k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data

Abstract

This paper proposes a novel methodology for very short term forecasting of hourly global solar irradiance (GSI). The proposed methodology is based on meteorology data, especially for optimizing the operation of power generating electricity from photovoltaic (PV) energy. This methodology is a combination of k-nearest neighbor (k-NN) algorithm modelling and artificial neural network (ANN) model. The k-NN-ANN method is designed to forecast GSI for 60 min ahead based on meteorology data for the target PV station which position is surrounded by eight other adjacent PV stations. The novelty of this method is taking into account the meteorology data. A set of GSI measurement samples was available from the PV station in Taiwan which is used as test data. The first method implements k-NN as a preprocessing technique prior to ANN method. The error statistical indicators of k-NN-ANN model the mean absolute bias error (MABE) is 42 W/m 2 and the root-mean-square error (RMSE) is 242 W/m 2 . The models forecasts are then compared to measured data and simulation results indicate that the k-NN-ANN-based model presented in this research can calculate hourly GSI with satisfactory accuracy.

A Review on Artificial Intelligence Applications for Grid-Connected Solar Photovoltaic Systems

“…This research opens a new avenue for the development of probabilistic renewable energy management systems to support energy trading platforms and help the smart grid operators with critical decision making during the inherent uncertainty of stochastic power systems. Apart from the deep learning and neural network approaches, the use of machine-learning classifiers, such as the multilayer perceptron neural network [75], Naïve Bayes approach [76], and k-nearest neighbor neural network [77], and evolutionary algorithms, such as multigene genetic programming [75], are also widely adapted for solar irradiance forecasting. A brief comparison of the discussed literature on solar irradiance forecasting is provided in Table 4.…”

Machine learning meets big spatial data

“…For example, Quad-tree partitioning [15] is used for: (a) balancing the convolution computation in Convolutional Neural Networks (CNN) for object detection applications [21] and (b) efficient automatic features extraction and matrix factorization operations inside deep learning models [57]. Meanwhile, k-nearest neighbor operations are used to efficiently build specific neural network architectures from big spatial datasets [6,33]. Then, we discuss the role of deep learning in efficiently supporting numerous large-scale spatial prediction queries (e.g., aggregate prediction [54], fore- casting queries [28]), and other spatial analysis tasks (e.g., geospatial object detection [56], outdoors localization [46]).…”

Research on the joint fluctuation laws between locational marginal price and renewables based on complex networks: A case study in Independent System Operator New England

“…If there is great confidence in the short‐term hydro, wind, and solar power generation forecast, it is feasible to forecast the LMP trend according to the above analysis results. For instance, if it is known that the joint fluctuation pattern of the last time is RRFR , given the fluctuation pattern of hydro, wind, and solar power generation of the next step (about 5 minutes later) is RFR , then it can be forecasted that the LMP fluctuation pattern of the next step is most likely to be R, followed by E .…”