SMARTGREENS 2020 Abstracts

Area 1 - Smart and Digital Services

Full Papers

Paper Nr:	3
Title:	Software-defined Wireless Sensor Network: WSN Virtualization and Network Re-orchestration
Authors:	Indrajit S. Acharyya and Adnan Al-Anbuky
Abstract:	Flexible reorganization of complex IoT (Internet-of-Things)-based sensor networks is crucial for the alignment of the sensor network’s operational dynamics with that of the monitored external phenomenon. Software-Defined Networking (SDN), when supported by Cloud-level Network Virtualization (NV), offers a prospective avenue for a flexible sensor network that can re-orchestrate as the monitored process demands. In order to allow for seamless softwarization of the sensor network functional entities, this paper promotes function modularization and establishment of both virtual repositories of reusable software modules as well as requisite operational software. An architectural solution that is aligned with Industry 4.0’s ideology is presented in this work. This along with the software-defined resources is deemed as a viable solution to re-orchestrate the physical sensor network. By means of example simulation scenarios, this paper highlights the utility of NV for flexible soft trialling of sensor network topological re-orchestration and highlighting the possible network downtime associated with that operation. The outcome offers potential for the utilization of the virtual environment and the dynamics retained within it to offer ground for pre-planning for best possible re-orchestration scenario that comply with adaptive interaction with the dynamics of the physical environment.
Download

Area 2 - Smart Infrastructures and Smart Buildings

Full Papers

Paper Nr:	16
Title:	Flexible Power Distribution Networks: New Opportunities and Applications
Authors:	Konstantin Suslov, Ilia Shushpanov, Nadezhda Buryanina and Pavel Ilyushin
Abstract:	Today, electricity companies worldwide use digital devices. Their use is commonplace in the grid, whether it is electricity generation, transmission or distribution. Power distribution networks are the most widespread but are the least digitalized because they have to deal with the problems related to the collection of necessary information, the adaptation methods, failures to identify some emergencies and their effect, and the insufficient number of reliability assessment methods. These networks were not important for energy companies and they did not pay attention to them. Nowadays, however, there is a need to pay special attention to these networks. Insufficient attention to them has led to delay in their digitalization and today there are some issues to work on. For example, improper placement of devices leads to a lack of complete and reliable information, which is the reason why relay protection and automatic systems in distribution electrical networks do not provide selectivity. An algorithm is proposed to site measuring devices so that information is collected most effectively. The proper installation of the devices will allow adjusting the operating parameters of the relay protection and automatic systems depending on changes in external weather conditions and fluctuations in power consumption in the network. It will also help to determine the best network topology. The paper proposes a technique for distribution network control, which takes into account the type of failure in case of emergency in real time, and a method to locate measuring devices and establish an information and communication network.
Download

Short Papers

Paper Nr:	17
Title:	Estimating Environmental Variables in Smart Sensor Networks with Faulty Nodes
Authors:	Nicoleta Stroia, Daniel Moga, Vlad Muresan and Alexandru Lodin
Abstract:	Estimation of missing sensor data is an important issue in control systems that are based on smart sensor networks, since it can support an adaptive functionality of the control network. The paper investigates the extension of a low cost sensor network with a smart emulator module, able to act as a virtual sensor node on the network. The embedded emulator module should allow running of several pre-trained neural networks for estimating the values of faulty sensors. Training of the neural networks is made on a PC based on the records available at the level of the gateway module interfacing the control network. The proposed approach is exemplified for the case of a distributed control network system applied to smart homes.
Download

Area 3 - Sustainable Computing and Systems

Full Papers

Paper Nr:	15
Title:	ℓε-Regularized Economic Model Predictive Control for Thermal Comfort in Multizone Buildings
Authors:	Farah Gabsi, Frederic Hamelin, Nathalie Sauer and Joseph J. Yame
Abstract:	This paper presents a new thermal regulation technique for multizone buildings, possibly equipped with discontinuously (on/off) operating HVAC actuators, based on regularized economic model predictive control (REMPC). In the presence of actuators operating on an on/off basis, it often happens that the control scenario resulting from such a strategy is very “aggressive” towards these same actuators due to the many on/off cycles. This phenomenon can lead to premature wear of the actuators most sensitive to these repeated state changes (especially heat pump compressors). In order to take into account the “aggressiveness” of a control scenario and to increase the lifetime of the actuators, an economic criterion with a regularization term based on the parsimony-promoting property of the ℓε-norm (ε small) is used. This term is sufficiently generic to allow the regularization of the optimal control law by taking into account discontinuous control inputs (on/off), reducing the number of actuators used at any given time or avoiding inappropriate control scenarios (alternating use of heat pump in heating/cooling modes,...). To solve the minimization problem of the non-convex ℓε-regularized economic criterion, we use an iterative algorithm recently derived in (Gabsi et al., 2018b). The effectiveness of the proposed control strategy is illustrated on the “Eco-Safe” platform at CRAN Nancy, France.
Download

