Pub Date : 2018-05-01DOI: 10.1109/WAINA.2018.00139
Pacome L. Ambassa, Anne Kayem, S. Wolthusen, C. Meinel
In rural/remote areas, resource constrained smart micro-grid (RCSMG) architectures can offer a cost-effective power management and supply alternative to national power grid connections. RCSMG architectures handle communications over distributed lossy networks to minimize operation costs. However, the unreliable nature of lossy networks makes privacy an important consideration. Existing anonymisation works on data perturbation work mainly by distortion with additive noise. Apply these solutions to RCSMGs is problematic, because deliberate noise additions must be distinguishable both from system and adversarial generated noise. In this paper, we present a brief survey of privacy risks in RCSMGs centered on inference, and propose a method of mitigating these risks. The lesson here is that while RCSMGs give users more control over power management and distribution, good anonymisation is essential to protecting personal information on RCSMGs.
{"title":"Privacy Risks in Resource Constrained Smart Micro-Grids","authors":"Pacome L. Ambassa, Anne Kayem, S. Wolthusen, C. Meinel","doi":"10.1109/WAINA.2018.00139","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00139","url":null,"abstract":"In rural/remote areas, resource constrained smart micro-grid (RCSMG) architectures can offer a cost-effective power management and supply alternative to national power grid connections. RCSMG architectures handle communications over distributed lossy networks to minimize operation costs. However, the unreliable nature of lossy networks makes privacy an important consideration. Existing anonymisation works on data perturbation work mainly by distortion with additive noise. Apply these solutions to RCSMGs is problematic, because deliberate noise additions must be distinguishable both from system and adversarial generated noise. In this paper, we present a brief survey of privacy risks in RCSMGs centered on inference, and propose a method of mitigating these risks. The lesson here is that while RCSMGs give users more control over power management and distribution, good anonymisation is essential to protecting personal information on RCSMGs.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130002463","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00090
Aqdas Naz, N. Javaid, T. N. Qureshi, M. Imran, Mujahid Ali, Z. Khan
Now a days home energy management system is being used all across the world. Ever increasing energy demands has brought many challenges in aspect of luxury and cost saving. Our work is mainly based on efficient utilization of resources by smart planning. In this aspect scheduling of home electronic devices play vital role. Calculating energy consumption and its timings paved the way to utilize it in most efficient way. In our work we have proposed hybrid of meta heuristic techniques such as HSA, EDE, BPSO. Key feature of state of art techniques has been merged together to evolve a technique that works excellent not only in aspect of cost saving, peak average reduction as well as provision of adequate user comfort. In order to evaluate our proposed technique we have considered set of nine devices includes interruptible, non interruptible and base devices in single home and perform scheduling by advance meter controller (AMC) to further send demand response to utility by smart meters. In response, utility provides real time pricing signals. Two way communication is establish to perform scheduling meticulously.
{"title":"EDHBPSO: Enhanced Differential Harmony Binary Particle Swarm Optimization for Demand Side Management in Smart Grid","authors":"Aqdas Naz, N. Javaid, T. N. Qureshi, M. Imran, Mujahid Ali, Z. Khan","doi":"10.1109/WAINA.2018.00090","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00090","url":null,"abstract":"Now a days home energy management system is being used all across the world. Ever increasing energy demands has brought many challenges in aspect of luxury and cost saving. Our work is mainly based on efficient utilization of resources by smart planning. In this aspect scheduling of home electronic devices play vital role. Calculating energy consumption and its timings paved the way to utilize it in most efficient way. In our work we have proposed hybrid of meta heuristic techniques such as HSA, EDE, BPSO. Key feature of state of art techniques has been merged together to evolve a technique that works excellent not only in aspect of cost saving, peak average reduction as well as provision of adequate user comfort. In order to evaluate our proposed technique we have considered set of nine devices includes interruptible, non interruptible and base devices in single home and perform scheduling by advance meter controller (AMC) to further send demand response to utility by smart meters. In response, utility provides real time pricing signals. Two way communication is establish to perform scheduling meticulously.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124449107","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00101
A. Sawada, Dilawaer Duolikun, Ryoma Watanabe, T. Enokido, M. Takizawa
In application processes like Web and databases, files and databases are manipulated on servers. Thus, both CPU and storage resources are used to perform application processes. In this paper, we propose a computation model to give the expected termination time of each application process. Here, computation operations and storage operations of a process are integrated into virtual computation steps. Then, we propose an SGEAG (Simple Globally-Energy-Aware for General processes) algorithm to select a server to perform a new process issued by a client, which is expected to consume the minimum electric energy to perform not only the new process but also every current process. In the evaluation, we show the electric energy consumed by servers and the average execution time of processes can be more reduced in the SGEAG algorithm than the other algorithms.
