An energy community with photovoltaic (PV) gener-ation, Electric Vehicles (EV s), static storage and grid connection is considered. The problem of sizing (PV, static battery and grid connection) and operation of the community is addressed. The problem is posed as a two stage stochastic linear optimization problem with uncertainty, modeled through scenarios, in demand, energy prices and PV generation. The objective function is to minimize the total cost (investment + operation). The main question is how much static battery storage (endogenous variable) is needed in addition to the storage provided by the EV s. The EV s batteries size are data. The effect of demand side management is also studied, and a sensitivity analysis is performed on the amortization cost of PV and the static storage. Results are illustrated on a community with 11 homes and 11 EVs.
{"title":"How much static storage capacity is needed to maximize the profitability of an energy community with electric vehicles?","authors":"Ruben Martinez Martinez, Alejandro Lopez Bueno, Sebastián Martín","doi":"10.23919/SpliTech55088.2022.9854265","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854265","url":null,"abstract":"An energy community with photovoltaic (PV) gener-ation, Electric Vehicles (EV s), static storage and grid connection is considered. The problem of sizing (PV, static battery and grid connection) and operation of the community is addressed. The problem is posed as a two stage stochastic linear optimization problem with uncertainty, modeled through scenarios, in demand, energy prices and PV generation. The objective function is to minimize the total cost (investment + operation). The main question is how much static battery storage (endogenous variable) is needed in addition to the storage provided by the EV s. The EV s batteries size are data. The effect of demand side management is also studied, and a sensitivity analysis is performed on the amortization cost of PV and the static storage. Results are illustrated on a community with 11 homes and 11 EVs.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129832783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854333
R. Jose
Urban Digital Transformation opens many opportunities for cities, but there are also risks that the evolution of our cities may be driven by the unforeseen effects of emerging technologies or by the interests of technology corporations, rather than by the ethical values and real needs of society. The active engagement of citizens can be the key for an effective alignment between technological progress and societal progress. However, most citizens are essentially unaware of changes, much less of their more profound future implications. There is also scarcity of contexts where they can engage in informed discussions about the future of their city and the cocreation of new services. In this work, we explore how Future Thinking and Responsible Research and Innovation may provide a methodological background for promoting systematic reflection about possible futures and elicit generic policy guidelines for novel urban digital services. The goal is to help closing the gap between science, policy makers and society, by helping to shape strategic agendas for innovation on Smart Cities. The key contribution is a thorough analysis of the key motivations associated with this type of societal reflection and the proposal of a novel framework for the responsible design of digital services for cities. The proposed framework is conceived to work as a large-scale and open science project, where multiple stakeholders could concurrently add contributions to this reflection framework.
{"title":"Future scenarios as a tool for citizen engagement in Smart Cities","authors":"R. Jose","doi":"10.23919/SpliTech55088.2022.9854333","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854333","url":null,"abstract":"Urban Digital Transformation opens many opportunities for cities, but there are also risks that the evolution of our cities may be driven by the unforeseen effects of emerging technologies or by the interests of technology corporations, rather than by the ethical values and real needs of society. The active engagement of citizens can be the key for an effective alignment between technological progress and societal progress. However, most citizens are essentially unaware of changes, much less of their more profound future implications. There is also scarcity of contexts where they can engage in informed discussions about the future of their city and the cocreation of new services. In this work, we explore how Future Thinking and Responsible Research and Innovation may provide a methodological background for promoting systematic reflection about possible futures and elicit generic policy guidelines for novel urban digital services. The goal is to help closing the gap between science, policy makers and society, by helping to shape strategic agendas for innovation on Smart Cities. The key contribution is a thorough analysis of the key motivations associated with this type of societal reflection and the proposal of a novel framework for the responsible design of digital services for cities. The proposed framework is conceived to work as a large-scale and open science project, where multiple stakeholders could concurrently add contributions to this reflection framework.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127628665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854313
P. Mazzeo, Simone Miglietta, P. Spagnolo, P. Carcagnì, C. Distante
Skin prick testing (SPT) is a reliable method to diagnose IgE-mediated allergic disease in patients with rhino conjunctivitis, asthma, urticaria, anaphylaxis, atopic eczema and suspected food and drug allergy. Due to the the lack of wheals public available dataset and related diameters and due to expen-sive acquisition system, in this work we investigate the feasibility to have high performance and low cost device for wheals detection and measurements. Having cheap acquisition device, it would be easier to have more acquisition stations per clinic, also speeding up the process of building the dataset. Proposed paper aims to automate the wheals measuring process, by detecting multiple wheals and by isolating them from the rest of the image, which is an essential step for the dataset building. We also proposed a cheap acquisition system made by a consumer type depth camera, Intel Realsense d435, a 3D printed arm support, a touchscreen panel displaying a GUI for the acquisitions, a Raspberry Pi 4 computer. Preliminary results showing promising performance even if they are acquired with a very cheap acquisition station proposed.
