The solar power generation (SPG) prediction is indispensable to establish a reliable and secure power grid. The intelligent and knowledgeable techniques are required to forecast the most nonlinear and volatile SPG due to its dependency on fluctuating weather conditions (solar irradiance and temperature). In this work, an optimized Extreme Learning Machine (ELM) is employed to forecast real-time SPG of Chhattisgarh state of India by conceding weather conditions. The performance of ELM approach is enhanced by exploring relevant parameters such as weights, biases, and numbers of hidden layers. It requires computational techniques which are proficient enough to deal with high dimensional and complex problems. Teaching Learning Based Optimization (TLBO) technique is modified with two novel approaches to enhance the exploration and exploitation proficiency of TLBO algorithm. The collaboration of modified TLBO (MTLBO) and optimizable ELM technique is implemented to forecast SPG for four different case studies such as an hour ahead, a day ahead, a month ahead and three months ahead forecasting. The performance measures such as mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), mean arctangent absolute percentage error (MAAPE), and correlation of determination (R²) are used to demonstrate the performance of proposed approach. Diebold-Mariano (DM) test and forecasting effectiveness are employed to hypothetically corroborate the capability of MTLBO based ELM model to outperform different optimization based ELM, ELM (with randomly fixed weights and biases) and ANN models. The simulation results contribute the evidence of excel performance of proposed approach for SPG forecasting.

太阳能发电（SPG）预测对于建立可靠和安全的电网必不可少。由于 SPG 依赖于波动的天气条件（太阳辐照度和温度），因此需要智能和知识渊博的技术来预测最非线性和最易波动的 SPG。在这项工作中，采用优化的极限学习机（ELM）通过承认天气条件来预测印度恰蒂斯加尔邦的实时 SPG。通过探索相关参数（例如权重、偏差和隐藏层数），ELM 方法的性能得到增强。它需要足够精通处理高维和复杂问题的计算技术。基于教学优化 (TLBO) 技术的改进采用两种新方法，以提高 TLBO 算法的探索和开发能力。实施改进的 TLBO (MTLBO) 和可优化 ELM 技术的协作，以预测四个不同案例研究的 SPG，例如提前一小时、提前一天、提前一个月和提前三个月预测。诸如平均绝对误差 (MAE)、均方误差 (MSE)、平均绝对百分比误差 (MAPE)、平均反正切绝对百分比误差 (MAAPE) 和确定相关性 (R) 等性能指标² ) 用于证明所提出方法的性能。Diebold-Mariano (DM) 测试和预测有效性被用来假设证实基于 MTLBO 的 ELM 模型优于基于不同优化的 ELM、ELM（具有随机固定的权重和偏差）和 ANN 模型的能力。模拟结果证明了所提出的 SPG 预测方法的卓越性能。