SMARTGREENS 2022 Abstracts

Area 1 - Smart and Digital Services

Full Papers

Paper Nr:	4
Title:	End-user Development for Smart Spaces: A Comparison of Block and Data-flow Programming
Authors:	Marcel Altendeitering and Sonja Schimmler
Abstract:	Block and data-flow programming are well-known concepts for enabling end users to visually create their own customized solutions. They both offer comprehensive visual interfaces and are becoming popular within the smart spaces domain. However, there is currently no systematic, comparative evaluation of the two concepts in the domain. In this user study, we implemented two prototypes for block and data-flow programming and compared their performance on typical usage scenarios in common smart spaces. We used a mixed methods approach of quantitative and qualitative analysis to gain an in-depth understanding of the user experience. Our results show that data-flow programming is overall better received by users than block programming and is considered being state-of-the art and visually more appealing. For block programming, our results reveal that participants appreciate the playful character and the feedback provided. Our study contributes to the improvement of block and data-flow solutions in place and discusses aspects relevant to the future advancement of end-user development in smart spaces.
Download

Paper Nr:	17
Title:	Evaluation of Smart City Models: A Conceptual and Structural View
Authors:	Leonard Walletzký, Odonchimeg Bayarsaikhan, Mouzhi Ge and Zuzana Schwarzová
Abstract:	With the rapid development of smart cities, there has been a variety of smart city models that are proposed to facilitate the smart city design and service architecture. Meanwhile those smart city models also create complexity to follow the models and it is difficult to observe how the models can work collaboratively as well as how to possibly improve the models. Therefore, this paper firstly classifies the smart city models with a conceptual and structural view, where the conceptual models focus on the interactions of components and the structural models are featured by layers with processes. Based on the model classification, the paper further evaluates the models with service structure, interoperability, multi-context and adaptability. The evaluation results can be used to compare, select and improve the smart city models and service design.
Download

Short Papers

Paper Nr:	12
Title:	Privacy-preserving Information Security for the Energy Grid of Things
Authors:	Mohammed Alsaid, Nirupama Bulusu, Abdullah Bargouti, N. S. Fernando, John M. Acken, Tylor Slay and Robert B. Bass
Abstract:	Smart grid infrastructure relies on information exchange between multiple actors in order to ensure system reliability. These actors include but are not limited to smart loads, grid control, and energy management technologies. As information exchange between these actors is susceptible to cyber-attacks, security and privacy issues are indispensable to ensure a reliable and stable grid. This position paper proposes a privacy-preserving, trust-augmented secure scheme for a smart grid implementation.
Download

Paper Nr:	19
Title:	BIKE2WORK: A Shift Towards Sustainable Mobility
Authors:	Antonio Bucchiarone, Annapaola Marconi, Piergiorgio Cipriano and Luca Giovannini
Abstract:	Encouraging a shift towards sustainable mobility habits based on active mobility is a key challenge for many cities, since they are increasingly facing problems of traffic congestion, road safety, energy dependency and air pollution. Active modes, as cycling, which are also the least polluting, should be particularly encouraged, especially for local recurrent journeys (i.e., home–to–school, home–to–work). In this context, addressing and mitigating commuter-generated traffic requires engaging public and private stakeholders through new innovative and collaborative approaches that focus not only on supply (e.g., roads and vehicles), but also on transportation demand management. In this paper we propose an approach to home–to–work mobility able to support the company Mobility Manager (MM) acting on the promotion of sustainable mobility and transport demand management by analysing the problems, needs and habits of employees, and trying to orient them towards new sustainable transport habits.
Download

Area 2 - Smart Infrastructures and Smart Buildings

Short Papers

Paper Nr:	3
Title:	SP4LC: A Method for Recognizing Power Consumers in a Smart Plug
Authors:	Dániel I. Németh and Kálmán Tornai
Abstract:	Electrical load classification is a crucial task related to balance management in smart electrical grids. The classification algorithms and methods enable the smart system to schedule and adjust the grid load to meet the production capabilities. Fast decision-making is key to creating a responsive grid, especially when grid operators utilize renewable energy sources such as wind or solar power. This paper proposes new approach Smart Plug for Load Classification, an active load classification system to recognize the connected devices based on their load with less than 10 seconds of measurement data. Also, we propose an IoT-capable measurement device and show the collected data’s classification results with multiple methods suited for both Edge Computing and Cloud computation.
Download