Paper Nr:	28
Title:	Energy Optimisation of Cascading Neural-network Classifiers
Authors:	Vinamra Agrawal and Anandha Gopalan
Abstract:	Artificial Intelligence is increasingly being used to improve different facets of society such as healthcare, education, transport, security, etc. One of the popular building blocks for such AI systems are Neural Networks, which allow us to recognise complex patterns in large amounts of data. With the exponential growth of data, Neural Networks have become increasingly crucial to solve more and more challenging problems. As a result of this, the computational and energy requirements for these algorithms have grown immensely, which going forward will be a major contributor to climate change. In this paper, we present techniques to reduce the energy use of Neural Networks without significantly reducing their accuracy or requiring any specialised hardware. In particular, our work focuses on Cascading Neural Networks and reducing the dimensions of the input space which in turn allows us to create simpler classifiers which are more energy-efficient. We reduce the input complexity by using semantic data (Colour, Edges, etc.) from the input images and systematic techniques such as LDA. We also introduce an algorithm to efficiently arrange these classifiers to optimise gain in energy efficiency. Our results show a 13% reduction in energy usage over the popular Scalable effort classifier and a 35% reduction when compared to Keras CNN for Cifar10. Finally, we also reduced energy usage of the full input neural network (often used as the last stage in the cascading technique) by using Bayesian optimisation with adjustable parameters and minimal assumptions to search for the best model under given energy constraints. Using this technique we achieve significant energy savings of 29% and 34% for MNIST and Cifar10 respectively.
Download

Paper Nr:	33
Title:	Environmental Impact Assessment (EIA) of pH and Other Factors on Organic Photovoltaic Performance Output
Authors:	Abodunrin T. Jolaolu, Emetere M. Eterigho and Ajayi O. Olanrewaju
Abstract:	A methodical frame for evaluating the prospective ecological and health impacts of photovoltaics is necessary to consider both their negative and positive underlying effects. These pros come with a probability to advance carbon sequestration perspective. The cons are considered with a view to alleviate their negative consequences or eliminating them altogether. In this work, we report the effect of pH and dye sol ambient temperature on the environmental impact of three dye-sensitized solar cells, C.papaya, P.dulcis and C.longa to gauge their environmental impact. In the wake of several generations of photovoltaic trends a precautionary check on their effectiveness, stability, cost-competitiveness, storage time and ecological friendliness is a way of isolating carbon for storage and transportation. Thus, although the objective of this project is to investigate factors which are not tangible, discrete factors that impact photovoltaics will be analyzed using direct qualitative techniques. Using valued environmental components with spatial boundaries, and software effort estimation model to investigate the possibility for re-use, compactness and photo-corrosion among others. The significance of this research is for subsequent moderation in planning, design and to redress newer models of dye-sensitized solar cells technology for higher photovoltaic efficiency and lessen their photo-corrosive influence on our ecological system.
Download

Paper Nr:	36
Title:	Approach using the Internet of Things in the Sahel for Smart Irrigation
Authors:	Fatoumata Thiam and Cheikhou Thiam
Abstract:	Nowadays the Internet of Things (IoT) is used in many sectors such as health, military, industry, agriculture and so on. This technology is considered as a special type of ad hoc network and one of these promising areas is precision farming where it can provide important support that will facilitate agricultural practices and that can modernize and replace some of the traditional techniques. In Sahelian area, water is a critical resource due to short rainy seasons and waste of water in gross irrigation. The main activity in the Niayes area is market gardening. Urgent measures must be taken to save water reserves during the long dry season. Smart irrigation can be a solution for water wastage problem. Many techniques have been developed to solve these problems. In this paper, we can find techniques based on evapotranspiration (ET), Soil Water Assessment Tool (SWAT) and Internet of Things (IoT). This paper aims to propose a solution of smart irrigation based on IoT.
Download

