Pub Date : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646433
Xiaoyu Zhang, Xuanfeng Li, Yong Zhou, H. Qian, Xiliang Luo
To tackle the uplink pilot contamination problem in massive multiple-input multiple-output (MIMO) systems, current researches only relied on the angle of arrival at the base station. However, this information is insufficient when the users share the same scattering environment. In this paper, we propose a novel strategy by exploiting the user mobility. Due to limited scatterers around the users, we first investigate the channel sparsity and derive the corresponding angle-Doppler frequency domain channel power spectrum (AD-CPS). We then propose a method to mitigate the pilot contamination through aligning the AD-CPSs. Compared with the existing works, we further demonstrate the effectiveness of the proposed scheme in supporting more orthogonal pilots when the interfering users exhibit different moving patterns. Simulations verify the superior performance and show that the proposed scheme can serve as an additional decontamination mechanism for the UL pilots in massive MIMO systems.
{"title":"HOW TO EXPLOIT MOBILITY TO MITIGATE PILOT CONTAMINATION?","authors":"Xiaoyu Zhang, Xuanfeng Li, Yong Zhou, H. Qian, Xiliang Luo","doi":"10.1109/GlobalSIP.2018.8646433","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646433","url":null,"abstract":"To tackle the uplink pilot contamination problem in massive multiple-input multiple-output (MIMO) systems, current researches only relied on the angle of arrival at the base station. However, this information is insufficient when the users share the same scattering environment. In this paper, we propose a novel strategy by exploiting the user mobility. Due to limited scatterers around the users, we first investigate the channel sparsity and derive the corresponding angle-Doppler frequency domain channel power spectrum (AD-CPS). We then propose a method to mitigate the pilot contamination through aligning the AD-CPSs. Compared with the existing works, we further demonstrate the effectiveness of the proposed scheme in supporting more orthogonal pilots when the interfering users exhibit different moving patterns. Simulations verify the superior performance and show that the proposed scheme can serve as an additional decontamination mechanism for the UL pilots in massive MIMO systems.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127606314","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646419
J. Baur, G. Dobler, F. Bianco, Mohit S. Sharma, A. Karpf
We present the persistent hyperspectral imaging of the New York City urban lightscape, with ~ 7.2 ×10−4 μm spectral resolution, surveyed over 25 consecutive summer nights over a 6 minute time resolution. We train a supervised classifier to automatically determine the location of light sources in each hyperspectral image. This work issues the first urban lightscape combined hyperspectral - multitemporal survey of its kind.
{"title":"Persistent Hyperspectral Observations of the Urban Lightscape","authors":"J. Baur, G. Dobler, F. Bianco, Mohit S. Sharma, A. Karpf","doi":"10.1109/GlobalSIP.2018.8646419","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646419","url":null,"abstract":"We present the persistent hyperspectral imaging of the New York City urban lightscape, with ~ 7.2 ×10−4 μm spectral resolution, surveyed over 25 consecutive summer nights over a 6 minute time resolution. We train a supervised classifier to automatically determine the location of light sources in each hyperspectral image. This work issues the first urban lightscape combined hyperspectral - multitemporal survey of its kind.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127607737","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646532
M. Khatun, H. Mehrpouyan, D. Matolak
This paper presents a large scale fading channel model at the 60 GHz band. This model is based on the measurement campaign that our team conducted at Boise Airport and Boise State University. The close-in reference path loss and floating-intercept path loss models with both statistical and stochastic approaches are investigated for these environments. The measurements were collected at several different locations in line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios using high gain directional antenna. The path loss exponent and shadowing factor are determined based on the measurement results and compared with recent work at this frequency. Both the stochastic gradient descent algorithm and the statistical least-square technique are used to analyze the floating-intercept path loss model. The results show that the path loss exponents in the outdoor scenarios are higher than the indoor environment due the RF noise caused by the sunny and dry climate in the Boise area. Finally, a good agreement is found between the measurement results and the prior work results in presented in the literature.
