Online refinement of day‐ahead forecasting using intraday data for campus‐level load

Abstract

Day-ahead forecasting for campus-level load is important for better energy management, but especially difficult to be accurate, compared to large-scale loads such as cities or regions. This is because irregular and unpredictable behavior of individual loads in small-scale loads cannot be fully smoothed out and thus pose a negative impact on forecasting accuracy. This paper presents an online refinement strategy for day-ahead forecasting using intraday data for a campus-level load, focusing on self-adapting correction of forecasting considering load pattern. First, according to the load pattern forecasted by Classification and Regression Trees (CART) one day ahead, the correction parameter group is assigned to the correction model. If the correction conditions are met, the forecasting results for the rest of the day will be updated. After all-day load data is achieved, the actual load pattern can be identified and used to train CART model. To confirm the effectiveness of the proposed strategy, the model is evaluated by two datasets, a real-life dataset of an industrial park in Shanghai China and a public dataset of an institute campus in Delhi, India. The results demonstrate that the proposed strategy can improve short-term forecasting accuracy.

Scalable multi‐site photovoltaic power forecasting based on stream computing

“…Stream computing engine can also use realtime data for analysis and data-mining, thus preventing data value from decreasing over time. Especially Flink, a new stream computing framework [27], provides advanced features such as window aggregation and status management [28], which can utilize real-time data [29] and support the incremental learning [30,31] of neural network models. By integrating MQ and stream computing architecture within a cloud-based environment, operating costs can be regulated while facilitating real-time forecasting.…”

Forecasting-based electricity tariff selection for resident users with photovoltaic and energy storage considering forecast uncertainties

“…In the field of photovoltaic forecasting, reference [12] proposed a layered correction approach where forecasts from different time periods can complement each other based on continuously updated meteorological data. In terms of park-level load forecasting, reference [13] proposed a dynamic forecasting model based on load pattern recognition and intra-day corrections,which utilizes the data from the current day to update the final forecasting results in a rolling manner. Therefore, further research and development of timely updating methods for peak power demand forecasting are necessary to enhance the effectiveness of household energy management.…”