Pub Date : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909750
Xiang Fan, Qing-Sheng Hu, Guo Cao
This paper investigates a grouping-based extended discontinuous reception (eDRX) scheme for smart grid in order to save energy efficiently. By dividing users into different groups and assigning them different eDRX parameters, each group can employ appropriate cycle of themselves and only respond in this cycle rather than work in the whole time. Based on a semi- Markov model, the proposed eDRX process has been simulated and compared with standard DRX from the aspects of power saving factor and wake-up delay. Simulation results show that our scheme outperforms standard DRX in many cases, and a good tradeoff between power saving factor and wake-up delay should be considered properly for practical applications.
{"title":"Grouping-Based Extended Discontinuous Reception with Adjustable eDRX Cycles for Smart Grid","authors":"Xiang Fan, Qing-Sheng Hu, Guo Cao","doi":"10.1109/SmartGridComm.2019.8909750","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909750","url":null,"abstract":"This paper investigates a grouping-based extended discontinuous reception (eDRX) scheme for smart grid in order to save energy efficiently. By dividing users into different groups and assigning them different eDRX parameters, each group can employ appropriate cycle of themselves and only respond in this cycle rather than work in the whole time. Based on a semi- Markov model, the proposed eDRX process has been simulated and compared with standard DRX from the aspects of power saving factor and wake-up delay. Simulation results show that our scheme outperforms standard DRX in many cases, and a good tradeoff between power saving factor and wake-up delay should be considered properly for practical applications.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122297820","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909707
Ayman Uddin Mahin, S. Islam, Md. Farhad Hossain
Power transmission monitoring and control are essential components of a smart grid. Power transmission capacity of an overhead transmission line is greatly dependent on the sag of the line. When the sag is lower, more power can be transmitted safely through the line. Due to this, real-time sag measurement and monitoring is important for effective transmission of power through the line. In this paper, a mmWave based sag measurement technique incorporating parabolic approximation is proposed which improves the accuracy of sag calculation. Impact of different system parameters on the calculated value of the sag is also investigated. The results show that the proposed method can achieve better accuracy even with smaller number of samples, though the accuracy degrades with error in angle of arrival.
{"title":"Millimeter Wave Based Sag Measurement Using Parabolic Approximation for Smart Grid Overhead Transmission Line Monitoring","authors":"Ayman Uddin Mahin, S. Islam, Md. Farhad Hossain","doi":"10.1109/SmartGridComm.2019.8909707","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909707","url":null,"abstract":"Power transmission monitoring and control are essential components of a smart grid. Power transmission capacity of an overhead transmission line is greatly dependent on the sag of the line. When the sag is lower, more power can be transmitted safely through the line. Due to this, real-time sag measurement and monitoring is important for effective transmission of power through the line. In this paper, a mmWave based sag measurement technique incorporating parabolic approximation is proposed which improves the accuracy of sag calculation. Impact of different system parameters on the calculated value of the sag is also investigated. The results show that the proposed method can achieve better accuracy even with smaller number of samples, though the accuracy degrades with error in angle of arrival.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124091833","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909723
H. Schwefel, J. Rasmussen, R. Olsen, Henrik Ringgaard, N. Silva
Knowledge of currents in individual Low Voltage feeders of a secondary substation is interesting for distribution system operators for a variety of purposes. Deploying measurement devices at each feeder in each substation, however, can be costly. Due to the increasing deployment of Smart Meters, the knowledge about currents at each connected customer is in principle available. This paper proposes and evaluates an approach to determine the feeder currents taking into account the impact of measurement errors of Smart Meter measurements. The developed approach makes a rigorous derivation of confidence intervals for the calculated voltage and current values utilizing a subset of measured voltages and currents as input. The approach is applied to two realistic low voltage grids and the impact of measurement errors and missing smart meter measurements is quantitatively analyzed.
{"title":"Using Smart Meter measurements to manage accuracy of current calculations in LV feeders","authors":"H. Schwefel, J. Rasmussen, R. Olsen, Henrik Ringgaard, N. Silva","doi":"10.1109/SmartGridComm.2019.8909723","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909723","url":null,"abstract":"Knowledge of currents in individual Low Voltage feeders of a secondary substation is interesting for distribution system operators for a variety of purposes. Deploying measurement devices at each feeder in each substation, however, can be costly. Due to the increasing deployment of Smart Meters, the knowledge about currents at each connected customer is in principle available. This paper proposes and evaluates an approach to determine the feeder currents taking into account the impact of measurement errors of Smart Meter measurements. The developed approach makes a rigorous derivation of confidence intervals for the calculated voltage and current values utilizing a subset of measured voltages and currents as input. The approach is applied to two realistic low voltage grids and the impact of measurement errors and missing smart meter measurements is quantitatively analyzed.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131143849","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909704
Lihan Fang, Fang Yang, Xuan Liu, Hailong Zhang, Jun Ye
In this paper, the spectral coexistence between the broadband power line communication system and the short wave radio system is analyzed. The variances of interference signals of each system over the other are obtained firstly, where the significant differences between the two networks are taken into consideration. And then, the global spectral efficiency of the two systems are derived under both uniform and non-uniform scenarios of power allocation among overlapped and non overlapped frequency spectrum. Moreover, some analytical and numerical evaluations of the global spectral efficiency effected by overlapped ratio and power allocation ratio are drawn to verify the proposed power allocation strategy.