在Web和数据库等应用程序进程中，文件和数据库是在服务器上操作的。因此，CPU和存储资源都用于执行应用程序进程。在本文中，我们提出了一个计算模型来给出每个应用进程的预期终止时间。在这里，一个进程的计算操作和存储操作被集成到虚拟计算步骤中。然后，我们提出了一种SGEAG (Simple global - energy - aware for General processes)算法，用于选择服务器来执行客户端发出的新进程，该算法期望在执行新进程和每个当前进程时消耗最少的电能。在评估中，我们发现SGEAG算法比其他算法更能减少服务器消耗的电能和进程的平均执行时间。
{"title":"A Simple Algorithm to Select Energy-Efficient Servers for Storage and Computation Processes","authors":"A. Sawada, Dilawaer Duolikun, Ryoma Watanabe, T. Enokido, M. Takizawa","doi":"10.1109/WAINA.2018.00101","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00101","url":null,"abstract":"In application processes like Web and databases, files and databases are manipulated on servers. Thus, both CPU and storage resources are used to perform application processes. In this paper, we propose a computation model to give the expected termination time of each application process. Here, computation operations and storage operations of a process are integrated into virtual computation steps. Then, we propose an SGEAG (Simple Globally-Energy-Aware for General processes) algorithm to select a server to perform a new process issued by a client, which is expected to consume the minimum electric energy to perform not only the new process but also every current process. In the evaluation, we show the electric energy consumed by servers and the average execution time of processes can be more reduced in the SGEAG algorithm than the other algorithms.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126920857","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00096
Alfredo J. Perez
We address the problem of the placement of static sensors and relays to monitor specific locations in an area assuming a single-tiered wireless sensor network model with limited communication and sensing constraints. We present a multiobjective optimization model with two conflicting objectives: total number of devices used in the placement and total energy dissipated by the placement. To optimize the model, we propose the Multiobjective Sensor Placement Optimizer (M-SPOT) algorithm, which is a hybrid evolutionary algorithm that combines the Non-Sorting Genetic Algorithm 2 (NSGA2) algorithm with local search heuristics. We evaluate the performance of M-SPOT by simulating the placement of sensors and relays. We found that the utilization of local search heuristics greatly contribute to find better placements when compared to the NSGA2 algorithm.
{"title":"M-SPOT: A Hybrid Multiobjective Evolutionary Algorithm for Node Placement in Wireless Sensor Networks","authors":"Alfredo J. Perez","doi":"10.1109/WAINA.2018.00096","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00096","url":null,"abstract":"We address the problem of the placement of static sensors and relays to monitor specific locations in an area assuming a single-tiered wireless sensor network model with limited communication and sensing constraints. We present a multiobjective optimization model with two conflicting objectives: total number of devices used in the placement and total energy dissipated by the placement. To optimize the model, we propose the Multiobjective Sensor Placement Optimizer (M-SPOT) algorithm, which is a hybrid evolutionary algorithm that combines the Non-Sorting Genetic Algorithm 2 (NSGA2) algorithm with local search heuristics. We evaluate the performance of M-SPOT by simulating the placement of sensors and relays. We found that the utilization of local search heuristics greatly contribute to find better placements when compared to the NSGA2 algorithm.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133820202","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00150
A. Navarra, D. Cacciagrano
In distributed computing, many tasks have been studied involving mobile entities - also called robots - with weak capabilities. A well-known scenario is that in which robots operate in Look-Compute-Move (LCM) cycles. During each cycle, a robot acquires a snapshot of the surrounding environment (Look phase), then executes an appropriate algorithm by using the obtained snapshot as input (Compute phase), and finally moves toward a desired destination, if any (Move phase). In this context, we consider robots that have to visit a partially ordered set of locations. A solution to the problem is the assignment to each robot of a trajectory to follow in order to visit the required locations. The resolution of the task is subject to two main constraints. Robots have to minimize the energy spent to accomplish an assigned trajectory, and they have to avoid collisions among each other. The minimization of the energy is expressed in terms of the number of turns a robot has to perform in between two different locations. This equals the number of bends the assigned trajectory contains in between such locations. In general, the problem is known to require Ω(n) bends per connection, with n being the number of locations, even if considering just two robots involved. We study the case where the locations that a single robot has to visit are represented as colored points in the Euclidean plane, and only two colors are provided. This means the partial order among the locations is just based on two colors per robot. In this case, we provide a constructive solution for two robots with five bends per connection.
