R. Redondo, Ana Fernández Vilas, Antonio Abadía Rodríguez
The advent of smart meters have radically changed the mechanisms traditionally used for energy consumption monitoring. The possibility of having (i) highly frequent readings (even every minute); (ii) accurate energy data gathering; and (iii) real time data exchange capabilities to share the energy consumption data with other elements in the Smart Grid, open the door to further deeper analysis within this context. In this paper, we focus on obtaining energy consumption patterns. Our approach combines clustering and predictive techniques in order to infer these patterns using data gathered from public buildings in a university campus. Our analysis allows us to infer that clustering is not an appropriate mechanism, since the use of buildings is mixed (administrative, labs, classrooms, etc.). However, predictive approaches give promising results, specially LSTM and XGBoost.
{"title":"Inferring Energy Consumption Patterns in Public Buildings","authors":"R. Redondo, Ana Fernández Vilas, Antonio Abadía Rodríguez","doi":"10.1145/3416011.3424753","DOIUrl":"https://doi.org/10.1145/3416011.3424753","url":null,"abstract":"The advent of smart meters have radically changed the mechanisms traditionally used for energy consumption monitoring. The possibility of having (i) highly frequent readings (even every minute); (ii) accurate energy data gathering; and (iii) real time data exchange capabilities to share the energy consumption data with other elements in the Smart Grid, open the door to further deeper analysis within this context. In this paper, we focus on obtaining energy consumption patterns. Our approach combines clustering and predictive techniques in order to infer these patterns using data gathered from public buildings in a university campus. Our analysis allows us to infer that clustering is not an appropriate mechanism, since the use of buildings is mixed (administrative, labs, classrooms, etc.). However, predictive approaches give promising results, specially LSTM and XGBoost.","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77154618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Juan Diego Belesaca, Pablo Avila-Campos, Andrés Vázquez Rodas
Next-generation wireless technologies face considerable challenges in terms of providing the required latency and connectivity for new heterogeneous mobile networks. Driven by these problems, this study focuses on increasing user connectivity together with system throughput. For doing so, we propose and evaluate a hybrid machine learning-driven orthogonal/non-orthogonal multiple access (OMA/NOMA) system. In this work, we use an artificial neural network (ANN) to assign an OMA or NOMA access method to each user equipment (UE). As part of this research we also evaluate the accuracy and training time of the three most relevant learning algorithms of ANN (L-M, BFGS, and OSS). The main objective is to increase the sum-rate of the mobile network in the introduced beamforming and mmWave channel environment. Simulation results show up to a $20%$ sum-rate average performance increase of the system using the ANN management in contrast to a random non-ANN managed system. The Leveberg-Marquard (L-M) training algorithm is the best overall algorithm for this proposed application as presents the highest accuracy of around $77%$ despite 37 minutes of training and lower accuracy of $73%$ with approximately 28 seconds of training time.
{"title":"Artificial Neural Network Performance Evaluation for a Hybrid Power Domain Orthogonal / Non-Orthogonal Multiple Access (OMA / NOMA) System","authors":"Juan Diego Belesaca, Pablo Avila-Campos, Andrés Vázquez Rodas","doi":"10.1145/3416011.3424760","DOIUrl":"https://doi.org/10.1145/3416011.3424760","url":null,"abstract":"Next-generation wireless technologies face considerable challenges in terms of providing the required latency and connectivity for new heterogeneous mobile networks. Driven by these problems, this study focuses on increasing user connectivity together with system throughput. For doing so, we propose and evaluate a hybrid machine learning-driven orthogonal/non-orthogonal multiple access (OMA/NOMA) system. In this work, we use an artificial neural network (ANN) to assign an OMA or NOMA access method to each user equipment (UE). As part of this research we also evaluate the accuracy and training time of the three most relevant learning algorithms of ANN (L-M, BFGS, and OSS). The main objective is to increase the sum-rate of the mobile network in the introduced beamforming and mmWave channel environment. Simulation results show up to a $20%$ sum-rate average performance increase of the system using the ANN management in contrast to a random non-ANN managed system. The Leveberg-Marquard (L-M) training algorithm is the best overall algorithm for this proposed application as presents the highest accuracy of around $77%$ despite 37 minutes of training and lower accuracy of $73%$ with approximately 28 seconds of training time.","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75090969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Solimini, Pere Tuset, Guillem Boquet, Xavier Vilajosana, F. V. Gallego
