Int. J. Adv. Sci. Eng. Vol.9 No.1 2591-2598 (2022) 2591 E-ISSN: 2349 5359; P-ISSN: 2454-9967 Divya & Umamaheswari International Journal of Advanced Science and Engineering www.mahendrapublications.com Solar Power Forecasting Methods – A Review R. Divya, S. Umamaheswari* Department of Electrical and Electronics, Mahendra Engineering College, Mahendhirapuri, Mallasamudram - 637 503, Namakkal District, Tamil Nadu, India. INTRODUCTION Due to rapid exhaustion of the fossil fuels and the concept of the Global warming the non renewable energy sources have been losing importance. To estimate the performance of PV installations in the approaching years the effect of global warming have been analyzed by Peters et al.,[1]. In case of the Industrial and home loads solar energy is of primary importance [2] but only demerit is that they are unpredictable in nature. Different amounts of electricity are generated by solar plants in case of various climatic condition and solar radiation [3]. There has been more change noticed in case of the output power. This change can happen at any time and it is not constrained [4]. This often leads to load-generation incongruity in the grid, thus on the whole making the solar power forecasting quite vital, more important while taking into consideration of the high penetration solar grid [5]. The Grid integration with the renewable energy sources is quite complex. The Grid management complexity occurs due to the fitful perspective of the solar energy and moreover balancing the electrical energy generation and consumptions becomes challenging [6]. Most common issues that arise during the generations and consumption are voltage fluctuations, low power quality, instability. Asynchronous operations, variability and uncertainty are the main technical challenges that the operators are supposed to deal with while integrating renewable energy with the grid [7]. For the purpose of optimal management of the electrical grid accurate forecasting of solar power is essential [8]. In case of dealing with the generated power, scheduling, minimizing the cost of production of electrical energy, overcrowding management and for the purpose of better operation of the power grid. Solar power forecasting is required. While the penetration of the grid increases the solar power prediction is critical. For the purpose of controlling electricity variation usage of storage systems with renewable energy is suggested by many researches. For the purpose of maintaining a continuous flow of electricity, to dampen the fluctuations and to absorb excess power mostly the storage systems are being preferred. Forecasting ABSTRACT: Solar power forecasting is crucial for the purpose of ensuring grid stability and proper grid management. Recent advancements with inside the discipline of solar power forecasting are presented, and the main focus is on the different types of Machine Learning (ML) Techniques used. These ML techniques can solve both the complex and nonlinear data structures. The two types of solar power forecasting are direct and indirect. It entails three models namely: plane of array irradiance, estimating solar irradiance forecast, solar performance. For the purpose of classification of solar power forecasting we take into consideration 3 main parameters such as the Forecast Horizon, Input Parameters and the Forecasting methodology. During the failure of the real-time data acquisition or with inside the case of unavailability of solar power for a new PV plant the concept of Indirect solar power forecasting can be used. According to recent studies models like the hybrid models, deep neural networks take over the conventional methods of the short-term solar forecasting. Data-preparation techniques and various intelligent optimizations enhance the performance accuracy. KEYWORDS: Optimization, Direct Forecasting, Indirect Forecasting, SVM, ELM, ANN, MLR, Forecast Horizon, Global Horizontal Irradiance. https://doi.org/10.29294/IJASE.9.1.2022.2591-2598 ©2022 Mahendrapublications.com, All rights reserved *Corresponding Author: umas.sundar@gmail.com Received: 11.06.2022 Accepted: 27.07.2022 Published on: 01.08.2022