{"title":"Energy Saving and Collision-Free Motion Planning for Oblivious Robots","authors":"A. Navarra, D. Cacciagrano","doi":"10.1109/WAINA.2018.00150","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00150","url":null,"abstract":"In distributed computing, many tasks have been studied involving mobile entities - also called robots - with weak capabilities. A well-known scenario is that in which robots operate in Look-Compute-Move (LCM) cycles. During each cycle, a robot acquires a snapshot of the surrounding environment (Look phase), then executes an appropriate algorithm by using the obtained snapshot as input (Compute phase), and finally moves toward a desired destination, if any (Move phase). In this context, we consider robots that have to visit a partially ordered set of locations. A solution to the problem is the assignment to each robot of a trajectory to follow in order to visit the required locations. The resolution of the task is subject to two main constraints. Robots have to minimize the energy spent to accomplish an assigned trajectory, and they have to avoid collisions among each other. The minimization of the energy is expressed in terms of the number of turns a robot has to perform in between two different locations. This equals the number of bends the assigned trajectory contains in between such locations. In general, the problem is known to require Ω(n) bends per connection, with n being the number of locations, even if considering just two robots involved. We study the case where the locations that a single robot has to visit are represented as colored points in the Euclidean plane, and only two colors are provided. This means the partial order among the locations is just based on two colors per robot. In this case, we provide a constructive solution for two robots with five bends per connection.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129381699","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00144
L. Caviglione, A. Merlo, M. Migliardi
Interconnected and always on devices are continuously and rapidly growing in number and, according to a study from Cisco, will be three times the number of humans on earth in 2021. Unfortunately, recent events such as the DDoS mounted using the Mirai botnet, have shown that the level of resilience to intrusion and hacking of these devices is far from optimal and puts the systems connected to the Internet of Things in serious danger. Among such systems, industrial systems that are now being integrated into the IoT ecosystem, have revealed to be weak against the threat coming from the IT world. Such previously inexistent scenario opens up to a plethora of new attack patterns leveraging previously unexploited techniques. Among these, we argue that convert channels built by leveraging information hiding techniques could be exploited. To this aim, this position paper introduces the usage of convert channels, built on information hiding techniques, in IoT scenarios.
{"title":"Covert Channels in IoT Deployments Through Data Hiding Techniques","authors":"L. Caviglione, A. Merlo, M. Migliardi","doi":"10.1109/WAINA.2018.00144","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00144","url":null,"abstract":"Interconnected and always on devices are continuously and rapidly growing in number and, according to a study from Cisco, will be three times the number of humans on earth in 2021. Unfortunately, recent events such as the DDoS mounted using the Mirai botnet, have shown that the level of resilience to intrusion and hacking of these devices is far from optimal and puts the systems connected to the Internet of Things in serious danger. Among such systems, industrial systems that are now being integrated into the IoT ecosystem, have revealed to be weak against the threat coming from the IT world. Such previously inexistent scenario opens up to a plethora of new attack patterns leveraging previously unexploited techniques. Among these, we argue that convert channels built by leveraging information hiding techniques could be exploited. To this aim, this position paper introduces the usage of convert channels, built on information hiding techniques, in IoT scenarios.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125598526","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00054
Jianhua Yang, Yongzhong Zhang
In this paper, we propose an approach to use postal mail system to teach computer networking communication. From many years of teaching computer networking class in college, we found that most students are hard to understand some key concepts well in computer networking communication, such as packet, encapsulation, packet switching vs. circuit switching, routing, IP address, and MAC address. We explored to use postal mail system, esp. how a letter travels, to help students understand packet switching in computer network, and received positive feedback. In this paper, we first modeling postal mail system and packet switching computer network, then compare the two systems in terms of layering design, communication architecture, packet encapsulation, IP address, packet routing, datalink layer delivery, and AS. The whole idea is to help college students learn computer networking by referring to a real world system which can be easily understood.
{"title":"Using Postal Mail System to Teach Packet Switching in Computer Networks","authors":"Jianhua Yang, Yongzhong Zhang","doi":"10.1109/WAINA.2018.00054","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00054","url":null,"abstract":"In this paper, we propose an approach to use postal mail system to teach computer networking communication. From many years of teaching computer networking class in college, we found that most students are hard to understand some key concepts well in computer networking communication, such as packet, encapsulation, packet switching vs. circuit switching, routing, IP address, and MAC address. We explored to use postal mail system, esp. how a letter travels, to help students understand packet switching in computer network, and received positive feedback. In this paper, we first modeling postal mail system and packet switching computer network, then compare the two systems in terms of layering design, communication architecture, packet encapsulation, IP address, packet routing, datalink layer delivery, and AS. The whole idea is to help college students learn computer networking by referring to a real world system which can be easily understood.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116228932","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00124
C. Baudoin
Cloud computing could be on a collision course with the increasingly complex and restrictive web of laws and regulations that govern where certain types of data may be located. This paper reviews the definition of data residency, the risks it poses to cloud customers and cloud providers, and actions they can take to manage those risks.