{"title":"The Coexistence Between Broadband Power Line Communication and Shortwave Radio Systems with an Optimized Power Allocation Strategy","authors":"Lihan Fang, Fang Yang, Xuan Liu, Hailong Zhang, Jun Ye","doi":"10.1109/SmartGridComm.2019.8909704","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909704","url":null,"abstract":"In this paper, the spectral coexistence between the broadband power line communication system and the short wave radio system is analyzed. The variances of interference signals of each system over the other are obtained firstly, where the significant differences between the two networks are taken into consideration. And then, the global spectral efficiency of the two systems are derived under both uniform and non-uniform scenarios of power allocation among overlapped and non overlapped frequency spectrum. Moreover, some analytical and numerical evaluations of the global spectral efficiency effected by overlapped ratio and power allocation ratio are drawn to verify the proposed power allocation strategy.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131695999","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909706
F. Luo, G. Ranzi, M. Kolokotroni
Smart home energy management is one of the main topics in demand side management. In the literature, many Home Energy Management Systems (HEMSs) are designed to optimally schedule the operation ofhousehold appliances. However, most of existing work ignores the lifestyle related requirements of the user on the appliances’ operational dependencies. In this paper, we propose a new household appliance commitment model that integrates both the operational constraints of individual appliances and the dependency constraints among them. In this sense, the proposed HEMS can more accurately reflect the end user’s lifestyle requirements. Several simulation scenarios are designed to validate the proposed HEMS.
{"title":"Household Appliance Commitment with Appliance Dependency Modelling","authors":"F. Luo, G. Ranzi, M. Kolokotroni","doi":"10.1109/SmartGridComm.2019.8909706","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909706","url":null,"abstract":"Smart home energy management is one of the main topics in demand side management. In the literature, many Home Energy Management Systems (HEMSs) are designed to optimally schedule the operation ofhousehold appliances. However, most of existing work ignores the lifestyle related requirements of the user on the appliances’ operational dependencies. In this paper, we propose a new household appliance commitment model that integrates both the operational constraints of individual appliances and the dependency constraints among them. In this sense, the proposed HEMS can more accurately reflect the end user’s lifestyle requirements. Several simulation scenarios are designed to validate the proposed HEMS.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132378843","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909794
L. Orda, O. Gehrke, H. Bindner
Aggregation and aggregators can play an important role in enabling utilization of end user flexibility for provision of system services. A key element to achieve this is to ensure efficient operation of the aggregator and the aggregator’s ICT infrastructure plays a key role in that. Overlay networks has the potential to contribute to efficiently manage the portfolio of controlled units. Overlay networks provide the technology to enable and support distributed and decentralized communication for use with applications in the smart grid, e.g. to locate flexibility in particular network areas or units with certain characteristics or a combination thereof. These applications of overlay networks are very different from traditional use and the approach to testing them has to be adapted to this situation. Since the application scenario is different from traditional overlay network applications, it is unclear how to test, compare and validate the functionality relevant for smart grids. In this paper we examine the topics involved with testing decentralized overlay networks for smart grid applications, for simulated networks, for scalability and as deployed in physical smart grid research networks. We examine how to deploy and manage experiments efficiently and coherently on the physical infrastructure, with the goal of minimizing testing and development turnaround time. A simulation framework is built to support both and used in a case study, where an overlay network application for optimized routing in a smart grid, is tested and validated.
