• Title/Summary/Keyword: Predictive

Search Result 5,234, Processing Time 0.037 seconds

Water consumption prediction based on machine learning methods and public data

  • Kesornsit, Witwisit;Sirisathitkul, Yaowarat
    • Advances in Computational Design
    • /
    • v.7 no.2
    • /
    • pp.113-128
    • /
    • 2022
  • Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

Predictive Location Management Strategy Using Two Directional Consecutive LAs in a Cellular Network (이동 통신망에서 방향성을 지닌 2개의 연속적 위치영역을 이용한 예측 위치 관리 전략)

  • Chang, I.K.;Hong, J.S.;Kim, J.P.;Lie, C.H.
    • Journal of the Korean Operations Research and Management Science Society
    • /
    • v.33 no.3
    • /
    • pp.43-58
    • /
    • 2008
  • In this paper, we have presented a dynamic, predictive location update scheme that takes into account each user's mobility patterns. A user's past movement history is used to create two-dimensional transition probability matrix which makes use of two directional consecutive location areas. A mobile terminal utilizes the transition probability to develop a predictive path which consists of several predictive nodes and then the location update is saved as long as a mobile user follows the predictive path. Using continuous-time Markov chain, cost functions of location update and paging are derived and it is shown that the number of predictive nodes can be determined optimally. To evaluate the proposed scheme, simulations are designed and the numerical analysis is carried out. The numerical analysis features user's mobility patterns and regularity, call arrival rates, and cost ratio of location update to paging. Results show that the proposed scheme gives lower total location management cost, compared to the other location update schemes.

Actual Energy Consumption Analysis of Temperature Control Strategies for Secondary Side Hot Water District Heating System with an Inverter (인버터시스템 적용 지역난방 시스템의 2차측 공급수 온도 제어방안에 따른 에너지사용량 실증 비교)

  • Cho, Sung-Hwan;Hong, Seong-Ki
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.27 no.4
    • /
    • pp.179-186
    • /
    • 2015
  • In this study, the actual energy consumption of the secondary side District Heating System (DHS) with different hot water supply temperature control methods is compared. The two methods are Outdoor Temperature Reset Control and Outdoor Temperature Predictive Control. While Outdoor Temperature Reset Control has been widely used for energy savings of the secondary side system, the results show that the Outdoor Temperature Predictive Control method saves more energy. In general, the Outdoor Temperature Predictive Control method lowers the supply temperature of hot water, and it reduces standby losses and increases the overall heat transfer value of heated spaces due to more flow into the space. During actual energy consumption monitoring, the Outdoor Temperature predictive Control method saves about 6.6% of energy when compared to the Outdoor Temperature Reset Control method. Also, it is found that at partial load condition, such as during daytime, the fluctuation of hot water supply temperature with Outdoor Temperature Reset Control is more severe than that with Outdoor Temperature Predictive Control. Thus, it proves that Outdoor Temperature Predictive Control is more stable even at partial load conditions.

Imposed Weighting Factor Optimization Method for Torque Ripple Reduction of IM Fed by Indirect Matrix Converter with Predictive Control Algorithm

  • Uddin, Muslem;Mekhilef, Saad;Rivera, Marco;Rodriguez, Jose
    • Journal of Electrical Engineering and Technology
    • /
    • v.10 no.1
    • /
    • pp.227-242
    • /
    • 2015
  • This paper proposes a weighting factor optimization method in predictive control algorithm for torque ripple reduction in an induction motor fed by an indirect matrix converter (IMC). In this paper, the torque ripple behavior is analyzed to validate the proposed weighting factor optimization method in the predictive control platform and shows the effectiveness of the system. Therefore, an optimization method is adopted here to calculate the optimum weighting factor corresponds to minimum torque ripple and is compared with the results of conventional weighting factor based predictive control algorithm. The predictive control algorithm selects the optimum switching state that minimizes a cost function based on optimized weighting factor to actuate the indirect matrix converter. The conventional and introduced weighting factor optimization method in predictive control algorithm are validated through simulations and experimental validation in DS1104 R&D controller platform and show the potential control, tracking of variables with their respective references and consequently reduces the torque ripple.

Improved Deadbeat Current Controller with a Repetitive-Control-Based Observer for PWM Rectifiers

  • Gao, Jilei;Zheng, Trillion Q.;Lin, Fei
    • Journal of Power Electronics
    • /
    • v.11 no.1
    • /
    • pp.64-73
    • /
    • 2011
  • The stability of PWM rectifiers with a deadbeat current controller is seriously influenced by computation time delays and low-pass filters inserted into the current-sampling circuit. Predictive current control is often adopted to solve this problem. However, grid current predictive precision is affected by many factors such as grid voltage estimated errors, plant model mismatches, dead time and so on. In addition, the predictive current error aggravates the grid current distortion. To improve the grid current predictive precision, an improved deadbeat current controller with a repetitive-control-based observer to predict the grid current is proposed in this paper. The design principle of the proposed observer is given and its stability is discussed. The predictive performance of the observer is also analyzed in the frequency domain. It is shown that the grid predictive error can be decreased with the proposed method in the related bode diagrams. Experimental results show that the proposed method can minimize the current predictive error, improve the current loop robustness and reduce the grid current THD of PWM rectifiers.

