{"title":"Short- and long-term electricity load forecasting using classical and neural network based approach: A case study for the Philippines","authors":"Mary Joyce T. Bantugon, R. J. Gallano","doi":"10.1109/TENCON.2016.7848779","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848779","url":null,"abstract":"Higher quality of power service is needed in order to sustain the increasing economic activities of a growing country such as the Philippines. An important step in achieving such goal is to have a good forecasting model that could accurately model the load behavior that must be met at all cost in order to have a secure and optimal electrical power system. This paper compared the performance of Holt-Winters' method and neural network both in short and long term Philippine electricity demand forecasting. The results show that although all methods can model the data under study well, the Holt-Winters' method yielded the most promising results both on short and long term forecasting with a mean absolute percentage error(MAPE) of about 9% and 3% respectively. A simple combination of the two models was also made and tested for hour-ahead load projection. The corresponding mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean square error (RMSE) were measured and served as the performance metrics for all methods considered in this paper.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121230791","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}
{"title":"Experimental investigation of multiphase transformer fed induction motor","authors":"B. Jyothi, M. Rao, S. Karthikeyan","doi":"10.1109/TENCON.2016.7848618","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848618","url":null,"abstract":"The production of multiphase system was a challenging task in earlier days, multiphase means more than three phases and very much popular now a days due to eminent features compared to conventional three-phase counter parts. In order to obtain the multiphase machine, it requires same phase input with respect to the no. of phases at the output. This paper mainly focuses on five phases because even after failure of one phase, the performance does not degrade much. Therefore, to attain a five phase supply a multiphase transformer connection is proposed. The induction motor is (five phase) fed by the output of the proposed transformer connection scheme. The performance of the motor is analyzed by an experimental investigation through experiment set up and MATLABR@, the simulation results are presented in the form of computer traces and high traded performance of the machine are discussed, under balanced as well as unbalanced supply conditions.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"208 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114315072","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}
{"title":"A lower switching noise two-legs three-phase inverter applying new type modulation scheme","authors":"A. Hirota, S. Mekhilef, M. Nakaoka","doi":"10.1109/TENCON.2016.7847963","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7847963","url":null,"abstract":"This paper mentions about a lower switching noise control method for two-legs three-phase inverter. Usually, six switch devices are necessary to construct three-phase inverter, one of two-legs type inverter can generate three-phase voltage. This type inverter uses voltage divide capacitors, and often uses rectified voltage source with ripple component. To switch control of the inverter, PWM method is generally used. But in the case of PWM measure, large switching noise peak components appear on the multiple numbers of the carrier frequency, and this causes noise interference problem to the peripheral equipment. For the purpose of reducing large switching noise components of two-legs three-phase inverter, this paper proposes a novel type switch control scheme. The proposed method improves delta-sigma modulator and also removes input voltage fluctuation effect simultaneously.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116187287","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}
{"title":"Improvement of velocity control in the permanent magnet-HTS hybrid magnetically levitated conveyance system","authors":"Y. Takaki, T. Sumida, S. Ohashi","doi":"10.1109/TENCON.2016.7848620","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848620","url":null,"abstract":"The hybrid magnetically levitated conveyance system has been developed. In this system, pinning force of the HTS achieves stable levitation and guidance without control. Interaction between the permanent magnet and the air core copper coils (propulsion coils) generates propulsion force. As larger propulsion force is needed to improve propulsion characteristics, the pinned flux of the HTS for keeping the carrier levitation is also used. The propulsion coils under the influence of the HTSs are excited, and then propulsion force is added. To control the carrier velocity, improved excitation method for the propulsion coils is introduced. The hysteresis region around the target velocity is defined. By choosing the adequate hysteresis region, the exceeded acceleration and deceleration are suppressed. From the experimental results, the average velocity error decreases about 30% and rise time is improved by about 20%.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121542414","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}
{"title":"Traffic flow prediction with Long Short-Term Memory Networks (LSTMs)","authors":"Hong Shao, B. Soong","doi":"10.1109/TENCON.2016.7848593","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848593","url":null,"abstract":"Accurate traffic flow information is crucial for an intelligent transportation system management and deployment. Over the past few years, many existing models have been designed for short-term traffic flow prediction. However, they fail to provide favorable results due to their shallow architectures or incapability to extract the sequence correlations in the data. In this paper, we explore the application of Long Short-Term Memory Networks (LSTMs) in short-term traffic flow prediction. As a deep learning approach, LSTMs are able to learn more abstract representations in the non-linear traffic flow data. The intrinsic feature of capturing long-term dependencies in a sequential data also makes it a suitable choice in traffic prediction. Experiments on real traffic data sets indicate a good performance of our model. The LSTMs architecture is also compared with state-of-the-art models and experiments show that our model achieves desirable results by lowering the MAPE metrics to 5.4%.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121546305","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}
