Chiara Pielli, Federico Chiariotti, N. Laurenti, A. Zanella, M. Zorzi
Jamming may be a serious issue in Internet of Things networks with battery-powered nodes, as an attacker can not only disrupt packet delivery, but also reduce the lifetime of energy-constrained nodes. In this work, we consider a malicious attacker with the dual objective of preventing communication and depleting the battery of a targeted node. We model this scenario as a multistage game, derive optimal strategies for both sides, and evaluate their consequences on network performance. Our work highlights the trade-off between node lifetime and communication reliability and how the presence of a jammer affects both these aspects.
{"title":"A game-theoretic analysis of energy-depleting jamming attacks","authors":"Chiara Pielli, Federico Chiariotti, N. Laurenti, A. Zanella, M. Zorzi","doi":"10.1145/3366486.3366546","DOIUrl":"https://doi.org/10.1145/3366486.3366546","url":null,"abstract":"Jamming may be a serious issue in Internet of Things networks with battery-powered nodes, as an attacker can not only disrupt packet delivery, but also reduce the lifetime of energy-constrained nodes. In this work, we consider a malicious attacker with the dual objective of preventing communication and depleting the battery of a targeted node. We model this scenario as a multistage game, derive optimal strategies for both sides, and evaluate their consequences on network performance. Our work highlights the trade-off between node lifetime and communication reliability and how the presence of a jammer affects both these aspects.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122846525","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 : 2017-07-20DOI: 10.1109/ICCNC.2017.7876135
Run Tian, Yuan Liang, Xuezhi Tan, Tongtong Li
This paper considers capacity and quality of service improvement in Internet of Things (IoT) oriented massive MIMO systems through overlapping user grouping. In massive MIMO systems, user selection and grouping are generally used to reduce multiuser interference. In existing approaches, users with less favorable channel conditions are generally dropped for capacity optimization. As a result, some users would never be served by the system in IoT networks. Moreover, user subgroups are generally non-overlapping, leading to unnecessary resource waste. Motivated by these observations, in this paper, we propose two new user grouping approaches. First, we propose a new user grouping method based on greedy algorithm by allowing overlapping between the selected subgroups. Second, we introduce a new channel similarity measure, and develop another overlapping user grouping method by exploiting the spectral clustering method in machine learning. It is observed that the proposed approaches can increase the system capacity through subgroup overlapping, and can ensure that each user will be served in at least one subgroup.
{"title":"Overlapping user grouping in IoT oriented massive MIMO systems","authors":"Run Tian, Yuan Liang, Xuezhi Tan, Tongtong Li","doi":"10.1109/ICCNC.2017.7876135","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876135","url":null,"abstract":"This paper considers capacity and quality of service improvement in Internet of Things (IoT) oriented massive MIMO systems through overlapping user grouping. In massive MIMO systems, user selection and grouping are generally used to reduce multiuser interference. In existing approaches, users with less favorable channel conditions are generally dropped for capacity optimization. As a result, some users would never be served by the system in IoT networks. Moreover, user subgroups are generally non-overlapping, leading to unnecessary resource waste. Motivated by these observations, in this paper, we propose two new user grouping approaches. First, we propose a new user grouping method based on greedy algorithm by allowing overlapping between the selected subgroups. Second, we introduce a new channel similarity measure, and develop another overlapping user grouping method by exploiting the spectral clustering method in machine learning. It is observed that the proposed approaches can increase the system capacity through subgroup overlapping, and can ensure that each user will be served in at least one subgroup.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126498953","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 : 2017-03-13DOI: 10.1109/ICCNC.2017.7876247
A. Shabut, K. Dahal
The use of recommendation in trust-based models has its advantages in enhancing the correctness and quality of the rating provided by mobile and autonomous nodes in MANETs. However, building a trust model with a recommender system in dynamic and distributed networks is a challenging problem due to the risk of dishonest recommendations. Dealing with dishonest recommendations can result in the additional problem of data sparsity, which is related to the availability of information in the early rounds of the network time or when nodes are inactive in providing recommendations. This paper investigates the problems of data sparsity and cold start of recommender systems in existing trust models. It proposes a recommender system with clustering technique to dynamically seek similar recommendations based on a certain timeframe. Similarity between different nodes is evaluated based on important attributes includes use of interactions, compatibility of information and closeness between the mobile nodes. The recommender system is empirically tested and empirical analysis demonstrates robustness in alleviating the problems of data sparsity and cold start of recommender systems in a dynamic MANET environment.
