and exploration. Overall, this methodology provides the premises of using simulations for recommending marketing strategies that support the distribution of environmental-friendly energy providers.

Increasing energy efficiency with traffic adapted intelligent streetlight management

Street lighting consumes a non inconsiderable amount of energy. First promising approaches include the deployment of LED based lights to reduce energy consumption. The paper presents a further step of increasing energy efficiency by implementing traffic adapted intelligent management strategies of the luminaries. The idea is to include a communication module into each streetlight that exchanges data via a field aggregated point device with a streetlight management center being an integral part of a traffic management system. Information of the current traffic situation is delivered by traffic sensors and applies traffic adapted control of the luminaries. Consequently, additional energy savings and CO2 reductions are possible without decreasing road safety because a traffic dependent level of luminosity can be provided if needed.

Usage of spreading activation for content retrieval in an autonomous agent

For cognitive agents that decide based on experiences, memory retrieval is a significant issue. In this article a contribution to this field is made by introducing the concept of psychic spreading activation for memory retrieval in an autonomous agent. Using the psychoanalytical foundation of that as a constraint, a variant of spreading activation was created to regard perceptional as well as motivational inputs and considering the emotional component of a situation. Results show how this type of memory retrieval can influence the decision making process.

A cognitive architecture for building automation

The operation of buildings holds the potential for significant energy savings and high flexibility during operation without affecting indoor comfort. The leverage for this potential is the building automation system, which can modify and optimize operation without the need of investments in energy systems or refurbishment of the envelope. The challenge is the uniqueness of each building and its energy systems. By introducing a cognitive architecture, it is possible to autonomously and adaptively optimize operation and allow for individual optimization. This work describes a cognitive architecture and its application to an optimization task for a renewable energy system.

Decision-making in the cognitive architecture SiMA

In a cognitive architecture, decision-making is the task that processes information from sensor data and stored knowledge to get appropriate action plans and actuator commands. Its aim is to make a decision in a given situation based upon available options and current goals of the system. In this paper, the decision-making process of the cognitive architecture SiMA is presented. Its unique features are the comprehensive evaluation of options, an application of case-based reasoning, as well as the management of resources by a two-step decision-making process. The implementation is verified through an artificial world implementation of a use case.

A multi-criteria exemplar model for holistic categorization in autonomous agents

When developing a model of perceptual categorization, a functional and holistic approach is required. Therefore, considering the influence of an agents current needs, perceptual categorization is modeled as the valuation of a stimulus regarding its potential to satisfy an agents needs. Based on an exemplar model, an activation-based model is developed that considers two kinds of categorization criteria, namely perceptual similarity and expectation, which represents bottom-up and top-down approaches of perception, respectively. The aggregation of these two criteria then corresponds to the integration of these approaches into a holistic model. A simplified simulation of the categorization model shows that the multi-criteria model leads to a more confident valuation of stimulus objects. In particular, the model is able to eliminate ambiguity in perceptual categorization. Although used equivalently, the simulation shows that the bottom-up similarity criterion is more significant than the top-down expectation-based criterion. In particular, the latter is only significant in case of ambiguity in an objects appearance.