PLUG-N-HARVEST Architecture for Secure and Intelligent Management of Near-Zero Energy Buildings.

Building Automation (BA) is key to encourage the growth of more sustainable cities and smart homes. However, current BA systems are not able to manage new constructions based on Adaptable/Dynamic Building Envelopes (ADBE) achieving near-zero energy-efficiency. The ADBE buildings integrate Renewable Energy Sources (RES) and Envelope Retrofitting (ER) that must be managed by new BA systems based on Artificial Intelligence (AI) and Internet of Things (IoT) through secure protocols. This paper presents the PLUG-N-HARVEST architecture based on cloud AI systems and security-by-design IoT networks to manage near-zero ADBE constructions in both residential and commercial buildings. To demonstrate the PLUG-N-HARVEST architecture, three different real-world pilots have been considered in Germany, Greece and Spain. The paper describes the Spain pilot of residential buildings including the deployment of IoT wireless networks (i.e., sensors and actuators) based on Zwave technology to enable plug-and-play installations. The real-world tests showed the high efficiency of security-by-design Internet communications between building equipment and cloud management systems. Moreover, the results of cloud intelligent management demonstrate the improvements in both energy consumption and comfort conditions.

Decomposing user-defined tasks in a reinforcement learning setup using TextWorld.

The current paper proposes a hierarchical reinforcement learning (HRL) method to decompose a complex task into simpler sub-tasks and leverage those to improve the training of an autonomous agent in a simulated environment. For practical reasons (i.e., illustrating purposes, easy implementation, user-friendly interface, and useful functionalities), we employ two Python frameworks called TextWorld and MiniGrid. MiniGrid functions as a 2D simulated representation of the real environment, while TextWorld functions as a high-level abstraction of this simulated environment. Training on this abstraction disentangles manipulation from navigation actions and allows us to design a dense reward function instead of a sparse reward function for the lower-level environment, which, as we show, improves the performance of training. Formal methods are utilized throughout the paper to establish that our algorithm is not prevented from deriving solutions.

CoFly-WeedDB: A UAV image dataset for weed detection and species identification.

The CoFly-WeedDB contains 201 RGB images (∼436 MB) from the attached camera of DJI Phantom Pro 4 from a cotton field in Larissa, Greece during the first stages of plant growth. The 1280 × 720 RGB images were collected while the Unmanned Aerial Vehicle (UAV) was performing a coverage mission over the field's area. During the designed mission, the camera angle was adjusted to -87°, vertically with the field. The flight altitude and speed of the UAV were equal to 5 m and 3 m/s, respectively, aiming to provide a close and clear view of the weed instances. All images have been annotated by expert agronomists using the LabelMe annotation tool, providing the exact boundaries of 3 types of common weeds in this type of crop, namely (i) Johnson grass, (ii) Field bindweed, and (iii) Purslane. The dataset can be used alone and in combination with other datasets to develop AI-based methodologies for automatic weed segmentation and classification purposes.

Large scale nonlinear control system fine-tuning through learning.

Despite the continuous advances in the fields of intelligent control and computing, the design and deployment of efficient large scale nonlinear control systems (LNCSs) requires a tedious fine-tuning of the LNCS parameters before and during the actual system operation. In the majority of LNCSs the fine-tuning process is performed by experienced personnel based on field observations via experimentation with different combinations of controller parameters, without the use of a systematic approach. The existing adaptive/neural/fuzzy control methodologies cannot be used towards the development of a systematic, automated fine-tuning procedure for general LNCS due to the strict assumptions they impose on the controlled system dynamics; on the other hand, adaptive optimization methodologies fail to guarantee an efficient and safe performance during the fine-tuning process, mainly due to the fact that these methodologies involve the use of random perturbations. In this paper, we introduce and analyze, both by means of mathematical arguments and simulation experiments, a new learning/adaptive algorithm that can provide with convergent, an efficient and safe fine-tuning of general LNCS. The proposed algorithm consists of a combination of two different algorithms proposed by Kosmatopoulos (2007 and 2008) and the incremental-extreme learning machine neural networks (I-ELM-NNs). Among the nice properties of the proposed algorithm is that it significantly outperforms the algorithms proposed by Kosmatopoulos as well as other existing adaptive optimization algorithms. Moreover, contrary to the algorithms proposed by Kosmatopoulos , the proposed algorithm can operate efficiently in the case where the exogenous system inputs (e.g., disturbances, commands, demand, etc.) are unbounded signals.

Correction on 'Dynamical neural networks that ensure exponential identification error convergence'

In the article by [Kosmatopoulos et al. (1997)] (Neural Networks 10(2) 299-314) the Theorem 4.1 was incorrect. In this note we present the correct version of Theorem 4.1.

Dynamical Neural Networks that Ensure Exponential Identification Error Convergence.

Classical adaptive and robust adaptive schemes, are unable to ensure convergence of the identification error to zero, in the case of modeling errors. Therefore, the usage of such schemes to "black-box" identification of nonlinear systems ensures-in the best case-bounded identification error. In this paper, new learning (adaptive) laws are proposed which when applied to recurrent high order neural networks (RHONN) ensure that the identification error converges to zero exponentially fast, and even more, in the case where the identification error is initially zero, it remains equal to zero during the whole identification process. The parameter convergence properties of the proposed scheme, that is, their capability of converging to the optimal neural network model, is also examined; it is shown to be similar to that of classical adaptive and parameter estimation schemes. Finally, it is mentioned that the proposed learning laws are not locally implementable, as they make use of global knowledge of signals and parameters. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.