🕒 21.04.2023 at 13:45 UTC+3 – Online (Portal)

Chaired by Galyna Tabunshchyk and Gediminas Marcinkevičius

Methods and Tools for Minimizing the Power Consumption of Wireless Sensor Network

– by Anastasiia Yatsenko, Carsten Wolff, Anzhelika Parkhomenko, Artem Tulenkov


Nowadays, wireless sensor networks (WSN) are gaining more popularity, in particular for Smart City and Smart Building systems implementation. The ensuring of long-term uninterrupted operation of such networks can be solved on the basis of the integrated introduction of autonomous alternative power sources, energy-efficient modes of WSN components operation and modern data transfer protocols, as well as the development of software solutions to ensure reliable operation with data from sensors. As the studies have shown, data transmission in WSN is the part of the workflow which consumes a significant part of electricity. Thus, the algorithm of data collecting and transmitting based on fuzzy logic has been developed for analysis of devices’ state, assessment of sensor data changes and the time of the last connection at each iteration. It allows setting the behavior of the endpoints, whether to send data to the router or save a certain time in local memory. In critical cases (low battery charge, volume of saved data is too large to transfer), a corresponding message will be sent to the router. The developed algorithm will minimize the number of connections of the endpoints to the network, which will significantly reduce the energy consumption of each device and WSN as a whole. In addition to energy saving, the proposed approach will improve the reliability of WSN, as it also predicts the state of the available routers to eliminate the case of data loss due to router failures.

An Autonomous Energy Management Concept for Sustainable Smart Cities

– by Ulrich Ludolfinger, Maren Martens


In the course of the extreme expansion of distributed renewable energy generation systems and the increasing bottlenecks of energy resources due to political tensions, it is necessary to adapt the energy demand in cities and districts to availability. In addition, it is required to enable balancing across different energy resources, e.g., compensating gas shortages by an increased use of electricity. In this paper, we introduce a concept that makes such a load management control technically possible by using the flexibility of consumers of a city or district. To control the loads of a building autonomously multi agent deep reinforcement learning is applied, which automatically adapts to the consumption system. Dynamic energy prices are used as communication signals, they reflect the availability and demand of energy resources. We show that this concept meets all criteria for a load management system suitable for practice. Such are scalability, adaptability, data security, convergence speed, changeability and interoperability.

The Interplay Between Individual Nurse Resilience and Organizational Hospital Resilience During Critical Events

– by Neringa Gerulaitiene, Irene Georgescu, Marlene Barreda and Yana Us


The need for this research arises from the stressful and complex work environment (e.g., limited
healthcare resources) and critical events that nurses constantly face in hospitals (e.g., Covid-19 pandemic, cyber-attacks).
Resilience can refer to both an individual’s and an organization’s response to unforeseen events and their ability to return to their initial, pre-disruption state. In the scientific literature, it is stated that compared to the general population, the level of resilience is lower in nurses. The mentioned study confirms that nurses are not resilient enough and that new organizational models are needed to ensure the resilience of nurses. Researchers have highlighted the gap in research concerning the interplay between organizational hospital resilience and individual nurse resilience. A better understanding of how resilience levels interplay might help prioritize preparations and future interventions before a critical event takes place. Thus, we are aiming to investigate the interplay between individual nurse resilience and organizational hospital resilience during critical events. The research method
used was scientific literature analysis. The literature analysis revealed that individual nurse resilience affects group resilience, which in turn affects organizational resilience. In other words, the more resilient nurses are, the more resilient their hospital is to critical events.

Early Flood Monitoring and Detection System with a Machine Learning’s Neural Network Technique and IoT Platform

– by Harinidevi Nadarajan, Nagesparan Ainarappan, Farah Adilah Binti Jamaludink


Floods are the most common type of natural calamity and arise when the normally dry land is inundated by water overflow. Property destruction, agricultural damage, animal mortality, waterborne infections, and loss of life were among the devastating environmental and economic consequences of this natural catastrophe, impacting millions of people worldwide. Due to ongoing climate change, the indirect influence of tropical winds, rapid urbanization, clearing of green zones, logging and monsoon rains, more widespread flooding is expected in the future. Malaysia has been repeatedly plagued by flood disasters, which have gotten significantly more severe in the previous decade. This research presents an early flood monitoring and detection system using GSM SIM900A and IoT to detect floods. The system examines a range of natural parameters such as temperature, humidity, water flow rate and its level using sensors. All captured data will be delivered to the IoT platform via Arduino Uno for real-time monitoring information. The GSM module delivers SMS alerts to the user about rising water levels. The sensor’s data will then be processed by the LSTM model to predict flood using water level data by 1-hour time step ahead. This would give enough lead time to warn the residents to save their belongings and evacuate to a safer location. The suggested LSTM model attained MSE, RMSE, and MAE values of 0.001, 0.03, and 0.019 respectively, and outperformed the naive forecast baseline.

Smart City Development Using Transit-Oriented-Development (T.O.D) and Walkability

– by Jaeshik Shin, Young Hoon Kwak , Changwoo Park


Walkability is one of the fundamental transport components to consider when planning a new city. However, there has been a lack of research nor application on defining a detailed correlation between walkability and Transit Oriented Development (T.O.D) components, particularly when planning a new smart city. This paper aims to identify the correlation between the T.O.D components and walkability in high- and low-density cities using a machine learning algorithm. To do so, this study analyzes key explanatory variables affecting the increase or decrease of walkability. Then, a decision-tree ensemble CATBoost model is used to predict walkability using public transit data, including shared transport modes such as bicycle and electric quick scooters, supply characteristics, amenities information, street networks, and urban future network elements. By using the SHAP algorithm, the explainable A.I. method, this study seeks to determine which T.O.D component affects walkability positively or negatively.

Architecture Approach to Manage Electricity Utility in a Smart City

– by Sello S. Pokane, Musa C. Shilenge , Arnesh Telukdarie


Local and remote control and equipment monitoring is vital in various trades such as electricity utilities, water treatment, manufacturing, etc. Hence, most organizations use Supervisory Control and Data Acquisition (SCADA) systems. Thus, the appropriate connection of SCADA components and smart city enabling technologies is vital for the optimum functioning of a smart energy management system. Information and Operational Technologies (IT/OT) are essential in smart cities to enable a seamless data flow to improve city services and the quality of life. Furthermore, due to the limitations of legacy SCADA systems, such as inflexibility. This study seeks to develop an electricity utility SCADA system architecture of a smart city using modern technologies such as cloud computing. The study finds that an IoTSCADA system integrated with other smart city applications delivers the benefits of smart energy management and the goals of smart cities.