Paper Nr:	5
Title:	Accelerated Variant of Reinforcement Learning Algorithms for Light Control with Non-stationary User Behaviour
Authors:	Nassim Haddam, Benjamin C. Boulakia and Dominique Barth
Abstract:	In the context of smart building energy management, we address in this work the problem of controlling light so as to minimise energy usage of the building while maintaining the satisfaction of the user regarding comfort using a stateless Reinforcement Learning approach. We consider that the user can freely interact with the building and changes the intensity of the light according to his comfort. Moreover, we consider that the behaviour of the user depends not only on present conditions but also on past behaviour of the control system. In this setting, we use the pursuit algorithm to control the signal and investigate the impact of the discretization of the action space on the convergence speed of the algorithm and the quality of the policies learned by the agent. We propose ways to accelerate convergence speed by varying the maximal duration of the actions while maintaining the quality of the policies and compare different solutions to achieve it.
Download

Paper Nr:	6
Title:	Simulating Weather Events on a Real-world Map using Unity 3D
Authors:	Hamza Noueihed, Heba Harb and Joe Tekli
Abstract:	During the past decade, 3D simulation models have gained importance in the development of software solutions that aim to mimic real-world events and phenomena with increasing levels of accuracy and detail. In this paper, we introduce VOWES, a Virtual Outdoor Weather Event Simulator to replicate and measure outdoor weather events in vivid 3D visualizations. We make use of the Unity 3D engine to build the simulator environment and its virtual sensors, and integrate the Mapbox SDK and the WeatherStack API for realistic real-world weather mapping. We have conducted a large battery of experiments involving 30 human testers, considering various evaluation criteria. Results highlight VOWES’ quality and performance, and its ability to simulate complex weather environments with large numbers of sensors and weather phenomena.
Download

Paper Nr:	18
Title:	Application of AI-based Image Processing for Occupancy Monitoring in Building Energy Management
Authors:	Andreas Reichel, Jens Döge, Dirk Mayer and Jan Bräunig
Abstract:	Smart Buildings enable significant savings in energy and CO2 emissions by model-predictive methods. The building users have a considerable influence on the energetic building management. On the one hand, they dictate the comfort parameters to be set. On the other hand, they generate internal thermal gains through their presence, affect humidity, consume oxygen and produce carbon dioxide. The more precisely the user behavior is known, the more precisely and resource-efficiently the room climate control can be adapted to this user behavior. In this paper, an intelligent vision-based sensor concept is proposed and tested that is capable to estimate occupancy and activity inside a building. The contribution initially concentrates on functional buildings, since here, compared to residential buildings, there is an even greater need for use-oriented room air conditioning, including savings potential.
Download

Area 3 - Sustainable Computing and Systems

Full Papers

Paper Nr:	11
Title:	Indirect Network Impact on the Energy Consumption in Multi-clouds for Follow-the-renewables Approaches
Authors:	Miguel S. Vasconcelos, Daniel Cordeiro and Fanny Dufossé
Abstract:	Cloud computing has become an essential component of our digital society. Efforts for reducing its environmental impact are being made by academics and industry alike, with commitments from major cloud providers to be fully operated by renewable energy in the future. One strategy to reduce nonrenewable energy usage is the “follow-the-renewables”, in which the workload is migrated to be executed in the data centers with the most availability of renewable energy. In this paper, we study the indirect impacts on the energy consumption caused by the additional load in the network generated from the live migrations of the “follow-the-renewables” approaches. We then provide an algorithm that thoroughly considers the network to schedule the live migrations and, combined with an accurate estimation model for the duration of the migrations, is able to perform the live migrations without network congestion with the same or even reducing the brown energy consumption in comparison to other state-of-the-art algorithms.
Download

Short Papers

Paper Nr:	7
Title:	Apply Deep Learning in Real-time Customer Detection and Classification System for Advertisement Decision Making at Supermarket
Authors:	Dang T. Phuc, Dau S. Hieu, Nguyen M. Hoang and Tran M. Khoa
Abstract:	Shopping in shopping malls and supermarket is gradually increasing and replacing traditional market because of the convenient conditions such as full of products, clean place with all time air-conditioner, modern environment, etc. Supermarket owner always want to find the way that attract more and more customers come to the supermarket as well as advertise their products to the customers as many as possible. In order to offer relevant and attractive advertising to customers, detection and classification customers entering to the supermarket is taken into consideration. Due to the characteristics different customer groups, the relevant products should be showed to attract customer, help them save the time for finding products. In this paper, we build a real-time customer detection and classification system at the supermarket. The goal of this proposed Internet of Things (IoT) system is automatically show the suitable advertising clips to many customers at the right time. We build a classification model using deep learning with a large amount of data. The dataset is collected from reality and labelled with five different object classes. To ensure reliability, 7000 images are collected from different conditions such as variations in camera used, bad lighting, angles, and not stable background. The data is trained on YOLOv4 and YOLOv4-tiny models. The models are deployed on the embedded system with the Jetson Nano device as the processor. We compare the accuracy and speed of the two models on the same embedded system, analyse the results, and chose the best model according to the specific system requirements.
Download