{"title":"Automatize skin prick test with a low cost Machine vision system","authors":"P. Mazzeo, Simone Miglietta, P. Spagnolo, P. Carcagnì, C. Distante","doi":"10.23919/SpliTech55088.2022.9854313","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854313","url":null,"abstract":"Skin prick testing (SPT) is a reliable method to diagnose IgE-mediated allergic disease in patients with rhino conjunctivitis, asthma, urticaria, anaphylaxis, atopic eczema and suspected food and drug allergy. Due to the the lack of wheals public available dataset and related diameters and due to expen-sive acquisition system, in this work we investigate the feasibility to have high performance and low cost device for wheals detection and measurements. Having cheap acquisition device, it would be easier to have more acquisition stations per clinic, also speeding up the process of building the dataset. Proposed paper aims to automate the wheals measuring process, by detecting multiple wheals and by isolating them from the rest of the image, which is an essential step for the dataset building. We also proposed a cheap acquisition system made by a consumer type depth camera, Intel Realsense d435, a 3D printed arm support, a touchscreen panel displaying a GUI for the acquisitions, a Raspberry Pi 4 computer. Preliminary results showing promising performance even if they are acquired with a very cheap acquisition station proposed.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125731975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854357
Ona Egbue, D. Naidu, Charles E. A. Uko
Batteries of plug-in electric vehicles (PEVs) can be used in vehicle-to-grid (V2G) systems for controlled bidirectional power flow between the vehicles and the power grid. Some benefits of V2G include the use of PEVs to provide ancillary services to the grid. However, there are concerns about PEV use for these services, particularly about the degradation of vehicle batteries due to frequent charging and discharging. In this study, a model is used to calculate the total cost of battery degradation for a significant number of vehicles as a result of V2G. Battery degradation is considered to be caused by cycling aging because this type of aging occurs during the V2G process. Simulation is conducted to determine how the battery degradation cost changes based on competing objectives. This study demonstrates the importance of considering PEV battery health during V2G operation and shows how battery degradation can be affected by the different objectives of the aggregator and PEV owners.
{"title":"Electric Vehicles and Smart Grid Integration: Analysis of Battery Degradation Cost","authors":"Ona Egbue, D. Naidu, Charles E. A. Uko","doi":"10.23919/SpliTech55088.2022.9854357","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854357","url":null,"abstract":"Batteries of plug-in electric vehicles (PEVs) can be used in vehicle-to-grid (V2G) systems for controlled bidirectional power flow between the vehicles and the power grid. Some benefits of V2G include the use of PEVs to provide ancillary services to the grid. However, there are concerns about PEV use for these services, particularly about the degradation of vehicle batteries due to frequent charging and discharging. In this study, a model is used to calculate the total cost of battery degradation for a significant number of vehicles as a result of V2G. Battery degradation is considered to be caused by cycling aging because this type of aging occurs during the V2G process. Simulation is conducted to determine how the battery degradation cost changes based on competing objectives. This study demonstrates the importance of considering PEV battery health during V2G operation and shows how battery degradation can be affected by the different objectives of the aggregator and PEV owners.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126009198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854238
D. Donchev, D. Petrova-Antonova, Petar O. Hristov
The energy and water demand is growing at an increasing rate on a global scale. This trend is especially pronounced in urban areas, which expand rapidly in size and population. At the same time, there is strong evidence to suggest that urban buildings are a major contributor to the resource and emissions footprint of human activity. For this reason, there are a number of initiatives, on a global and national level, to assess and improve the energy efficiency of buildings. This paper presents the development of a fast method for modelling the electricity, water consumption and indoor air temperature of a municipal kindergarten building in Sofia, Bulgaria. The models utilise a hybrid approach to analysing the data and successfully represents its trend. The use of statistical methods results in highly interpretable results, which can be built upon with more sophisticated techniques to achieve increased accuracy.
