Search

The online retail market shows a sharp increase in traffic during holiday sales. The ability to distinguish customers who will likely purchase is critical for provisioning traffic and for providing cost-effective promotions. This paper uniquely studies the browsing and purchasing behaviors of online shoppers during a yearly sale event in China, the world’s largest online marketplace. Based on 31 million action logs gathered from wide residential areas, we characterize the steps leading to purchases and determine their precursors. We investigate the effect of time (e.g., date, time of date), environment (e.g., platform, viewed category), and action (e.g., session time, clicks, sequence) on purchases. Action cues from shopping behaviors can be used for early detection. While most shoppers start with strong intentions to purchase, yet the moment of ordering comes rather impulsively within 30 seconds to several minutes of browsing. The predictive accuracy reaches as a high AUC of 0.924. The findings in this paper provide an understanding of traffic during mega sale events that can help online shops plan and provide a better user experience for upcoming shopping festivals. [ABSTRACT FROM AUTHOR]

Conventionally, the 2-parameter Weibull model, Arrhenius-Weibull model, has been used vastly for transformer aging-dependent unavailability modeling. However, this model only uses the lifetime feature to describe the transformer's degradation process and to calibrate the Weibull parameters, which harms the accuracy of aging-dependent unavailability forecasting. In response, this paper develops a 3-calibratable-parameter Weibull model for evaluating the transformer aging-dependent unavailability. In the proposed model, both the individualized aging threshold and lifetime are taken into the calibration of the Weibull parameters to accurately characterize the heterogeneity in transformer populations. First, a degree of polymerization (DP) analysis and Monte Carlo Simulation (MCS) based approach is proposed for estimating the transformers’ uncertain aging thresholds and lifetimes. Then, the Maximum Likelihood Estimate and Particle Swarm Optimization are jointly adopted to model the relationship among the calibratable Weibull parameters, aging threshold, and lifetime. Finally, the analytical formula of aging-dependent unavailability is derived from the established 3-calibratable-parameter Weibull model using an integral-discretization method. A real utility application example in China's Chongqing power system has been presented to validate and demonstrate the practicality and usefulness of this method. [ABSTRACT FROM AUTHOR]

The insulation paper loss of life (LOL) of a distribution transformer (DT) is largely determined by its winding hot-spot temperature. It is mainly estimated via the transformer load, ambient temperature, and related physical parameters. Fortunately, advanced metering infrastructure (AMI) can provide load profiles of DTs, allowing a cost-effective LOL estimation solution. However, the AMI dataset contains measurement errors that significantly reduce LOL estimation accuracy. A forecasting method is needed to recover the erroneous AMI data. This is a challenging problem, as the load profiles of DTs are nonstationary and volatile. We propose an ensemble of stacked long short-term memory (ES-LSTM) networks to simultaneously capture load consumption patterns of DTs and their correlations. The ES-LSTM consists of two independent LSTM networks and a feed-forward neural network (FFNN) stacked on top of them. A two-stage training procedure is applied. In the first stage, two LSTM networks are trained to capture the daily or weekly load patterns. In the second stage, the FFNN is trained to optimally combine the last hidden outputs of the two LSTM networks. Field verification is conducted using real AMI data obtained from an urban distribution utility in China. The test results confirmed the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Stationless bike-sharing systems such as Mobike are currently becoming extremely popular in China as well as some other big cities in the world. Compared to traditional bicycle-sharing systems, stationless bike-sharing systems do not need bike stations. Users can rent and return bikes at arbitrary locations through an App installed on their smart phones. Such a convenient and flexible bike-sharing mode greatly solves the last mile issue of the commuters, and better meets their real bike usage demand. However, it also poses new challenges for operators to manage the system. The first primary challenge is how to accurately estimate the real bike usage demand in different areas of a city and in different time intervals, which is crucial for the system planning and operation. This paper for the first time proposes a data driven approach for bike usage demand inference in stationless bike-sharing systems. The idea is that we first estimate the demands in some regions and time intervals from a small number of observed bike check-out/in data directly, and then use them as seeds to infer the region-level bike usage demands of an entire city. Specifically, we formulate this problem as a matrix completion task by modeling the bike usage demand as a matrix whose two dimensions are time intervals of a day and regions of a city, respectively. With the observation that POI distribution of a region is an important indicator to bike demand, we propose to utilize inductive matrix factorization by considering POIs as side information. As the bike usage data are highly correlated in both spatial and temporal dimensions, we also incorporate the spatial-temporal correlations as well as the balanced bike usage constraint into a joint optimization framework. We evaluate the proposed model on a large Mobike trip dataset collected from Beijing, and the experimental results show its superior performance by comparison with various baseline methods. [ABSTRACT FROM AUTHOR]