Short Papers

Paper Nr:	7
Title:	Prediction Method of Plant Irrigation Timing Considering Data Imbalance
Authors:	Ryosuke Mizuno, Masaya Goto and Hiroshi Mineno
Abstract:	Predicting the plant irrigation timing is an essential task in the domain of agriculture. A model that can predict the irrigation timing in tomato cultivation can assist new farmers who do not have sufficient experience and intuition. In this study, we propose an irrigation timing prediction method based on past irrigation data, environmental data, and plant water stress using a Random Forest model, which is a general machine learning method. Our proposed model reproduces irrigation decision making by an expert farmer for new farmers. Furthermore, we propose a method for resolving imbalances, focusing on the change in the characteristics of the state of plants due to irrigation. This is because irrigation timing data has a large imbalance, which is known to be difficult to formulate. Our proposed model clarifies the characteristics of the irrigation class, and can suppress its misjudgment. We evaluated the proposed method using tomato cultivation greenhouse data in Shizuoka, Japan. The results show a recall of 92% and f-measure 69% and hence, the irrigation timing can be predicted with high accuracy. In addition, the results show that the model works effectively to automatically determine the irrigation timing in greenhouse tomato cultivation.
Download

Paper Nr:	9
Title:	Up-cycling e-Waste into Innovative Products through Social Enterprise
Authors:	Jarrod Trevathan and Tony Sharp
Abstract:	Advances in information technology have brought about numerous benefits for many aspects of life. However, the increased pervasiveness of electronic devices has also resulted in significant amounts of e-waste. E-waste now extensively occupies scarce landfill resources and contributes to pollution due to the toxic and highly reactive materials used in construction. This paper describes a unique social enterprise business model that deals with the duel problem of social disadvantage and e-waste. Through building capacity across all sectors in the community, this case study shows how a social enterprise can improve societal outcomes through training and education, whilst also dramatically reducing the amount of e-waste going to landfill. Furthermore, in addition to recycling, this social enterprise model can work with relevant stakeholders to up-cycle e-waste into practical and environmentally conscious commercial products. The social enterprise model (with partner organisations) and spin-off projects have led to multiple individual and commercial successes. This paper provides an overview of how this social enterprise operates and some of the major projects that are underway using up-cycled e-waste.
Download

Paper Nr:	10
Title:	Decision Tree Extraction using Trained Neural Network
Authors:	Nikola Vasilev, Zheni Mincheva and Ventsislav Nikolov
Abstract:	This paper introduces an algorithm for the extraction of rules from trained neural network. One of the main disadvantages of neural networks is their presumed complexity and people’s inability to fully comprehend their underlying logic. Their black box nature deems them useless in cases where the process of classification is important and must be presented in an observable and understandable way. The described algorithm extracts rules from a trained neural network and presents them in a form easily interpretable to humans. The paper demonstrates different approaches of rule extraction. Extracted rules explain and illustrate the network’s decision-making process. Rules can also be observed in the form of a tree. The presented algorithm generates rules by changing the input data and classifying them using the Reverse Engineering approach. After processing the data, the algorithm can use different approaches for creating the rules.
Download

Area 4 - Energy-Aware Systems and Technologies

Full Papers

Paper Nr:	14
Title:	A Blockchain-based Privacy-friendly Renewable Energy Community
Authors:	Stephan Cejka, Franz Zeilinger, Argjenta Veseli, Marie-Theres Holzleitner and Mark Stefan
Abstract:	The European Union’s Clean Energy Package introduces two kinds of energy communities, namely the Renewable Energy Community (REC) in the Renewable Energy Directive of 2018 and the Citizen Energy Community (CEC) in the Electricity Directive of 2019. They aim for local improvements of energy efficiency, increasing integration of renewable energy sources, and a reduction of greenhouse gas emissions, to be achieved by jointly producing, temporarily storing, sharing, consuming, and selling locally generated energy. Households and individuals shall thus be enabled to take an active part in the energy transition. When utilizing blockchain technology for the implementation of such energy communities, as proposed in current research projects, a focus must be laid on the technology-inherent area of conflict with privacy issues, especially since data on households’ energy consumption count as personal data.
Download