{"title":"60-GHz Millimeter-Wave Pathloss Measurements in Boise Airport","authors":"M. Khatun, H. Mehrpouyan, D. Matolak","doi":"10.1109/GlobalSIP.2018.8646532","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646532","url":null,"abstract":"This paper presents a large scale fading channel model at the 60 GHz band. This model is based on the measurement campaign that our team conducted at Boise Airport and Boise State University. The close-in reference path loss and floating-intercept path loss models with both statistical and stochastic approaches are investigated for these environments. The measurements were collected at several different locations in line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios using high gain directional antenna. The path loss exponent and shadowing factor are determined based on the measurement results and compared with recent work at this frequency. Both the stochastic gradient descent algorithm and the statistical least-square technique are used to analyze the floating-intercept path loss model. The results show that the path loss exponents in the outdoor scenarios are higher than the indoor environment due the RF noise caused by the sunny and dry climate in the Boise area. Finally, a good agreement is found between the measurement results and the prior work results in presented in the literature.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129023889","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646567
Ding Xiang, Ermin Wei
As opposed to the traditional supply-follow-demand approach, demand response is seen as an effective solution to improve efficiency of electricity system. In demand response, dynamic pricing schemes are believed to have significant potential to fully exploit the flexibility of shiftable energy consumptions. Most existing work on dynamic pricing schemes, however, falls short on consideration of price discrimination over different types of consumer groups. In this work, we propose a bilevel game theoretical Stackelberg model between a price-making utility company (a leader) and price-taking consumer groups (followers) in a discriminated dynamic pricing environment. We show under price discrimination producer surplus is monotonically increasing as energy consumption capacity of consumer groups increases. Numerical simulation validates our theoretical analysis and also shows that without price discrimination the social welfare may decrease against the energy consumption capacity of consumer groups. Moreover, social welfare can be higher under price discrimination.
{"title":"DYNAMIC PRICE DISCRIMINATION IN DEMAND RESPONSE MARKET: A BILEVEL GAME THEORETICAL MODEL","authors":"Ding Xiang, Ermin Wei","doi":"10.1109/GlobalSIP.2018.8646567","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646567","url":null,"abstract":"As opposed to the traditional supply-follow-demand approach, demand response is seen as an effective solution to improve efficiency of electricity system. In demand response, dynamic pricing schemes are believed to have significant potential to fully exploit the flexibility of shiftable energy consumptions. Most existing work on dynamic pricing schemes, however, falls short on consideration of price discrimination over different types of consumer groups. In this work, we propose a bilevel game theoretical Stackelberg model between a price-making utility company (a leader) and price-taking consumer groups (followers) in a discriminated dynamic pricing environment. We show under price discrimination producer surplus is monotonically increasing as energy consumption capacity of consumer groups increases. Numerical simulation validates our theoretical analysis and also shows that without price discrimination the social welfare may decrease against the energy consumption capacity of consumer groups. Moreover, social welfare can be higher under price discrimination.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116907595","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646562
Hongbin Zhu, Haifeng Wang, Xiliang Luo, H. Qian
Fog computing extends cloud computing and services to the edge of networks, bringing advantages of the cloud closer to where data is created and acted upon. To support real time applications, latency performance is a crucial metric in fog computing. In this paper, we consider a sequential decision-making problem for computation offloading with unknown dynamics in which a mobile user offloads its arrival tasks to associated fog nodes (FNs) at each time slot. The queue of arrival tasks at each FN is modeled as a Markov chain. In order to provide satisfactory quality of experience, the network latency, which is directly associated with the queue condition, needs to be minimized. Taking advantage of reinforcement learning, the sequential decision-making problem is formulated as a restless multi-armed bandit problem. We construct a policy with interleaved exploration and exploitation stages, which achieves a regret with sub-linear order. Both analytical and simulation results validate the effectiveness of the proposed method in dealing with sequential decision-making problem.
{"title":"AN ONLINE LEARNING APPROACH TO WIRELESS COMPUTATION OFFLOADING","authors":"Hongbin Zhu, Haifeng Wang, Xiliang Luo, H. Qian","doi":"10.1109/GlobalSIP.2018.8646562","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646562","url":null,"abstract":"Fog computing extends cloud computing and services to the edge of networks, bringing advantages of the cloud closer to where data is created and acted upon. To support real time applications, latency performance is a crucial metric in fog computing. In this paper, we consider a sequential decision-making problem for computation offloading with unknown dynamics in which a mobile user offloads its arrival tasks to associated fog nodes (FNs) at each time slot. The queue of arrival tasks at each FN is modeled as a Markov chain. In order to provide satisfactory quality of experience, the network latency, which is directly associated with the queue condition, needs to be minimized. Taking advantage of reinforcement learning, the sequential decision-making problem is formulated as a restless multi-armed bandit problem. We construct a policy with interleaved exploration and exploitation stages, which achieves a regret with sub-linear order. Both analytical and simulation results validate the effectiveness of the proposed method in dealing with sequential decision-making problem.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131091923","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 : 2018-11-01DOI: 10.1109/GLOBALSIP.2018.8646443
Sifat Shahriar Khan, Jin Wei
With the omnipresence of big data, social sensing has become a valuable technique for information retrieval and event detection. In recent years, extensive research has been conducted on using social sensing as a platform to detect critical events and emergency situations such as natural disasters, criminal activities, and power outages. In this paper, we focus on detecting real-time power outages using social sensing by investigating different predictive models, preprocessing techniques and feature extraction methods. The investigation shows that multi-layer perception neural network outperforms other popular predictive models. The paper proposes a real-time situational-awareness mechanism to detect the ongoing power outages and extract useful information for power outage management. In the proposed framework, for temporal analysis, a modified approach of Kleinberg’s burst detection algorithm is proposed to ensure the prompt detection of power outages. This study paves the way for future investigation and innovation in efficient real-time event detection using social sensing.