{"title":"Social factors for data sparsity problem of trust models in MANETs","authors":"A. Shabut, K. Dahal","doi":"10.1109/ICCNC.2017.7876247","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876247","url":null,"abstract":"The use of recommendation in trust-based models has its advantages in enhancing the correctness and quality of the rating provided by mobile and autonomous nodes in MANETs. However, building a trust model with a recommender system in dynamic and distributed networks is a challenging problem due to the risk of dishonest recommendations. Dealing with dishonest recommendations can result in the additional problem of data sparsity, which is related to the availability of information in the early rounds of the network time or when nodes are inactive in providing recommendations. This paper investigates the problems of data sparsity and cold start of recommender systems in existing trust models. It proposes a recommender system with clustering technique to dynamically seek similar recommendations based on a certain timeframe. Similarity between different nodes is evaluated based on important attributes includes use of interactions, compatibility of information and closeness between the mobile nodes. The recommender system is empirically tested and empirical analysis demonstrates robustness in alleviating the problems of data sparsity and cold start of recommender systems in a dynamic MANET environment.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130732933","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 : 2017-03-13DOI: 10.1109/ICCNC.2017.7876137
Musab Isah, Steven Simpson, Yusuf Sani, C. Edwards
Host mobility protocols such as Locator-Identifier Separation Protocol Mobile Node (LISP-MN) are known to experience packet loss at the point of handover. For the duration of the handover, packets sent to the MN via the old access link are dropped by the router since it has no way of knowing where the device has moved to. This affects the performance of transport layer protocols of the TCP/IP stack, which results in degradation of network performance. Buffering these packets close to the MN's new location and forwarding them to the MN on handover completion is one way of improving the overall performance of the mobility protocol. Hence, we introduce a novel network node, loc-server, to buffer these packets in order to mitigate the packet loss and reduce the service disruption time (SDT) experienced by MNs during handovers. Using a laboratory testbed implementation, LISP-MN with loc-server support shows significant reduction in packet loss and reduced SDT in comparison to vanilla LISP-MN. Similarly, performance analysis of DASH video player also shows the new architecture helps in improving the average video quality downloaded by the MN and reduces the player's instability.
{"title":"Towards zero packet loss with LISP Mobile Node","authors":"Musab Isah, Steven Simpson, Yusuf Sani, C. Edwards","doi":"10.1109/ICCNC.2017.7876137","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876137","url":null,"abstract":"Host mobility protocols such as Locator-Identifier Separation Protocol Mobile Node (LISP-MN) are known to experience packet loss at the point of handover. For the duration of the handover, packets sent to the MN via the old access link are dropped by the router since it has no way of knowing where the device has moved to. This affects the performance of transport layer protocols of the TCP/IP stack, which results in degradation of network performance. Buffering these packets close to the MN's new location and forwarding them to the MN on handover completion is one way of improving the overall performance of the mobility protocol. Hence, we introduce a novel network node, loc-server, to buffer these packets in order to mitigate the packet loss and reduce the service disruption time (SDT) experienced by MNs during handovers. Using a laboratory testbed implementation, LISP-MN with loc-server support shows significant reduction in packet loss and reduced SDT in comparison to vanilla LISP-MN. Similarly, performance analysis of DASH video player also shows the new architecture helps in improving the average video quality downloaded by the MN and reduces the player's instability.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125885587","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 : 2017-03-10DOI: 10.1109/ICCNC.2017.7876251
Jinoh Kim, Wucherl Yoo, A. Sim, S. Suh, Ikkyun Kim
While the network anomaly detection is essential in network operations and management, it becomes further challenging to perform the first line of detection against the exponentially increasing volume of network traffic. In this work, we develop a technique for the first line of online anomaly detection with two important considerations: (i) availability of traffic attributes during the monitoring time, and (ii) computational scalability for streaming data. The presented learning technique is lightweight and highly scalable with the beauty of approximation based on the grid partitioning of the given dimensional space. With the public traffic traces of KDD Cup 1999 and NSL-KDD, we show that our technique yields 98.5% and 83% of detection accuracy, respectively, only with a couple of readily available traffic attributes that can be obtained without the help of post-processing. The results are at least comparable with the classical learning methods including decision tree and random forest, with approximately two orders of magnitude faster learning performance.