{"title":"An efficient hybrid regression model for energy and water consumption in a municipal kindergarten","authors":"D. Donchev, D. Petrova-Antonova, Petar O. Hristov","doi":"10.23919/SpliTech55088.2022.9854238","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854238","url":null,"abstract":"The energy and water demand is growing at an increasing rate on a global scale. This trend is especially pronounced in urban areas, which expand rapidly in size and population. At the same time, there is strong evidence to suggest that urban buildings are a major contributor to the resource and emissions footprint of human activity. For this reason, there are a number of initiatives, on a global and national level, to assess and improve the energy efficiency of buildings. This paper presents the development of a fast method for modelling the electricity, water consumption and indoor air temperature of a municipal kindergarten building in Sofia, Bulgaria. The models utilise a hybrid approach to analysing the data and successfully represents its trend. The use of statistical methods results in highly interpretable results, which can be built upon with more sophisticated techniques to achieve increased accuracy.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"51 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120821151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854225
P. Spagnolo, P. Mazzeo, Francesco Buccoliero, P. Carcagnì, C. Distante
Vehicle re-identification is currently one of the most important topics within the scientific community. Registration plate recognition may not be a sufficient solution in environments where the vehicle is observed from particular angles (e.g, laterally), or in low light conditions. For this reason, in this paper, we will focus on the study of alternative solutions, able to extract information useful for re-identification regardless of the license plate. Approaches based on the Convolutional Neural Network (CNN) will be analyzed in order to implement a methodology that can learn the salient characteristics of a vehicle and exploit them for the re-identification of the same in different areas, or at different times. The proposed approach will be tested on VeRI 776 datasets and it will be demonstrated that it overcomes the state-of-the-art approaches.
{"title":"A Deep Learning Approach for Vehicle Re-Identification","authors":"P. Spagnolo, P. Mazzeo, Francesco Buccoliero, P. Carcagnì, C. Distante","doi":"10.23919/SpliTech55088.2022.9854225","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854225","url":null,"abstract":"Vehicle re-identification is currently one of the most important topics within the scientific community. Registration plate recognition may not be a sufficient solution in environments where the vehicle is observed from particular angles (e.g, laterally), or in low light conditions. For this reason, in this paper, we will focus on the study of alternative solutions, able to extract information useful for re-identification regardless of the license plate. Approaches based on the Convolutional Neural Network (CNN) will be analyzed in order to implement a methodology that can learn the salient characteristics of a vehicle and exploit them for the re-identification of the same in different areas, or at different times. The proposed approach will be tested on VeRI 776 datasets and it will be demonstrated that it overcomes the state-of-the-art approaches.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"729 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114929777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854229
P. López-Matencio, F. González-Castaño, J. Vales-Alonso
Monitoring the performance of athletes is crucial for improving exercise quality and planning new training goals. Specifically, boxing sports demand strength and balance, requiring concentration and coordination when training with a speed bag. With a speed bag, the boxer has to strike the bag repeatedly while the bag moves fast and maintains a rhythm of hits. A monitor system for this type of training is challenging because it must be unobtrusive to keep the boxer focused on the exercise. This study introduces a methodology to get the frequency of the speed bag, which is a crucial feature to get insight into the boxer's performance. Our approach takes advantage of UHF Radio Frequency Identification (RFID) technology. RFID tags are small and can easily be embedded in the speed bag without hindering the activity of the boxer. Our methodology uses the phase of the backscattered signal as the tag and bag move together, allowing to extract the oscillation frequency. Performed simulations reflect the bag motion at an indicated frequency of 4 Hz and up to 4 meters of tag-to-reader separation. This preliminary study establishes the system's applicability, which can obtain the oscillation rate without human intervention.
{"title":"Phase-based UHF RFID approach for speed bag monitoring","authors":"P. López-Matencio, F. González-Castaño, J. Vales-Alonso","doi":"10.23919/SpliTech55088.2022.9854229","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854229","url":null,"abstract":"Monitoring the performance of athletes is crucial for improving exercise quality and planning new training goals. Specifically, boxing sports demand strength and balance, requiring concentration and coordination when training with a speed bag. With a speed bag, the boxer has to strike the bag repeatedly while the bag moves fast and maintains a rhythm of hits. A monitor system for this type of training is challenging because it must be unobtrusive to keep the boxer focused on the exercise. This study introduces a methodology to get the frequency of the speed bag, which is a crucial feature to get insight into the boxer's performance. Our approach takes advantage of UHF Radio Frequency Identification (RFID) technology. RFID tags are small and can easily be embedded in the speed bag without hindering the activity of the boxer. Our methodology uses the phase of the backscattered signal as the tag and bag move together, allowing to extract the oscillation frequency. Performed simulations reflect the bag motion at an indicated frequency of 4 Hz and up to 4 meters of tag-to-reader separation. This preliminary study establishes the system's applicability, which can obtain the oscillation rate without human intervention.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130492575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854380
N. Panunzio, Valentina Olivieri, Francesco Montecchia, P. Papoff, G. Marrocco
Breath monitoring of sedated and under-treatment patients is a key clinical procedure in hospitals. Non-invasive de-vices are preferable to perform a comfortable screening, and they assume greater importance in case the patients are newborns. Ultra High Frequency (UHF) Radio Frequency IDentification (RFID) breath sensors are passive devices that can enable low-invasive and wireless monitoring of respiration. By embedding temperature sensors within their Integrated Circuits (ICs), these devices are compact and can record temperature signals that can be correlated with typical flow-based signals. This paper aims at assessing the feasibility of involving RFID breath sensors for the monitoring of newborns breathing temperature in a real hospital ward. A pediatric disposable facemask was sensorized with a T-match dipole antenna. Following a preliminary evaluation of its electromagnetic performance and safety, in-hospital breath monitoring was performed on a newborn undergoing mild hypothermia treatment. Compared to traditional flow meter measurements, RFID results are promising and the ease-of-use and the wireless transmission of the data permit the monitoring of patients without interfering with the undergoing treatments.
