This work aims to model the combined cycle power plant (CCPP) using different algorithms. The algorithms used are Ridge, Linear regressor (LR), and upport vector regressor (SVR). The CCPP energy output data collected as a factor of thermal input variables, mainly exhaust vacuum, ambient temperature, relative humidity, and ambient pressure. Initially, the Ridge algorithm-based modeling is performed in detail, and then SVR-based LR, named as SVR (LR), SVR-based radial basis function—SVR (RBF), and SVR-based polynomial regression—SVR (Poly.) algorithms, are applied. Mean absolute error (MAE), R-squared (R²), median absolute error (MeAE), mean absolute percentage error (MAPE), and mean Poisson deviance (MPD) are assessed after their training and testing of each algorithm. From the modeling of energy output data, it is seen that SVR (RBF) is the most suitable in providing very close predictions compared to other algorithms. SVR (RBF) training R² obtained is 0.98 while all others were 0.9–0.92. The testing predictions made by SVR (RBF), Ridge, and RidgeCV are nearly the same, i.e., R² is 0.92. It is concluded that these algorithms are suitable for predicting sensitive output energy data of a CCPP depending on thermal input variables.

The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (Nu_avg) data using four activations functions. The battery Nu_avg is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. Nu_avg is modeled at first using only one hidden layer in the network (NN₁). The neurons in NN₁ are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN₁. Similarly, deep NN (NN_D) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the Nu_avg. RSME (root mean square error) and R-Squared (R²) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN₁ and NN_D both accurately predict the battery data. Six neurons in the hidden layer for NN₁ give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN₁ model. In NN_D, the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN₁ model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NN_D model. Overall, the deep NN (NN_D) model predicted better than the single-layered NN (NN₁) model for each activation function.

Combined heat and power (CHP) plants are known as efficient technologies to reduce environmental emissions, balance energy costs, and increase total energy efficiency. To obtain a more efficient system, various optimization methods have been employed, based on numerical, experimental, parametric, and algorithmic optimization routes. Due to the significance of algorithmic optimization, as a systematic method for optimizing energy systems, this novel review paper is focused on the meta-heuristic optimization algorithms, implemented in CHP energy systems. By considering the applied objective functions, the main sections are divided into single-objective and multi-objective algorithms. In each case, the units’ combination is briefly detailed, the objective functions are introduced, and analyses are conducted. The main aim of this paper is to gather a database for the optimization of CHPs, demonstrate the effect of the applied optimization methods on the objective functions, and finally, introduce the most efficient methods. The most significant feature of this paper is that it covers all types of CHP optimization issues including scheduling, sizing, and designing problems, finding the extent of each optimization issue in the relevant papers in the last decade. Based on the findings, in the single-objective problems the combined heat and power economic dispatch (CHPED) issue as a subcategory of the scheduling problems is introduced as the most paid topic; the designing issue is known as the lowest paid topic. In the multi-objective problems, working on various types of CHP optimization problems has been conducted with an almost similar share. The combined heat and power economic emission dispatch (CHPEED) problem with the most share, and the sizing issue with the lowest share. The CHP designing and sizing optimization issues could be introduced as topics to work on more in the future. Additionally, the numerical results of CHPED and CHPEED problems solved by various algorithms are presented and compared. In this regard, specified test systems are considered.