Paper Nr:	15
Title:	Value Proposition for Smart Retrofit Solutions
Authors:	Aditya Mairal, Michael Muller and Todd Rossi
Abstract:	Smart retrofitting can include automation, simulation, data collection and optimization of manufacturing processes. It is strongly coupled with the concept of Industrial Internet of Things (IIoT). The adoption of smart retrofitting in manufacturing is found to be modest despite their benefits. Lack of structured value proposition approach by application is suspected as one of the major reasons for lower adoption. This paper provides a value proposition matrix and applies the same to ten low-hanging fruit smart retrofit applications. This would provide a framework for understanding the full value a smart retrofit applications can provide. The matrix can also be used to rank the smart retrofit solutions.
Download

Area 4 - Energy-Aware Systems and Technologies

Full Papers

Paper Nr:	8
Title:	Modeling of Power Supply Systems Equipped with Double Two Wires and Earth Transmission Lines
Authors:	Yuri Bulatov, Andrey Kryukov, Le Van Thao, Konstantin Suslov and Tran D. Hung
Abstract:	Power supply systems (PSS) of the agro-industrial complex, as well objects located in the areas remote from the networks of electric power systems, sometimes use electric transmission lines (ETLs) that exploit the ground as a conducting part. When currents flow in the ground, it causes electrical safety issues. To solve them, double two wires and earth (TWE) lines can be used. Such lines use special transformers, in which the voltage vectors of the grounded terminals have an angular shift of 180º. Due to this, there are no currents in the ground a symmetrical mode. In the context of digitalization of the electric power industry, creating computer models of such PSSes that adequately simulate stationary modes is of particular relevance. This paper presents the results of studies aimed at the implementation of computer models of power supply systems that incorporate double TWE lines. Constructive diagrams of ETLs with double TWE lines are proposed. Simulation was carried out by means of the Fazonord software package. The simulation results drew us to the following conclusions: in comparison with a double-circuit ETL, a double TWE line can significantly reduce the cost of non-ferrous metal; the asymmetrical design of this ETL causes a decrease in the quality indicators of electricity at its receiving end; in addition, higher power losses are observed; the double TWE line can be implemented on the basis of two or four single-phase shielded cables.
Download

Paper Nr:	10
Title:	Energy-Aware Deep Learning for Green Cyber-Physical Systems
Authors:	Supadchaya Puangpontip and Rattikorn Hewett
Abstract:	Today's green computing has to deal with prevalent Cyber-Physical Systems (CPSs), engineered systems that tightly integrate computation and physical components. Green CPS aims to use electronic/computer devices and resources to perform operations as efficiently and eco-friendly as possible. With the rise of smart technology combining with Artificial Intelligence Deep Learning (DL) in Internet of Things and CPSs, continuing use of these compute intensive CPS software like DL can negatively impact energy resources and environments. Much research has advanced green hardware and physical component development. Our research aims to develop green CPSs by making them energy aware. To do this, we propose an analytical modelling approach to quantifying energy consumption of software artifacts in the CPS. The paper describes the approach through energy consumption modelling of DL in distributed CPS due to the popular deployment of DL in many modern CPSs. However, the approach is general and can be applied to any CPS. The paper illustrates the application of our approach for energy management in scaling and designing smart farming CPS that monitors crop health.
Download

Short Papers

Paper Nr:	14
Title:	Smart Energy Buildings: PV Integration and Grid Sensitivity for the Case of Vietnam
Authors:	Wolfram Heckmann, Nguyen Huu Duc, Dayana C. Granford Ruiz, Siddhi Shrikant Kulkarni and Nguyen Ngoc Van
Abstract:	The Vietnamese government is pushing for higher implementation of distributed photovoltaic (PV) generation through various policies. Due to the decreasing trend in feed-in tariff (FIT) prices, self-consumption of energy is an increasingly viable option. The increased PV penetration in the distribution grid also leads to changes in the voltage profile on the distribution line, which needs to be regulated. The paper discusses a study where an energy management system (EMS) is implemented for a commercial building in Hanoi after modelling the respective generating units. As a next step in the study, the self-consumption behaviour of the building is analyzed and the voltage regulation for a sample distribution grid in Vietnam is implemented.
Download