Short Papers

Paper Nr:	13
Title:	A Smart Energy Management System for Cross-sectoral Coupling and Water-energy Nexus
Authors:	Venkatesh Pampana, Pragya K. Gupta and Markus Duchon
Abstract:	Cross-sectoral coupling is one of the newly emerging research topics that refers to the idea of interconnecting and integrating the energy consuming sectors like buildings (heating and cooling), transport, water supply systems and other energy intensive process with the power-producing sector. The cross-sectoral integration of the water-energy nexus and the sustainability issues surrounding the availability of clean water and energy has drawn the attention to the problem from all around the globe. Smart decision-making and control systems can improve the efficiency of the overall operation of both water and energy systems. At a technological level, there have been attempts to optimize coupling points between the electricity and water systems to increase efficiency of both. Most of the optimization and smart decision-making systems focus on energy system and consider heterogeneous infrastructure in the form of energy consumption devices. In the scope of water-energy nexus, energy efficient decisions would have implications on water infrastructure. Tools and platforms for water-energy nexus are required, such that planning and executing the decisions and their implications on both energy and water infrastructure can be seen. Most of the existing controllers are specifically designed to efficiently serve either energy or water systems. In this paper, we propose a software architecture for the platform that is capable of monitoring, controlling, decision making and analysing the effect of decisions for water and energy nexus.
Download

Paper Nr:	23
Title:	Transparency in Energy Scenario Studies: Survey of Different Approaches Combining Scenario Planning, Energy System Analysis, and Multi-criteria Analysis
Authors:	Tobias Witt
Abstract:	The transition of today’s energy supply systems to renewable energy technologies requires planning processes that are usually supported by energy scenario studies. If scenario planning, energy system analysis, and multi-criteria analysis are combined in the design of such energy scenario studies, two possible method combinations can be identified in the literature. In this paper, these method combinations are discussed with regard to transparency and communication of uncertainties, which are basic requirements for energy scenarios. Finally, a clear specification of the intended purpose and of the method commendation is recommended to improve transparency in energy scenario studies and avoid over-interpretation by decision makers.
Download

Paper Nr:	29
Title:	Temporal Motifs in Smart Grid
Authors:	Rucha B. Joshi, Annada P. Behera and Subhankar Mishra
Abstract:	A complex network can be characterized by patterns. Such frequently occurring significant patterns are called motifs and in a time dependent network, they are called temporal motifs. One of the temporal networks where temporal motifs are observed and play a major role; is the Smart Grid. The energy consumption pattern across the appliances, houses, communities and entire cities help energy utility companies and consumers plan their electricity generation and consumption. The temporal motifs for the smart grid constitutes of the consumers and producers and the edge or connection represents energy flow between two participants of the network, these connections last till the power is being consumed/generated. This paper formally defines the temporal motifs for smart grid network and proposes a way to create such temporal motifs in the network. We also discuss how the temporal motifs fit into the hierarchical structure of power distribution system of Smart Grid.
Download

Paper Nr:	35
Title:	G.R.E.E.N.: Generare Risorse Ed Economie Nuove (Generating New Resources and Economies)
Authors:	Marcello Colao and Elvira Tarsitano
Abstract:	The project aims to realize interventions for phytodepuration and to evaluate the remediation capacity of the best Hemp variety (s) as a hyperaccumulator of heavy metals. Hemp (Cannabis sativa) can be used to reclaim the soils using an innovative, eco-friendly and low-cost technique called phytoremediation. Hemp is suitable to be used to recover soils, as it is easy to grow under different pedo-climatic conditions, is can be reintroduced in current cropping systems and produces high exploitable biomass for the Non-Food sector. The project aims to explore the potential uses of hemp and its contribution in promoting sustainable development (products) and investigate the potential carbon sequestration potential in the soil and evaluate different agricultural management practices, evaluating CO2, N2O and CH4 emissions related to certain climatic conditions (those provided by the IPCC - Intergovernmental Panel on Climate Change).
Download

Area 5 - Smart Cities

Short Papers

Paper Nr:	5
Title:	An Evaluation Model for Smart City Performance with Less Than 50,000 Inhabitants: A Greek Case Study
Authors:	C. Nikoloudis, E. Strantzali, T. Tounta, K. Aravossis, A. Mavrogiannis, A. Mytilinaioy, E. Sitzimi and E. Violeti
Abstract:	New intelligent technologies are seen as a key factor in fighting against climate change and improving the sustainability in cities. A smart city is a place where services use advanced information and communication technologies. According to literature, a smart city includes actions in 6 main domains: economy, environment, governance, living, mobility and people. The aim of the current study is to compose a holistic smart city ranking model for cities with population less than 50,000 inhabitants, applicable in the context of Greece. Based on the European guidelines, 25 crucial factors have been determined and 68 indicators have been adopted for the development of the evaluation model. The case of Municipality of Elefsina is analyzed and actions to improve its smartness profile are proposed. The proposed model will help cities with similar characteristics (less than 50.000 inhabitants) evaluate their status in the field of “smart cities” in order to develop programs and strategies.
Download