{"title":"RFID-Sensorized Facemask for Wireless Monitoring of Newborn Breath Temperature during Mild Hypothermia Treatment","authors":"N. Panunzio, Valentina Olivieri, Francesco Montecchia, P. Papoff, G. Marrocco","doi":"10.23919/SpliTech55088.2022.9854380","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854380","url":null,"abstract":"Breath monitoring of sedated and under-treatment patients is a key clinical procedure in hospitals. Non-invasive de-vices are preferable to perform a comfortable screening, and they assume greater importance in case the patients are newborns. Ultra High Frequency (UHF) Radio Frequency IDentification (RFID) breath sensors are passive devices that can enable low-invasive and wireless monitoring of respiration. By embedding temperature sensors within their Integrated Circuits (ICs), these devices are compact and can record temperature signals that can be correlated with typical flow-based signals. This paper aims at assessing the feasibility of involving RFID breath sensors for the monitoring of newborns breathing temperature in a real hospital ward. A pediatric disposable facemask was sensorized with a T-match dipole antenna. Following a preliminary evaluation of its electromagnetic performance and safety, in-hospital breath monitoring was performed on a newborn undergoing mild hypothermia treatment. Compared to traditional flow meter measurements, RFID results are promising and the ease-of-use and the wireless transmission of the data permit the monitoring of patients without interfering with the undergoing treatments.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130615241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854211
Raúl Miñón, Josu Díaz-de-Arcaya, Ana I. Torre-Bastida, Gorka Zárate, Aitor Moreno-Fernandez-de-Leceta
In the last years, MLOps (Machine Learning Operations) paradigm is attracting the attention from the community, extrapolating the DevOps (Development and Operations) paradigm to the artificial intelligence (AI) development life-cycle. In this area, some challenges must be addressed to successfully deliver solutions since there are specific nuances when dealing with AI operationalization such as the model packaging or monitoring. Fortunately, interesting and helpful approaches, both from the research community and industry have emerged. However, further research is still necessary to fulfil key gaps. This paper presents a tool, MLPacker, for addressing some of them. Concretely, this tool provides mechanisms to package and deploy analytic pipelines both in REST APIs and in streaming mode. In addition, the analytic pipelines can be deployed atomically (i.e., the whole pipeline in the same machine) or in a distributed fashion (i.e., deploying each stage of the pipeline in distinct machines). In this way, users can take advantage from the cloud continuum paradigm considering edge-fog-cloud computing layers. Finally, the tool is decoupled from the training stage to avoid data scientists the integration of blocks of code in their experiments for the operationalization. Besides the package mode (REST API or streaming), the tool can be configured to perform the deployments in local or in remote machines and by using or not containers. For this aim, this paper describes the gaps this tool addresses, the detailed components and flows supported, as well as an scenario with three different case studies to better explain the research conducted.