The popularity of online contents in social media frequently experiences ebb and flow, and thus its evolution often involves different stages, such as burst and valley. Exploring the patterns of popularity evolution, especially how burst forms and decays, and even further, predicting the trends of popularity evolution is both an important research topic and beneficial to support decision making for many applications, such as emergency management, business intelligence, and public security. Previous work on popularity prediction has focused on predicting the popularity volume of online contents, and at most, popularity burst and ignored the exploration of popularity evolution and the prediction of its stages. To fill this gap, in this paper, we propose our method for the popularity stage prediction problem both at the microscopic level and macroscopic level. At the microscopic level, we first extract multiple dynamic factors and infer future evolution stage by considering the contributions of different dynamic factors. At the macroscopic level, we extract the overall evolution patterns of popularity stages and adopt a pattern matching-based method to predict future popularity stages. We evaluate the proposed approach using tweets in SinaWeibo, the most popular Twitter-like social media platform in China. The experimental results show the effectiveness of our proposed approach in predicting popularity evolution stages. [ABSTRACT FROM AUTHOR]

Accurate and reliable low-voltage load forecasting is critical to optimal operation and control of distribution network and smart grid. However, compared to traditional regional load forecasting at high-voltage level, it faces tough challenges due to the inherent high uncertainty of the low-capacity load and distributed renewable energy integrated in the demand side. This paper proposes a novel hybrid ensemble deep learning (HEDL) approach for deterministic and probabilistic low-voltage load forecasting. The deep belief network (DBN) is applied to low-voltage load point prediction with the strong ability of approximating nonlinear mapping. A series of ensemble learning methods including bagging and boosting variants are introduced to improve the regression ability of DBN. In addition, the differencing transformation technique is utilized to ensure the stationarity of load time series for the application bagging and boosting methods. On the basis of the integrated thought of ensemble learning, a new hybrid ensemble algorithm is developed via integrating multiple separate ensemble methods. Considering the diversity in various ensemble algorithms, an effective K nearest neighbor classification method is utilized to adaptively determine the weights of sub-models. Furthermore, HEDL based probabilistic forecasting is proposed by taking advantage of the inherent resample idea in bagging and boosting. The effectiveness of the HEDL method for both deterministic and probabilistic forecasting has been systematically verified based on realistic load data from East China and Australia, indicating its promising prospective for practical applications in distribution networks. [ABSTRACT FROM AUTHOR]

Demand-side management (DSM) increases the complexity of forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from the data set. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to convert the continuity feature of input data into binomial distribution feature. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on the genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods. [ABSTRACT FROM AUTHOR]

With the rapid development of China high-speed railway, the low frequency oscillation (LFO) of electrical quantities appears more often recently and leads to some severe problems of train operation. To improve the traction line-side converter control and suppress the phenomenon economically and effectively, a model-based predictive direct power control (MPDPC) approach is proposed in this paper. The approach adopts a discrete-time model of traction line-side converter in d–q reference frame to predict the future values of the input active and reactive power. The optimal switching state is selected by minimizing a cost function of power to evaluate the power errors at the next sampling time. Through the theoretical analysis and simulations, the performance of MPDPC is compared with traditional transient direct current control (TDCC) that is widely adopted in China Railway High-Speed 3 electric-multiple-unit. The real-time online simulations based on Real-Time Laboratory (RT-LAB) are also realized to further validate the results. Moreover, two vehicle-grid cascade simulation systems are constructed, and the LFO suppressing capability of MPDPC and TDCC is compared. Finally, the steady-state characteristic, dynamic characteristic, and LFO suppressing capability of MPDPC are demonstrated through the analysis of key performance indexes. [ABSTRACT FROM AUTHOR]

Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for system reliability and promoting large-scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machines (SVM). In the process, the weather conditions are divided into four types which are clear sky, cloudy day, foggy day, and rainy day. In this paper, a one-day-ahead PV power output forecasting model for a single station is derived based on the weather forecasting data, actual historical power output data, and the principle of SVM. After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected PV systems is effective and promising. [ABSTRACT FROM PUBLISHER]

Due to its brief form and growing popularity, microblogging is becoming people’s favorite choice for seeking information and expressing opinions. Messages received by a user mainly depend on whom the user follows. Thus, recommending users with similar interests may improve the experience quality for information receiving. Since messages posted by microblogging users reflect their interests, and the keywords in the messages indicate their main focus to a large extent, we can discover users’ preferences by analyzing the user-generated contents. Moreover, users’ interests are not static, on the contrary, they change as time goes by. Based on such intuitions, in this paper, we propose a temporal-topic model to analyze users’ possible behaviors and predict their potential friends in microblogging. The model learns users’ latent preferences by extracting keywords on aggregated messages over a period of time via a topic model, and then the impact of time is considered to deal with interest drifts. The experimental results of friend recommendations on Sina Weibo, one of the most popular microblogging sites in China, have demonstrated the effectiveness of our model. [ABSTRACT FROM AUTHOR]