Abstract This paper presents three ensemble learning models for short term load forecasting. Machine has evolved quickly in recent years, leading to novel and advanced that are improving the forecasting results multiple fields. However, highly dynamic fields such as power energy systems, dealing with fast acquisition of large amounts data from sources taking advantage correlation between availa...

NoTeS project is developing a generic toolset for spatio-temporal forecasting and forecast uncertainty analysis through analyzing five widely different test cases: forecasting energy consumption, diagnosing quality variations at a pulp mill, estimating and controlling paper quality on the basis scanning sensors, supporting operational decisions at nuclear power plant, and segmenting medical ima...

In this paper we explore the consequences for forecasting of the following two facts: first, that over time statistical agencies revise and improve published data, so that observations on more recent events are those that are least well measured. Second, that economies are such that observations on the most recent events contain the the largest signal about the future. We discuss a variety of f...

• Support for very large deployments Would you like to become more demand-driven by using true end-customer demand for forecasting and replenishment planning? Are you able to understand and respond using downstream consumption data? Have you been unable to do this because of the large data volumes and performance limitations using traditional hardware and software? Oracle® In-Memory Consumption...

In the process of cointegration analysis, electricity consumption is chosen as the explained variable, and GDP per capita, heavy industry share, and efficiency improvement are chosen as the explanatory variables; then a cointegration model is put forward, which shows that there is a cointegration relationship between the explained variable and explanatory variables. The explained and explanator...

Managing electrical energy supply is a complex task. The most important part of electric utility resource planning is forecasting of the future load demand in the regional or national service area. This is usually achieved by constructing models on relative information, such as climate and previous load demand data. In this paper, a genetic programming approach is proposed to forecast long term...

Against a backdrop of healthy domestic and foreign demand, the steel industry is continuing its fundamental trend of increasing production for the manufacturing industry. Meanwhile, since the steel industry accounts for approximately 11% of final energy consumption in Japan, efforts to improve the efficiency of energy usage have been pursued actively for a long time. Since the first oil crisis,...

The Wavelet Neural Network (WNN) is widely used in power load forecasting. In view that the traditional WNN easily falls into the local minimum and has unstable forecast results, a new power load forecasting model of combining the AdaBoost algorithm with WNN was put forward to improve the forecasting accuracy and generalization ability. Firstly, the method performed the pre-treatment for the hi...

The use of a minimum quantity of lubrication (MQL) with extremely low consumption of lubricant in machining processes has been reported as a technologically and environmentally feasible alternative to conventional flood cooling. In hot machining, the external heat source is applied during machining that will assist to increase machining performance. Many external heating techniques are availabl...