{"title":"MLPacker: A Unified Software Tool for Packaging and Deploying Atomic and Distributed Analytic Pipelines","authors":"Raúl Miñón, Josu Díaz-de-Arcaya, Ana I. Torre-Bastida, Gorka Zárate, Aitor Moreno-Fernandez-de-Leceta","doi":"10.23919/SpliTech55088.2022.9854211","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854211","url":null,"abstract":"In the last years, MLOps (Machine Learning Operations) paradigm is attracting the attention from the community, extrapolating the DevOps (Development and Operations) paradigm to the artificial intelligence (AI) development life-cycle. In this area, some challenges must be addressed to successfully deliver solutions since there are specific nuances when dealing with AI operationalization such as the model packaging or monitoring. Fortunately, interesting and helpful approaches, both from the research community and industry have emerged. However, further research is still necessary to fulfil key gaps. This paper presents a tool, MLPacker, for addressing some of them. Concretely, this tool provides mechanisms to package and deploy analytic pipelines both in REST APIs and in streaming mode. In addition, the analytic pipelines can be deployed atomically (i.e., the whole pipeline in the same machine) or in a distributed fashion (i.e., deploying each stage of the pipeline in distinct machines). In this way, users can take advantage from the cloud continuum paradigm considering edge-fog-cloud computing layers. Finally, the tool is decoupled from the training stage to avoid data scientists the integration of blocks of code in their experiments for the operationalization. Besides the package mode (REST API or streaming), the tool can be configured to perform the deployments in local or in remote machines and by using or not containers. For this aim, this paper describes the gaps this tool addresses, the detailed components and flows supported, as well as an scenario with three different case studies to better explain the research conducted.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117235098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-05DOI: 10.23919/SpliTech55088.2022.9854291
A. Kalair, M. Seyedmahmoudian, S. Mekhilef, A. Stojcevski
Decentralized trigeneration (solar heating-cooling) for residential and commercial applications is being researched and adapted extensively. The transition from traditional uni-directional grids to bidirectional smart grids has motivated energy engineers to develop novel decentralized architectures that fully exploit distributed generation technologies. Solar heat and light stimulated trigeneration system is modeled, simulated, and analyzed over one year for subtropical climate conditions of Melbourne, Australia. The architecture replaces an electrical compressor of traditional chillers with solar heat stimulated absorption chiller. A residential building is scheduled as per standard living trends of a family of 5 individuals. The goal was to maintain livable thermal conditions (PID controlled: 26°C) and meet essential electronic needs at best. A detailed thermal and electrical performance analysis is documented using parameters such as solar fraction, collector thermal efficiency, fractional non-purchased energy, and others. The architecture was designed to meet all energy loads, thermal and electrical, with minimal auxiliary or grid energy expenditure. The analysis revealed that this unique combination of active and passive solar electro-thermal technologies has the potential to improve the overall performance and save considerable space for residential build environments. The solar photovoltaics produced power in the range 200 kW to 519 kW, active solar evacuated tube collectors produced hot water in the range 60-80°C, and passive solar thermal wall recorded storing heated air up to 70°C in summers and 40°C in winters. Heated water passed through solar heat stimulated absorption chillers to produce chilled air in range 17-19°C. An excess of 1500 watts on some summer days was recorded while no excess was available in peak winters. Solar fraction and fractional non-purchased energy showed slightly better performance than the same systems without a thermal wall.
{"title":"Dynamic Analysis of Solar Heat Stimulated Residential Absorption Cooling with Integrated Thermal Wall for Space Heating","authors":"A. Kalair, M. Seyedmahmoudian, S. Mekhilef, A. Stojcevski","doi":"10.23919/SpliTech55088.2022.9854291","DOIUrl":"https://doi.org/10.23919/SpliTech55088.2022.9854291","url":null,"abstract":"Decentralized trigeneration (solar heating-cooling) for residential and commercial applications is being researched and adapted extensively. The transition from traditional uni-directional grids to bidirectional smart grids has motivated energy engineers to develop novel decentralized architectures that fully exploit distributed generation technologies. Solar heat and light stimulated trigeneration system is modeled, simulated, and analyzed over one year for subtropical climate conditions of Melbourne, Australia. The architecture replaces an electrical compressor of traditional chillers with solar heat stimulated absorption chiller. A residential building is scheduled as per standard living trends of a family of 5 individuals. The goal was to maintain livable thermal conditions (PID controlled: 26°C) and meet essential electronic needs at best. A detailed thermal and electrical performance analysis is documented using parameters such as solar fraction, collector thermal efficiency, fractional non-purchased energy, and others. The architecture was designed to meet all energy loads, thermal and electrical, with minimal auxiliary or grid energy expenditure. The analysis revealed that this unique combination of active and passive solar electro-thermal technologies has the potential to improve the overall performance and save considerable space for residential build environments. The solar photovoltaics produced power in the range 200 kW to 519 kW, active solar evacuated tube collectors produced hot water in the range 60-80°C, and passive solar thermal wall recorded storing heated air up to 70°C in summers and 40°C in winters. Heated water passed through solar heat stimulated absorption chillers to produce chilled air in range 17-19°C. An excess of 1500 watts on some summer days was recorded while no excess was available in peak winters. Solar fraction and fractional non-purchased energy showed slightly better performance than the same systems without a thermal wall.","PeriodicalId":295373,"journal":{"name":"2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：