Paper Nr:	16
Title:	ETAP Simulations of Adaptive Overcurrent Protection Scheme for Distribution Network with Microgrids
Authors:	Paul J. Palayil, Ishan Desai and Divyesh Mangroliya
Abstract:	A microgrid (MG) includes Distributed Energy Resources (DER), controllable load with adequate protection scheme in an Electrical Power Distribution System. Renewable energy sources (RES) is expected to provide efficient, low cost and clean energy with decentralized generation, storage and local consumption with MG. In this paper an Adaptive Over Current Relays (AOCR) scheme in distribution networks (DN) considering intermittency of Distributed Generation (DG) operations using a fuzzy logic controller (FLC) is proposed. The onsite study included actual verification of protection scheme, the impact of DG on protection system and protection coordination. A part of the IEEE 44 nodes radial distribution test feeder is taken for modelling & simulating the proposed AOCR using Electrical Transient Analyzer Program (ETAP) software environment.
Download

Paper Nr:	20
Title:	DECART: Planning for Decarbonising Transport Sector with Predictive Analytics - An Irish Case Study
Authors:	Meghana Kshirsagar, Gauri Vaidya, Shravani Rajguru, Pruthviraj Jadhav, Hrushabh Kale, Nishanth Shanmugam, Conor Ryan and Vivek Kshirsagar
Abstract:	This article explores assessing the impact of the decarbonisation of the transport sector using an evidence-based approach incorporating data analysis and advanced machine learning (ML) modelling. We investigate the radical behavioural and societal changes needed for the decarbonisation of the transport sector in Ireland. We perform a study through our system DECArbonisation in Road Transport (DECART), a suite of statistical and time series ML models for facilitating policy making, monitoring and advising governments, companies and organisations in the transport sector. Based on data analysis and through scenario-modelling approaches, we present alternatives to policy and decision makers to achieve goals in mitigation of carbon emissions in road transport. The models depict how changes in mobility patterns in road transport affect CO2 emissions. Through insights obtained from the models, we infer that renewable energy in Ireland has the potential for meeting the growing electricity needs of electric vehicles. Experimentation is conducted on real-world datasets such as traffic, motor registrations, and data from renewable sources such as wind farms, for building efficient ML models. The models are validated in terms of accuracy, based on their potential to capture hidden insights from real-world events and domain knowledge.
Download

Area 5 - Smart Cities

Short Papers

Paper Nr:	9
Title:	Planning and Design Challenges for Smart Infrastructures: The Chiloé Island Case
Authors:	Stefania Pareti, David Flores, Loreto Rudolph and Martina Pareti
Abstract:	The objective of this study is to explore how to plan and design a type of green construction along with implementing urban governance plans, facilitating smart infrastructure and, in turn, the sustainability of the territory. The island of Chiloé, in southern Chile, has been selected as a case study, due to: (1) it has a unique vernacular architecture based on Smart buildings (2) it has a geographic morphology that has allowed from its genesis as a city to build in wood and sustainable materials; (3) it is going through a transition towards gentrification, due to its tourist attraction; (4) has a governance system. The methodology is developed through analysis of secondary sources, regarding interviews with: key actors of the place, together with developing a governance model adapted to the territory, finally a detailed analysis of a stilt house is made. It is concluded that planning and designing a type of Green construction together with implementing urban governance plans, if it facilitates the Smart infrastructure and in turn the sustainability of the territory.
Download

Paper Nr:	21
Title:	Smart Cities: The Role of Entrepreneurship for Urban Leftover Spaces
Authors:	Jasim Azhar and Sidra A. Qureshi
Abstract:	Smart City focuses on smarter solutions for the future to promote quality of life. Thus, the role of ICT interventions, innovations and creativity are emphasised to sustain economic and urban growth. The literature highlights business-led urban development is a major aspect of smart cities for entrepreneurship and identifies their inter-dependent role in economically efficient solutions. A barrier would be unused urban spaces as an inefficient allocation of resources. Entrepreneurship encourages innovation while smart cities adopt interventions that provide opportunities and a supporting environment for entrepreneurial activities. This paper explores the prospective relationship of using urban leftover spaces for entrepreneurial activities in smart cities. The study evaluates and analyses key attributes of entrepreneurship as to develop smart spaces for social sustainability.
Download