{"title":"Real-Time Power Outage Detection System using Social Sensing and Neural Networks","authors":"Sifat Shahriar Khan, Jin Wei","doi":"10.1109/GLOBALSIP.2018.8646443","DOIUrl":"https://doi.org/10.1109/GLOBALSIP.2018.8646443","url":null,"abstract":"With the omnipresence of big data, social sensing has become a valuable technique for information retrieval and event detection. In recent years, extensive research has been conducted on using social sensing as a platform to detect critical events and emergency situations such as natural disasters, criminal activities, and power outages. In this paper, we focus on detecting real-time power outages using social sensing by investigating different predictive models, preprocessing techniques and feature extraction methods. The investigation shows that multi-layer perception neural network outperforms other popular predictive models. The paper proposes a real-time situational-awareness mechanism to detect the ongoing power outages and extract useful information for power outage management. In the proposed framework, for temporal analysis, a modified approach of Kleinberg’s burst detection algorithm is proposed to ensure the prompt detection of power outages. This study paves the way for future investigation and innovation in efficient real-time event detection using social sensing.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128296141","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646358
N. Cassiau, L. Maret, Jean-Baptiste Doré, V. Savin, D. Kténas
The performance, error rate and synchronization, of recently released 5G New Radio (NR) physical layer (PHY) with typical satellite scenarios are assessed in this paper. Four propagation channels in Ka band are considered and implementation constraints are modeled. The conclusions highly depend on the channel type. For open rural and high speed train (300 km/h) scenarios, 5G NR PHY may be used as is. Higher speed scenarios (aero 1000 km/h) can benefit from the 5G NR mode that allows very short symbols (although this mode is only allowed for large band). Finally, we demonstrate that amendments should be considered in the standard for supporting 2-state channels (suburban for example), due to the long fading periods.
对最新发布的5G新空口物理层(PHY)在典型卫星场景下的性能、错误率和同步性进行了评估。考虑了Ka波段的四种传播通道，并对实现约束进行了建模。结论高度依赖于通道类型。对于开放的农村和高速列车(300公里/小时)场景，5G NR PHY可以原样使用。更高速度的场景(航空1000公里/小时)可以从5G NR模式中受益，该模式允许非常短的符号(尽管该模式只允许大频段)。最后，我们证明，由于长衰落周期，应该考虑在支持两状态信道(例如郊区)的标准中进行修订。
{"title":"Assessment of 5G NR Physical Layer for Future Satellite Networks","authors":"N. Cassiau, L. Maret, Jean-Baptiste Doré, V. Savin, D. Kténas","doi":"10.1109/GlobalSIP.2018.8646358","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646358","url":null,"abstract":"The performance, error rate and synchronization, of recently released 5G New Radio (NR) physical layer (PHY) with typical satellite scenarios are assessed in this paper. Four propagation channels in Ka band are considered and implementation constraints are modeled. The conclusions highly depend on the channel type. For open rural and high speed train (300 km/h) scenarios, 5G NR PHY may be used as is. Higher speed scenarios (aero 1000 km/h) can benefit from the 5G NR mode that allows very short symbols (although this mode is only allowed for large band). Finally, we demonstrate that amendments should be considered in the standard for supporting 2-state channels (suburban for example), due to the long fading periods.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128348029","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646519
G. Abreu, Alireza Ghods
We revisit the super multidimensional scaling (SMDS) wireless localization algorithm first proposed a decade ago, recasting it onto the complex-domain1. Under this new formulation, the edge kernel which carries both angle and distance information simultaneously and plays a central role in the SMDS algorithm, becomes a complex-valued rank-one matrix, resulting in a new complex-domain SMDS framework which yields several advantages over the original, including the elimination of redundancy and the enhancement of conditions to handle information erasure.