{"title":"The Impact of Data Residency on Cloud Computing","authors":"C. Baudoin","doi":"10.1109/WAINA.2018.00124","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00124","url":null,"abstract":"Cloud computing could be on a collision course with the increasingly complex and restrictive web of laws and regulations that govern where certain types of data may be located. This paper reviews the definition of data residency, the risks it poses to cloud customers and cloud providers, and actions they can take to manage those risks.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121114878","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00145
C. Ferrari, D. Marini, M. Moro
Keystroke dynamics is a behavioral biometric parameter that can be fully exploit in order to build a continuous biometric authentication system that must comply with strict constraints in the use of computational resources, as well as energy, without lowering the security required level. This paper introduces a typing biometric system that continuously adjourns the users models for taking into account both short term amd long term modification in their habits. The system relies on a reduced space features that mainly uses the hold time and both the keyUp-keyDown and keyDown-keyUp time for some selected keys. An Adaptive Continuous Biometric Authentication Scheme, recomputes each user model according to his/her most recent typing history in a temporal sliding window of fixed dimension. Contrary to the most recent work in the literature, we do not limit to adapt the model of the user under authentication but we consider the potential evolution of the model of the other enrolled users, forecasting their possible evolution, again from the data in the sliding window. System performances have been tested with different window size and under different distance metric (namely Euclidean distance, Manhattan distance and cosine similarity). Moreover, it has been considered the balancing among used computational resource and accuracy. Experimentations on the usability of this approach are also reported.
{"title":"An Adaptive Typing Biometric System with Varying users Model","authors":"C. Ferrari, D. Marini, M. Moro","doi":"10.1109/WAINA.2018.00145","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00145","url":null,"abstract":"Keystroke dynamics is a behavioral biometric parameter that can be fully exploit in order to build a continuous biometric authentication system that must comply with strict constraints in the use of computational resources, as well as energy, without lowering the security required level. This paper introduces a typing biometric system that continuously adjourns the users models for taking into account both short term amd long term modification in their habits. The system relies on a reduced space features that mainly uses the hold time and both the keyUp-keyDown and keyDown-keyUp time for some selected keys. An Adaptive Continuous Biometric Authentication Scheme, recomputes each user model according to his/her most recent typing history in a temporal sliding window of fixed dimension. Contrary to the most recent work in the literature, we do not limit to adapt the model of the user under authentication but we consider the potential evolution of the model of the other enrolled users, forecasting their possible evolution, again from the data in the sliding window. System performances have been tested with different window size and under different distance metric (namely Euclidean distance, Manhattan distance and cosine similarity). Moreover, it has been considered the balancing among used computational resource and accuracy. Experimentations on the usability of this approach are also reported.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114211155","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 : 2018-05-01DOI: 10.1109/WAINA.2018.00126
M. Abderrahim, Asma BEN LETAIFA, Amel Haji, S. Tabbane
One of the important objectives of service providers in the 5G network is to improve the use of network resources to provide multiple types of services with a good quality of service. In this context, the MEC (Mobile Edge Computing) presents a new opportunity that allows hosting applications close to end users with a reduction of latency and performance improvement. In this article we will propose a new architecture that improves the fast and efficient delivery of new applications, based on the concept of MEC and the important role of machine learning algorithms. The proposed architecture will help network operators to better exploit network resources and improve their services. Indeed, it ensures the collection of radio information, the prediction of necessary needs and the dynamic and efficient sharing of network resources.
{"title":"How to use MEC and ML to Improve Resources Allocation in SDN Networks ?","authors":"M. Abderrahim, Asma BEN LETAIFA, Amel Haji, S. Tabbane","doi":"10.1109/WAINA.2018.00126","DOIUrl":"https://doi.org/10.1109/WAINA.2018.00126","url":null,"abstract":"One of the important objectives of service providers in the 5G network is to improve the use of network resources to provide multiple types of services with a good quality of service. In this context, the MEC (Mobile Edge Computing) presents a new opportunity that allows hosting applications close to end users with a reduction of latency and performance improvement. In this article we will propose a new architecture that improves the fast and efficient delivery of new applications, based on the concept of MEC and the important role of machine learning algorithms. The proposed architecture will help network operators to better exploit network resources and improve their services. Indeed, it ensures the collection of radio information, the prediction of necessary needs and the dynamic and efficient sharing of network resources.","PeriodicalId":296466,"journal":{"name":"2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133927199","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：