Packet re-transmissions are a common technique to improve link reliability in low-power wireless networks. However, since packet re-transmissions increase the end-device energy consumption and the network load, a maximum number of re-transmissions per packet is typically set, also considering the duty-cycle limitations imposed by radio-frequency regulations. Moreover, the number of re-transmissions per packet is typically set to a constant value, meaning that all packet re-transmissions are treated the same regardless of actual channel conditions (i.e., multi-path propagation or internal/external interference effects). Taking that into account, in this paper we propose and evaluate the concept of re-transmission shaping, a mechanism that manages packet re-transmissions to maximize link reliability, while minimizing energy consumption and meeting radio-frequency regulation constraints. The proposed re-transmission shaping mechanism operates by keeping track of unused packet re-transmissions and allocating additional re-transmission when the instantaneous link quality decreases due to channel impairments. To evaluate the re-transmission shaping mechanism we use trace-based simulations using a IEEE~802.15.4g SUN data-set and two widely used metrics, the PDR (Packet Delivery Ratio) and the RNP (Required Number of Packets). The obtained results show that re-transmission shaping is a useful mechanism to improve link reliability of low-power wireless communications, as it can increase PDR from 77.9% to 99.2% while sustaining a RNP of 2.35 re-transmissions per packet, when compared to using a single re-transmission per packet.
{"title":"Improving Link Reliability of IEEE 802.15.4g SUN with Re-Transmission Shaping","authors":"D. Solimini, Pere Tuset, Guillem Boquet, Xavier Vilajosana, F. V. Gallego","doi":"10.1145/3416011.3424750","DOIUrl":"https://doi.org/10.1145/3416011.3424750","url":null,"abstract":"Packet re-transmissions are a common technique to improve link reliability in low-power wireless networks. However, since packet re-transmissions increase the end-device energy consumption and the network load, a maximum number of re-transmissions per packet is typically set, also considering the duty-cycle limitations imposed by radio-frequency regulations. Moreover, the number of re-transmissions per packet is typically set to a constant value, meaning that all packet re-transmissions are treated the same regardless of actual channel conditions (i.e., multi-path propagation or internal/external interference effects). Taking that into account, in this paper we propose and evaluate the concept of re-transmission shaping, a mechanism that manages packet re-transmissions to maximize link reliability, while minimizing energy consumption and meeting radio-frequency regulation constraints. The proposed re-transmission shaping mechanism operates by keeping track of unused packet re-transmissions and allocating additional re-transmission when the instantaneous link quality decreases due to channel impairments. To evaluate the re-transmission shaping mechanism we use trace-based simulations using a IEEE~802.15.4g SUN data-set and two widely used metrics, the PDR (Packet Delivery Ratio) and the RNP (Required Number of Packets). The obtained results show that re-transmission shaping is a useful mechanism to improve link reliability of low-power wireless communications, as it can increase PDR from 77.9% to 99.2% while sustaining a RNP of 2.35 re-transmissions per packet, when compared to using a single re-transmission per packet.","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2020-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74084225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PE-WASUN '20, Proceedings of the 17th ACM Symposium on Performance Evaluation of Wireless Ad Hoc, Sensor, & Ubiquitous Networks, Alicante, Spain, November 16-20, 2020","authors":"","doi":"10.1145/3416011","DOIUrl":"https://doi.org/10.1145/3416011","url":null,"abstract":"","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74891792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. M. Mezher, N. Rajendran, Pedro Enrique Iturria Rivera, Carlos Lester Dueñas Santos, J. Meng, Eduardo Castillo Guerra
At the present time, a great interest has been shown by the research and the industrial community concerning smart grid communications where important technical advances have arisen as a consequence. Concretely, one of the most important goals of RF mesh network is the design and development of an efficient routing protocol to connect different devices of the network between each other. Nevertheless, the overall performance of the RF Mesh network communications depends in high measure on the positions of key devices in Radio Frequency (RF) Mesh network such as routers and collectors. With this in mind, we focus our work in this paper to design a strategy to optimize the positions of the key devices of RF Mesh network such as routers and collectors to achieve the highest possible connectivity between different components of RF Mesh network. To do so, we have used a well-known clustering algorithm called Lloyd's algorithm, to design our strategy, with the clear objective of allocating routers and collectors in their optimal positions in a smart grid scenario. Extensive simulations have been carried out with the proposed strategy, and good results have been obtained.