{"title":"Hybrid Wireless Localization via Complex-domain Isometric Embedding","authors":"G. Abreu, Alireza Ghods","doi":"10.1109/GlobalSIP.2018.8646519","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646519","url":null,"abstract":"We revisit the super multidimensional scaling (SMDS) wireless localization algorithm first proposed a decade ago, recasting it onto the complex-domain1. Under this new formulation, the edge kernel which carries both angle and distance information simultaneously and plays a central role in the SMDS algorithm, becomes a complex-valued rank-one matrix, resulting in a new complex-domain SMDS framework which yields several advantages over the original, including the elimination of redundancy and the enhancement of conditions to handle information erasure.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131730627","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 : 2018-11-01DOI: 10.1109/GlobalSIP.2018.8646641
José Clemente, Fangyu Li, Wenzhan Song
In this paper, the problem of how to balance the energy consumption during data processing in networks is investigated using a fog middleware. We first demonstrate that for a fog network with different kind of nodes, balancing the energy relies on a combinatorial optimization that is solved using graph theory. We propose a transformation of the transshipment graph problem to formulate an optimization problem that we solve with linear programming (LP). We show the possibility of balancing and extending the battery life of the whole network based on cooperation between nodes without jeopardizing individual nodes’ battery life. We use both, emulation and real scenarios to test our optimization algorithm. We show we can balance the network energy, keep all nodes alive and active ~95% of the time.
{"title":"OPTIMAL DATA TASK DISTRIBUTION FOR BALANCING ENERGY CONSUMPTION ON COOPERATIVE FOG NETWORKS","authors":"José Clemente, Fangyu Li, Wenzhan Song","doi":"10.1109/GlobalSIP.2018.8646641","DOIUrl":"https://doi.org/10.1109/GlobalSIP.2018.8646641","url":null,"abstract":"In this paper, the problem of how to balance the energy consumption during data processing in networks is investigated using a fog middleware. We first demonstrate that for a fog network with different kind of nodes, balancing the energy relies on a combinatorial optimization that is solved using graph theory. We propose a transformation of the transshipment graph problem to formulate an optimization problem that we solve with linear programming (LP). We show the possibility of balancing and extending the battery life of the whole network based on cooperation between nodes without jeopardizing individual nodes’ battery life. We use both, emulation and real scenarios to test our optimization algorithm. We show we can balance the network energy, keep all nodes alive and active ~95% of the time.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134160894","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 : 2018-11-01DOI: 10.1109/GLOBALSIP.2018.8646654
Chase P. Dowling, D. Kirschen, Baosen Zhang
A significant portion of a business’ annual electrical payments can be made up of coincident peak charges: a transmission surcharge for power consumed when the entire system is at peak demand. This charge occurs only a few times annually, but with per-MW prices orders of magnitudes higher than non-peak times. A business is incentivized to reduce its power consumption, but accurately predicting the timing of peak demand charges is nontrivial. In this paper we present a decision framework based on predicting the day-ahead likelihood of peak demand charges. We train a feed-forward neural net-work to estimate the probability of system demand peaks and show it outperforms conventional forecasting methods using historical load. Using ERCOT demand and weather data from 2010-2017, we show the effectiveness of our framework.
{"title":"COINCIDENT PEAK PREDICTION USING A FEED-FORWARD NEURAL NETWORK","authors":"Chase P. Dowling, D. Kirschen, Baosen Zhang","doi":"10.1109/GLOBALSIP.2018.8646654","DOIUrl":"https://doi.org/10.1109/GLOBALSIP.2018.8646654","url":null,"abstract":"A significant portion of a business’ annual electrical payments can be made up of coincident peak charges: a transmission surcharge for power consumed when the entire system is at peak demand. This charge occurs only a few times annually, but with per-MW prices orders of magnitudes higher than non-peak times. A business is incentivized to reduce its power consumption, but accurately predicting the timing of peak demand charges is nontrivial. In this paper we present a decision framework based on predicting the day-ahead likelihood of peak demand charges. We train a feed-forward neural net-work to estimate the probability of system demand peaks and show it outperforms conventional forecasting methods using historical load. Using ERCOT demand and weather data from 2010-2017, we show the effectiveness of our framework.","PeriodicalId":119131,"journal":{"name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131694164","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：