{"title":"A lightweight network anomaly detection technique","authors":"Jinoh Kim, Wucherl Yoo, A. Sim, S. Suh, Ikkyun Kim","doi":"10.1109/ICCNC.2017.7876251","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876251","url":null,"abstract":"While the network anomaly detection is essential in network operations and management, it becomes further challenging to perform the first line of detection against the exponentially increasing volume of network traffic. In this work, we develop a technique for the first line of online anomaly detection with two important considerations: (i) availability of traffic attributes during the monitoring time, and (ii) computational scalability for streaming data. The presented learning technique is lightweight and highly scalable with the beauty of approximation based on the grid partitioning of the given dimensional space. With the public traffic traces of KDD Cup 1999 and NSL-KDD, we show that our technique yields 98.5% and 83% of detection accuracy, respectively, only with a couple of readily available traffic attributes that can be obtained without the help of post-processing. The results are at least comparable with the classical learning methods including decision tree and random forest, with approximately two orders of magnitude faster learning performance.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122633186","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 : 2017-03-10DOI: 10.1109/ICCNC.2017.7876207
Jinoh Kim, A. Sim, S. Suh, Ikkyun Kim
Network traffic monitoring is a core element in network operations and management for various purposes such as anomaly detection, change detection, and fault/failure detection. In this paper, we introduce a new approach to online monitoring using a pattern-based representation of the network traffic. Unlike the past online techniques limited to a single variable to summarize (e.g., sketch), the focus of this study is on capturing the network state from the multivariate attributes under consideration. To this end, we employ clustering with its benefit of the aggregation of multidimensional variables. The clustered result represents the state of the network with regard to the monitored variables, which can also be compared with the previously observed patterns visually and quantitatively. We demonstrate the proposed method with two popular use cases, one for estimating state changes and the other for identifying anomalous states, to confirm its feasibility.
{"title":"An approach to online network monitoring using clustered patterns","authors":"Jinoh Kim, A. Sim, S. Suh, Ikkyun Kim","doi":"10.1109/ICCNC.2017.7876207","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876207","url":null,"abstract":"Network traffic monitoring is a core element in network operations and management for various purposes such as anomaly detection, change detection, and fault/failure detection. In this paper, we introduce a new approach to online monitoring using a pattern-based representation of the network traffic. Unlike the past online techniques limited to a single variable to summarize (e.g., sketch), the focus of this study is on capturing the network state from the multivariate attributes under consideration. To this end, we employ clustering with its benefit of the aggregation of multidimensional variables. The clustered result represents the state of the network with regard to the monitored variables, which can also be compared with the previously observed patterns visually and quantitatively. We demonstrate the proposed method with two popular use cases, one for estimating state changes and the other for identifying anomalous states, to confirm its feasibility.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"374 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116793903","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 : 2017-03-10DOI: 10.1109/ICCNC.2017.7876275
Kui Zhang, E. D. Ayele, N. Meratnia, P. Havinga, Peng Guo, Youxin Wu
To ensure long network life-time, the duty-cycle of wireless sensor networks is often set to be low. This brings with itself the risk of either missing a sent packet or delaying the message delivery and dissemination depending on the duration of the duty-cycle and number of hops. This risk is increased in wireless sensor applications with hybrid architecture, in which a static ground wireless sensor network interacts with a network of mobile sensor nodes. Dynamicity and mobility of mobile nodes may lead to only a short rendezvous between them and the backbone network to exchange data. Additionally, such dynamicity generates complex and often random data traffic patterns. To support successful data delivery in case of short rendezvous between static and mobile wireless sensor nodes, we propose MobiBone, an energy-efficient and adaptive network protocol that utilizes data packet traffic to characterize the sleep schedule. Our simulation results show that compared with network protocols with fixed duty-cycles, MobiBone offers a good trade-off between energy consumption, latency, and detection rate of mobile nodes (which indicates awakens of the backbone network at crucial times of mobile node presence).