Predictive Validity of Pressure Ulcer Risk Assessment Scales among Patients in a Trauma Intensive Care Unit (외상중환자의 욕창 위험사정 도구의 타당도 비교)

  • Choi, Ja Eun;Hwang, Sun-Kyung
    • Journal of Korean Critical Care Nursing
    • /
    • v.12 no.2
    • /
    • pp.26-38
    • /
    • 2019
  • Purpose : The aims of this study were to identify the incidence of pressure ulcers and to compare the predictive validities of pressure ulcer risk assessment scales among trauma patients. Methods : This was a prospective observational study. A total of 155 patients admitted to a trauma intensive care unit in a university hospital were enrolled. The predictive validity of the Braden, Cubbin & Jackson, and Waterlow scales were assessed based on the sensitivity, specificity, positive and negative predictive values, and area under the receiver operating characteristic curve (AUC). Results : Of the patients, 14 (9.0%) subsequently developed pressure ulcers. The sensitivity, specificity, positive predictive values, and negative predictive values were 78.6%, 75.9%, 24.4%, and 97.3%, respectively, for the Braden scale (cut-off point of 12); 85.7%, 68.8%, 21.4%, and 98.0%, respectively, for the Cubbin & Jackson scale (cut-off point of 26); and 71.4%, 87.2%, 35.7%, and 96.9%, respectively, for the Waterlow scale (cut-off point of 18). The AUCs were 0.88 (Waterlow), 0.86 (Braden), and 0.85 (Cubbin & Jackson). Conclusion : The findings indicate that the predictive validity values of the Waterlow, Braden, and Cubbin & Jackson scales were similarly high. However, further studies need to also consider clinical usefulness of the scales.

Robustness of Predictive Density and Optimal Treatment Allocation to Non-Normal Prior for The Mean

  • Bansal, Ashok K.;Sinha, Pankaj
    • Journal of the Korean Statistical Society
    • /
    • v.22 no.2
    • /
    • pp.235-247
    • /
    • 1993
  • The predictive density function of a potential future observation and its first four moments are obtained in this paper to study the effects of a non-normal prior of the unknown mean of a normal population. The derived predictive density function is modified to study changes in utility curves, used to choose the optimum treatment from a given set of treatments, at a given level of stimulus due to slight deviations from normality of the prior distribution. Numerical illustrations are provided to exhibit some effectsl.

  • PDF

Robust Predictive Control of Robot Manipulator with The Bound Estimation

  • Kim, Jung-Kwan;Han, Myung-Chul
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.155.5-155
    • /
    • 2001
  • The robust predictive control law which use the bound estimation is proposed for uncertain robot manipulators. Since the control design of a real manipulator system may often be made on the basis of the imperfect knowledge about model, it´s an important tend to design a robust control law that will guarantee the desired performance of the manipulator under uncertain elements. In the preceeding work, the robust predictive control law was proposed. In this work, we propose a class of robust predictive control of manipulators with the bound estimate technique and fe stability based on Lyapunov function is presented.

  • PDF

Predictive controller using weighted input (입력 가중치를 이용한 예측제어)

  • 나상섭;신세희;어영구
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1989.10a
    • /
    • pp.343-347
    • /
    • 1989
  • In this paper, predictive control method using actual applied input which is the weighted summation of past inputs is presented. In conventional predictive control methods, a set of control inputs is computed and in these only the first element is applied to the process at each time instant. But this predictive control method based on conventional methods considers all computed control inputs. Consequently, the characteristic of response and the reliability of the control scheme in the case of imperfact model are improved.

  • PDF

Predictive Current Control of 12-Pulse Parallel Connected Dual Converter System (12펄스 병렬 연결 듀얼 컨버터 시스템의 예측전류제어)

  • 이창원;송인호;최창호
    • Proceedings of the KIPE Conference
    • /
    • 1998.07a
    • /
    • pp.405-408
    • /
    • 1998
  • In this paper, a predictive current control of 12-pulse parallel connected dual converter system with interphase transfromer(IPT) is presented. Firstly, 12-pulse parallel connected dual converter system and the predictive current control of this system is discussed. And the validity of the presented system and the excellence of the predictive current control response is proved through the simyulation and experiment result.

  • PDF