{"title":"Optimization of Key Devices Positions in Large-Scale RF Mesh Networks","authors":"A. M. Mezher, N. Rajendran, Pedro Enrique Iturria Rivera, Carlos Lester Dueñas Santos, J. Meng, Eduardo Castillo Guerra","doi":"10.1145/3345860.3361515","DOIUrl":"https://doi.org/10.1145/3345860.3361515","url":null,"abstract":"At the present time, a great interest has been shown by the research and the industrial community concerning smart grid communications where important technical advances have arisen as a consequence. Concretely, one of the most important goals of RF mesh network is the design and development of an efficient routing protocol to connect different devices of the network between each other. Nevertheless, the overall performance of the RF Mesh network communications depends in high measure on the positions of key devices in Radio Frequency (RF) Mesh network such as routers and collectors. With this in mind, we focus our work in this paper to design a strategy to optimize the positions of the key devices of RF Mesh network such as routers and collectors to achieve the highest possible connectivity between different components of RF Mesh network. To do so, we have used a well-known clustering algorithm called Lloyd's algorithm, to design our strategy, with the clear objective of allocating routers and collectors in their optimal positions in a smart grid scenario. Extensive simulations have been carried out with the proposed strategy, and good results have been obtained.","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2019-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85075514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. M. Mezher, Pedro Enrique Iturria Rivera, Carlos Lester Dueñas Santos, J. Cardenas-Barrera, J. Meng, Eduardo Castillo Guerra
Recently, smart grid communications have attracted much attention from the research community. An excellent performance of a RF Mesh network in terms of quality of service parameters depends not only on having an efficient routing protocol to route packets but also on the positions of routers and collectors located in the same network. This makes the positioning of routers and collectors in RF Mesh networks a challenging task. Moreover, an efficient strategy to optimize jointly routers and collectors positions have been proposed recently by us. However, in this work, we have studied the impact of using different Minkowski distance order on the proposed strategy in a RF Mesh context. Extensive simulations in OMNET++ have been carried out with the proposed strategy for different Minkowski distance order. Results indicate that the Euclidean distance is the best Minkowski distance order choice to obtain the best results in terms of average percentage of packet delivery rate and average end-to-end delay.
{"title":"Minkowski Distance Order Effect on the Optimization of Key Devices Positions in Large-Scale RF Mesh Networks","authors":"A. M. Mezher, Pedro Enrique Iturria Rivera, Carlos Lester Dueñas Santos, J. Cardenas-Barrera, J. Meng, Eduardo Castillo Guerra","doi":"10.1145/3345860.3361516","DOIUrl":"https://doi.org/10.1145/3345860.3361516","url":null,"abstract":"Recently, smart grid communications have attracted much attention from the research community. An excellent performance of a RF Mesh network in terms of quality of service parameters depends not only on having an efficient routing protocol to route packets but also on the positions of routers and collectors located in the same network. This makes the positioning of routers and collectors in RF Mesh networks a challenging task. Moreover, an efficient strategy to optimize jointly routers and collectors positions have been proposed recently by us. However, in this work, we have studied the impact of using different Minkowski distance order on the proposed strategy in a RF Mesh context. Extensive simulations in OMNET++ have been carried out with the proposed strategy for different Minkowski distance order. Results indicate that the Euclidean distance is the best Minkowski distance order choice to obtain the best results in terms of average percentage of packet delivery rate and average end-to-end delay.","PeriodicalId":55557,"journal":{"name":"Ad Hoc & Sensor Wireless Networks","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2019-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83577349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：