{"title":"Testing Overlay Networks in a Smart Grid using Simulated and Physical Networks","authors":"L. Orda, O. Gehrke, H. Bindner","doi":"10.1109/SmartGridComm.2019.8909794","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909794","url":null,"abstract":"Aggregation and aggregators can play an important role in enabling utilization of end user flexibility for provision of system services. A key element to achieve this is to ensure efficient operation of the aggregator and the aggregator’s ICT infrastructure plays a key role in that. Overlay networks has the potential to contribute to efficiently manage the portfolio of controlled units. Overlay networks provide the technology to enable and support distributed and decentralized communication for use with applications in the smart grid, e.g. to locate flexibility in particular network areas or units with certain characteristics or a combination thereof. These applications of overlay networks are very different from traditional use and the approach to testing them has to be adapted to this situation. Since the application scenario is different from traditional overlay network applications, it is unclear how to test, compare and validate the functionality relevant for smart grids. In this paper we examine the topics involved with testing decentralized overlay networks for smart grid applications, for simulated networks, for scalability and as deployed in physical smart grid research networks. We examine how to deploy and manage experiments efficiently and coherently on the physical infrastructure, with the goal of minimizing testing and development turnaround time. A simulation framework is built to support both and used in a case study, where an overlay network application for optimized routing in a smart grid, is tested and validated.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133002771","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909727
Yanan Sun, V. Wong, L. Lampe
This paper examines the prospect of using the energy storage systems (ESSs) in the distribution network for frequency regulation service under the two-settlement market mechanism. A bi-level problem is formulated to determine the bidding strategy for the ESS which provides regulation service for the system operator in the day-ahead and real-time markets, where the upper-level problem maximizes the ESS’ revenue from frequency regulation and the lower-level problem models the system operator’s market clearing. The problem is rendered applicable for the ESSs in the distribution network by addressing the power flow constraints. The uncertainty associated with other competitive ESSs and the system frequency deviations are incorporated by using scenarios for possible realizations. The formulated problem is transformed to a mixed-integer linear program by replacing the lower-level problem with the Karush-Kuhn-Tucker (KKT) optimality conditions and tackling the nonconvexity in the objective function based on strong duality. Case studies are carried out on an IEEE 37-bus test feeder by using market data from California Independent System Operator (CAISO). The results demonstrate that the ESS can increase its revenue from frequency regulation by using our proposed method to determine the bidding strategy.
{"title":"Market Participation of Energy Storage Systems for Frequency Regulation Service: A Bi-level Model","authors":"Yanan Sun, V. Wong, L. Lampe","doi":"10.1109/SmartGridComm.2019.8909727","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909727","url":null,"abstract":"This paper examines the prospect of using the energy storage systems (ESSs) in the distribution network for frequency regulation service under the two-settlement market mechanism. A bi-level problem is formulated to determine the bidding strategy for the ESS which provides regulation service for the system operator in the day-ahead and real-time markets, where the upper-level problem maximizes the ESS’ revenue from frequency regulation and the lower-level problem models the system operator’s market clearing. The problem is rendered applicable for the ESSs in the distribution network by addressing the power flow constraints. The uncertainty associated with other competitive ESSs and the system frequency deviations are incorporated by using scenarios for possible realizations. The formulated problem is transformed to a mixed-integer linear program by replacing the lower-level problem with the Karush-Kuhn-Tucker (KKT) optimality conditions and tackling the nonconvexity in the objective function based on strong duality. Case studies are carried out on an IEEE 37-bus test feeder by using market data from California Independent System Operator (CAISO). The results demonstrate that the ESS can increase its revenue from frequency regulation by using our proposed method to determine the bidding strategy.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133352720","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909800
Megan Culler, K. Davis, A. Sahu
Sensor integrity is arguably the most critical feature to protect in cyber-physical systems. Since power systems are cyber-physical systems with ubiquitous sensors that monitor and protect the grid, data must be trustworthy. Process safety and control decisions ultimately depend on data. The focus of this paper is how to design and apply perturbation based detection for sensor verification, under full AC unobservable false data injection (AU-FDI) attacks, by combining an active probing strategy with cyber-side data based on the cyber-physical situational awareness model CyPSA. A case study on a cyber-physical eight substation model is presented, where we construct an AU-FDI attack and introduce our probing-based detection solution and evaluate it with varying probe signals, values, and locations. Results demonstrate how sensor data in power systems can be systematically authenticated using perturbation-based techniques and how different perturbation types and locations affect the results. The case study then demonstrates the improvements to verification by using both physical and cyber data, as CyPSA provides risk prioritization in the form of authenticity weight measure of the sensors, for enhancing the security of power systems from a cyber-physical point of view.