{"title":"MobiBone: An energy-efficient and adaptive network protocol to support short rendezvous between static and mobile wireless sensor nodes","authors":"Kui Zhang, E. D. Ayele, N. Meratnia, P. Havinga, Peng Guo, Youxin Wu","doi":"10.1109/ICCNC.2017.7876275","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876275","url":null,"abstract":"To ensure long network life-time, the duty-cycle of wireless sensor networks is often set to be low. This brings with itself the risk of either missing a sent packet or delaying the message delivery and dissemination depending on the duration of the duty-cycle and number of hops. This risk is increased in wireless sensor applications with hybrid architecture, in which a static ground wireless sensor network interacts with a network of mobile sensor nodes. Dynamicity and mobility of mobile nodes may lead to only a short rendezvous between them and the backbone network to exchange data. Additionally, such dynamicity generates complex and often random data traffic patterns. To support successful data delivery in case of short rendezvous between static and mobile wireless sensor nodes, we propose MobiBone, an energy-efficient and adaptive network protocol that utilizes data packet traffic to characterize the sleep schedule. Our simulation results show that compared with network protocols with fixed duty-cycles, MobiBone offers a good trade-off between energy consumption, latency, and detection rate of mobile nodes (which indicates awakens of the backbone network at crucial times of mobile node presence).","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125161715","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 : 2017-03-10DOI: 10.1109/ICCNC.2017.7876103
Ammar Zafar, M. Shaqfeh, H. Alnuweiri, Mohamed-Slim Alouini
This work investigates the gain due to reduction in path loss by deploying buffer-aided moving relaying. In particular, the increase in gain due to moving relays is studied for dual-hop broadcast channels and the bidirectional relay channel. It is shown that the exploited gains in these channels due to buffer-aided relaying can be enhanced by utilizing the fact that a moving relay can communicate with the terminal closest to it and store the data in the buffer and then forward the data to the intended destination when it comes in close proximity with the destination. Numerical results show that for both the considered channels the achievable rates are increased as compared to the case of stationary relays. Numerical results also show that more significant increase in performance is seen when the relay moves to-and-fro between the source and the relay.
{"title":"Capacity gains of buffer-aided moving relays","authors":"Ammar Zafar, M. Shaqfeh, H. Alnuweiri, Mohamed-Slim Alouini","doi":"10.1109/ICCNC.2017.7876103","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876103","url":null,"abstract":"This work investigates the gain due to reduction in path loss by deploying buffer-aided moving relaying. In particular, the increase in gain due to moving relays is studied for dual-hop broadcast channels and the bidirectional relay channel. It is shown that the exploited gains in these channels due to buffer-aided relaying can be enhanced by utilizing the fact that a moving relay can communicate with the terminal closest to it and store the data in the buffer and then forward the data to the intended destination when it comes in close proximity with the destination. Numerical results show that for both the considered channels the achievable rates are increased as compared to the case of stationary relays. Numerical results also show that more significant increase in performance is seen when the relay moves to-and-fro between the source and the relay.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124169041","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 : 2017-03-10DOI: 10.1109/ICCNC.2017.7876278
Chih-Wei Chen, F. Maehara
This paper proposes an enhanced decision feedback equalizer (DFE) for filter bank multicarrier (FBMC) systems over offset quadrature amplitude modulation (OQAM) based on a minimal mean square error (MMSE) criterion. For each subcarrier, besides one feedforward (FF) filter and one feedback (FB) filter, we add two intercarrier interference (ICI)-suppressing filters, which feed back detected precursors extracted from neighboring subchannels to enhance ICI suppression in the presence of multipath channels. Our simulation results indicate our proposal makes a considerable improvement comparing with MMSE-DFE under a severe ICI and ISI scenario despite few extra costs in computational complexity.