Paper Nr:	21
Title:	Does Project Portfolio Management Approach Fit Smart City Management?
Authors:	Filippo M. Ottaviani, Adriano Tanda and Alberto De Marco
Abstract:	Nowadays public administrations have to face many challenges related to Smart City initiatives and must coordinate these projects executing effective Smart City strategies with the adoption of an efficient portfolio management framework. Except for a few aspects, literature about this topic is scarce so this study was carried out as an attempt to evaluate the feasibility of adopting PMI’s Project Portfolio Management methodology to handle Smart City initiatives. A specific survey investigating how much Smart City projects mirror portfolio dynamics has been submitted to experts across the globe and the collected results have been analysed according to our possibilities. Results are twofold: on the one hand, it appears that the Project Portfolio Management approach could be beneficial for managing Smart City project sets, on the other hand, the Project Portfolio Management seems to be a very suitable tool when the Smart City project portfolio is heavily influenced by external stakeholders.
Download

Paper Nr:	24
Title:	PUNTOnet: Innovative Prototype of Urban Trash Containers Improving Waste Sorting and Widening the Services Offered to the City
Authors:	Ilaria Fabbri, Gabriele Lelli and Walter Nicolino
Abstract:	In order to meet European objectives in the field of urban waste collection, dustbins need to achieve a greater intelligence to recognize users and measure their garbage. The ongoing changes in waste collection are transforming ordinary garbage bins into innovative urban interface with huge potential, especially due to the capillary diffusion of waste disposal in the built environment. This paper presents a research, commissioned by one of the leading Italian multi-utility operating in environmental service, with the aim to improve municipal management of separate waste collection through the design and test of an innovative multifunctional station, in line with the principles of circular economy. The pilot project combines existing technologies regarding urban waste collection and new smart services for the city (environmental quality, ICT, electrical charging for bikes, video-monitoring and others); PUNTOnet, the innovative urban waste collection point, improves user experience, provides further services for the city and ensures, at the same time, a better management. Results obtained after a 12-month test in a real-world environment show that a more intuitive and user friendly design of waste disposal, associated to rewarding schemes positively affect household behaviour and may generate virtuous attitude for correct waste sorting.
Download

Paper Nr:	34
Title:	Information Systems Security Management for Internet of Things: Enabled Smart Cities Conceptual Framework
Authors:	Zarina Din, Dian I. Jambari, Maryati M. Yusof and Jamaiah Yahaya
Abstract:	Evolving Information Technology (IT) that drives the fourth Industrial Revolution (4IR) is disrupting organisational management. Particularly in public sector, the global movement towards Smart Cities (SC) initiative involving the Internet of Things (IoT) is motivating drastic changes to IT management methods. The heavy adoption of the IoT technologies in SC creates complexity for the information security to be managed by Information Systems (IS). IS security management approach changes according to the current nature of an organisation. As organisations prepare towards SC, there is a need to understand key concepts in managing IS security in IoT towards SC. The current IS security management for organisations is challenged in five aspects: governance, integrity, interoperability, personalisation, and self-organisation. Therefore, this study proposes an IS security conceptual framework for IoT management towards realising SC. Literature review uses the document analysis method to identify key concepts on relevant reports, for the purpose of developing a proposed conceptual framework. Based on analysis from previous research, a conceptual framework for IS Security Management in IoT-enabled SC was proposed as the outcome of this study.
Download

Paper Nr:	30
Title:	AI for Future Mobility: What Amount of Willingness to Change Does a Society Need?
Authors:	Gesa Horn and Kathrin Schönefeld
Abstract:	In addition to demographic changes in society, the success of modern forms of mobility such as automated vehicles and new mobility models is increasingly contingent on the acceptance by users from the local community. Various factors influence acceptance and the related concepts of willingness or resistance to change. A distinction can be made between general and specific willingness to change. General willingness to change is an attitude of users towards innovations, whereas specific willingness to change is situation-specific and relates solely to a specific change and its process. In the project Rethinking Mobility at the University of Wuppertal (Bergische Universität Wuppertal), the question is investigated of how to overcome resistance, enhance acceptance towards new mobility concepts and how the best basis can be created for users to form individual’s opinion on future mobility concepts. In addition, users should be enabled to perceive the advantages of new solutions and to compare them with their own values and standards. From the project's point of view, a holistic view of the complex topic of technically assisted forms of mobility is crucial for the implementation of new mobility concepts. In particular, the advantages of the integration of artificial intelligence (AI) will be examined in the project.
Download