{"title":"PAVED: Perturbation Analysis for Verification of Energy Data","authors":"Megan Culler, K. Davis, A. Sahu","doi":"10.1109/SmartGridComm.2019.8909800","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909800","url":null,"abstract":"Sensor integrity is arguably the most critical feature to protect in cyber-physical systems. Since power systems are cyber-physical systems with ubiquitous sensors that monitor and protect the grid, data must be trustworthy. Process safety and control decisions ultimately depend on data. The focus of this paper is how to design and apply perturbation based detection for sensor verification, under full AC unobservable false data injection (AU-FDI) attacks, by combining an active probing strategy with cyber-side data based on the cyber-physical situational awareness model CyPSA. A case study on a cyber-physical eight substation model is presented, where we construct an AU-FDI attack and introduce our probing-based detection solution and evaluate it with varying probe signals, values, and locations. Results demonstrate how sensor data in power systems can be systematically authenticated using perturbation-based techniques and how different perturbation types and locations affect the results. The case study then demonstrates the improvements to verification by using both physical and cyber data, as CyPSA provides risk prioritization in the form of authenticity weight measure of the sensors, for enhancing the security of power systems from a cyber-physical point of view.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130365742","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909785
Weigao Sun, M. Zamani
This paper develops a nonparameteric Bayesian approach for the probabilistic representation of power system uncertainties involved with wind, solar and load power. The developed approach based on Dirichlet process mixture model (DPMM) analytically formulates the probability distributions of power uncertainties without prior knowledge of the number of mixture components. This provides a great improvement in probabilistic representation of power uncertainties as the proposed model can accommodate the ever growing power data. A computationally efficient VBI method is exploited to estimate the parameters involved with DPMM. Moreover, a novel truncated DPMM is designed to fit the special truncation feature of wind power distributions. The performance of proposed probabilistic representation approach for power uncertainties on real datasets of wind, solar and load power are validated and illustrated in the numerical simulations.
{"title":"A Nonparametric Bayesian Approach for Probabilistic Representation of Power Uncertainties","authors":"Weigao Sun, M. Zamani","doi":"10.1109/SmartGridComm.2019.8909785","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909785","url":null,"abstract":"This paper develops a nonparameteric Bayesian approach for the probabilistic representation of power system uncertainties involved with wind, solar and load power. The developed approach based on Dirichlet process mixture model (DPMM) analytically formulates the probability distributions of power uncertainties without prior knowledge of the number of mixture components. This provides a great improvement in probabilistic representation of power uncertainties as the proposed model can accommodate the ever growing power data. A computationally efficient VBI method is exploited to estimate the parameters involved with DPMM. Moreover, a novel truncated DPMM is designed to fit the special truncation feature of wind power distributions. The performance of proposed probabilistic representation approach for power uncertainties on real datasets of wind, solar and load power are validated and illustrated in the numerical simulations.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134412993","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 : 2019-10-01DOI: 10.1109/SmartGridComm.2019.8909760
Junkai Liang, Wenyuan Tang
With the rapid increase in the distributed wind generation, considerable efforts have been devoted to the microgrid day-ahead scheduling. The effectiveness of these methods will highly depend on the selection of the uncertainty set. In this work, we propose a distribution-free approach for wind power scenario generation using sequential generative adversarial networks. To capture the temporal correlation, the proposed model adopts the long short-term memory architecture and uses the concept of generative adversarial networks coupled with reinforcement learning to guide the learning process. In contrast to the existing methods, the proposed model avoids manual labeling and captures the complex dynamics of the weather. The proposed scenario generation method is applied to the wind power dataset of Bonneville Power Administration. The results indicate that the scenarios generated by our model can characterize the variability of wind power in a better manner. The generated scenarios are compared with those produced by Gaussian distribution and kernel density estimation, in terms of two statistical scores.
{"title":"Wind Power Scenario Generation for Microgrid Day-Ahead Scheduling Using Sequential Generative Adversarial Networks","authors":"Junkai Liang, Wenyuan Tang","doi":"10.1109/SmartGridComm.2019.8909760","DOIUrl":"https://doi.org/10.1109/SmartGridComm.2019.8909760","url":null,"abstract":"With the rapid increase in the distributed wind generation, considerable efforts have been devoted to the microgrid day-ahead scheduling. The effectiveness of these methods will highly depend on the selection of the uncertainty set. In this work, we propose a distribution-free approach for wind power scenario generation using sequential generative adversarial networks. To capture the temporal correlation, the proposed model adopts the long short-term memory architecture and uses the concept of generative adversarial networks coupled with reinforcement learning to guide the learning process. In contrast to the existing methods, the proposed model avoids manual labeling and captures the complex dynamics of the weather. The proposed scenario generation method is applied to the wind power dataset of Bonneville Power Administration. The results indicate that the scenarios generated by our model can characterize the variability of wind power in a better manner. The generated scenarios are compared with those produced by Gaussian distribution and kernel density estimation, in terms of two statistical scores.","PeriodicalId":377150,"journal":{"name":"2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116705169","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：