{"title":"An enhanced MMSE subchannel decision feedback equalizer with ICI suppression for FBMC/OQAM systems","authors":"Chih-Wei Chen, F. Maehara","doi":"10.1109/ICCNC.2017.7876278","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876278","url":null,"abstract":"This paper proposes an enhanced decision feedback equalizer (DFE) for filter bank multicarrier (FBMC) systems over offset quadrature amplitude modulation (OQAM) based on a minimal mean square error (MMSE) criterion. For each subcarrier, besides one feedforward (FF) filter and one feedback (FB) filter, we add two intercarrier interference (ICI)-suppressing filters, which feed back detected precursors extracted from neighboring subchannels to enhance ICI suppression in the presence of multipath channels. Our simulation results indicate our proposal makes a considerable improvement comparing with MMSE-DFE under a severe ICI and ISI scenario despite few extra costs in computational complexity.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130271982","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 : 2017-01-26DOI: 10.1109/ICCNC.2017.7876196
Ghulam Mohi Ud Din, Angelos K. Marnerides
Accurate load forecasting greatly influences the planning processes undertaken in operation centres of energy providers that relate to the actual electricity generation, distribution, system maintenance as well as electricity pricing. This paper exploits the applicability of and compares the performance of the Feed-forward Deep Neural Network (FF-DNN) and Recurrent Deep Neural Network (R-DNN) models on the basis of accuracy and computational performance in the context of time-wise short term forecast of electricity load. The herein proposed method is evaluated over real datasets gathered in a period of 4 years and provides forecasts on the basis of days and weeks ahead. The contribution behind this work lies with the utilisation of a time-frequency (TF) feature selection procedure from the actual “raw” dataset that aids the regression procedure initiated by the aforementioned DNNs. We show that the introduced scheme may adequately learn hidden patterns and accurately determine the short-term load consumption forecast by utilising a range of heterogeneous sources of input that relate not necessarily with the measurement of load itself but also with other parameters such as the effects of weather, time, holidays, lagged electricity load and its distribution over the period. Overall, our generated outcomes reveal that the synergistic use of TF feature analysis with DNNs enables to obtain higher accuracy by capturing dominant factors that affect electricity consumption patterns and can surely contribute significantly in next generation power systems and the recently introduced SmartGrid.
{"title":"Short term power load forecasting using Deep Neural Networks","authors":"Ghulam Mohi Ud Din, Angelos K. Marnerides","doi":"10.1109/ICCNC.2017.7876196","DOIUrl":"https://doi.org/10.1109/ICCNC.2017.7876196","url":null,"abstract":"Accurate load forecasting greatly influences the planning processes undertaken in operation centres of energy providers that relate to the actual electricity generation, distribution, system maintenance as well as electricity pricing. This paper exploits the applicability of and compares the performance of the Feed-forward Deep Neural Network (FF-DNN) and Recurrent Deep Neural Network (R-DNN) models on the basis of accuracy and computational performance in the context of time-wise short term forecast of electricity load. The herein proposed method is evaluated over real datasets gathered in a period of 4 years and provides forecasts on the basis of days and weeks ahead. The contribution behind this work lies with the utilisation of a time-frequency (TF) feature selection procedure from the actual “raw” dataset that aids the regression procedure initiated by the aforementioned DNNs. We show that the introduced scheme may adequately learn hidden patterns and accurately determine the short-term load consumption forecast by utilising a range of heterogeneous sources of input that relate not necessarily with the measurement of load itself but also with other parameters such as the effects of weather, time, holidays, lagged electricity load and its distribution over the period. Overall, our generated outcomes reveal that the synergistic use of TF feature analysis with DNNs enables to obtain higher accuracy by capturing dominant factors that affect electricity consumption patterns and can surely contribute significantly in next generation power systems and the recently introduced SmartGrid.","PeriodicalId":135028,"journal":{"name":"2017 International Conference on Computing, Networking and Communications (ICNC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133569173","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：