{"title":"Dynamic security analysis for voltage security using Decision Trees","authors":"N. Chaudhari, Trupti P. Hinge, S. Dambhare","doi":"10.1109/TENCON.2016.7848133","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848133","url":null,"abstract":"Power systems operations are affected by various contingencies like sudden increase or throw off of load or generator, switching of transmission line, etc. Voltage insecurity is mainly caused due to lack of reactive power at the bus. In this paper, an algorithm based on Decision Tree (DT) is proposed for the assessment of dynamic security of the system considering voltage stability. Voltage Stability Load Index (VSLI) is used as attribute for formulation of Decision Tree (DT). The load shedding and switching of capacitor banks is proposed to avoid voltage insecurity. The extensive case studies on 5 bus and IEEE New England 39 bus system in DigSILENT demonstrates the effectiveness of the proposed scheme.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124349657","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}
{"title":"Auxiliary noise power scheduling in active noise control systems with acoustic feedback path modeling","authors":"Zhe Wu, Weiming Ni","doi":"10.1109/TENCON.2016.7848053","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848053","url":null,"abstract":"This paper proposes a new method to model the acoustic feedback path in active noise control (ANC) systems. The auxiliary noise is injected to track the variation of acoustic feedback path, but it will degrade the noise reduction performance (NRP) after convergence. In most existing methods, auxiliary noise with fixed power is introduced throughout the experiment. An adaptive strategy is proposed to adapt the power of auxiliary noise in this paper. In this method, the gain of auxiliary noise is controlled by the power increment of the error signal of feedback path modeling (FBPM) filter, and the power of the input signal of anti-noise generation filter. The effectiveness of the proposed method is verified by computer simulations.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124058538","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}
{"title":"Low frequency region of vocal tract information for speech / music classification","authors":"B. K. Khonglah, S. Prasanna","doi":"10.1109/TENCON.2016.7848506","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848506","url":null,"abstract":"This work explores the energy variation in low frequency region corresponding mostly to the first formant of speech for speech / music classification. In speech, there are alternating states between high and low vowels. The information about highness of a vowel is characterized by the first formant. Due to the presence of these states in speech, there is higher energy variation around the first formant of speech whereas this kind of nature is not present in case of music. The energy variation around the first formant can be expressed in terms of the filter bank energy variance. Different distributions of the filter bank are explored to find the frequency range which gives the best discrimination, in terms of the first formant energy variation for the task. The best performing filter bank energy variance coefficient which represents this frequency range is derived. This coefficient called the Energy Variance of Inverse Mel Filter No. 2 (EVIMF2) is compared with the state of the art existing features. It is observed that performance of the proposed feature is better than the existing features. On combining this feature with the existing ones, an additional improvement is achieved for the speech / music classification task.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127724974","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}
Muhammad Faisal Zainal Abiden, Stephen Chai, Antoine Fagette
{"title":"Simulating a disaster-social solidarity in an emergency","authors":"Muhammad Faisal Zainal Abiden, Stephen Chai, Antoine Fagette","doi":"10.1109/TENCON.2016.7847965","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7847965","url":null,"abstract":"Due to the non-predictive nature of disasters, there is little first-hand data available which in turn is a serious constraint to conduct research on the implication of disasters on urban population. Computational sociology aims at by-passing this issue by simulating the situation that cannot be observed. This paper attempts to use agent-based simulation models to (i) examine the importance of Durkheim's notion of Social Solidarity on behavioral responses in an emergency situation [1], (ii) observe the influence of this Social Solidarity notion in an emergency situation and (iii) validate the use of simulation in this case. Our team created therefore two simulation models representing two hypothetical scenarios, one where the population exhibits low social solidarity, while in the other the virtual entities show high social solidarity. Our findings conclude that low social solidarity leads to behavioral responses of panic and selfishness while high solidarity leads to an ordered and organized evacuation. With these findings, a theory of how a typical urban population would react to a large-scale disaster is formulated. The validity and effectiveness of agent-based modeling as an epistemological tool is also discussed.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127754109","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}
{"title":"A 2.2 kW SiC based high frequency battery charger for substation backup power supply","authors":"A. Choudhury","doi":"10.1109/TENCON.2016.7847962","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7847962","url":null,"abstract":"This paper presents a 2.2 kW two-stage, high frequency AC-DC converter for substation battery charging with Nickel-Cadmium (NiCd) battery. Detailed analytical calculation of the converter parameters, analysis, and simulation studies are carried out to demonstrate the performance of the proposed system. As, substation converters are required to be naturally cooled to eliminate additional mechanical component like cooling fans, SiC (Silicon Carbide) switches are used for this project. These switches have much higher thermal limit compared to the Si based switches and losses are also quite low at higher switching frequencies. It helps to improve the overall efficiency of the AC-DC converter as well. Control strategy is developed to operate the battery charger in both CC and CV mode. Detailed list of parameters used for this proposed system is also presented.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127789596","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}