The demand for electrical energy continues to rise with the progression of time. This growth must be matched by a reliable and cost-effective supply of electricity, requiring power systems that are both dependable and economical. Since the amount of electricity consumed by users cannot be precisely predicted, balancing generation with consumption necessitates accurate electrical load forecasting. This study focuses on load forecasting using the Adaptive Neuro-Fuzzy Inference System (ANFIS) method. The forecast developed targets daily peak loads, which fall under short-term load forecasting. The data used for this forecasting consists of historical daily peak loads from January 1, 2017, to June 9, 2022. The forecasting process involves parameters such as radius, squash factor, accept ratio, reject ratio, and epoch. The forecast accuracy is evaluated using the Mean Absolute Percentage Error (MAPE) metric. The results are then compared with PLN’s load forecasting, which employs the load coefficient method. The ANFIS-based forecasting achieved a MAPE of 1.879%, using networks Jaringan_24 and Jaringan_25. This MAPE value is slightly lower than PLN’s load forecasting MAPE of 1.917%, indicating better accuracy by the ANFIS method.

<p><em>To reduce damage to electrical power equipment, protective equipment is needed that is designed as well as possible, so that the protection relay can isolate faults in parts of the distribution network as fast as possible. This backup protection need appropriate relay coordination, so that could protect, if it happens of a primary protection failure. To provide the best service to customers, it is necessary to coordinate the protection relay in the electric power system. To provide protection, the protection relay in the electric power system must be properly coordinated. In this study, we will make a simulation to calculate the TDS and Ipickup values of the overcurrent relay using a artificial neural network backpropagation with software Matlab R2016a. The results of this study can determine the value of TDS (Time Dial Setting) and Ipickup (Current pickup) by overcome the main problem of overcurrent relay protection coordination at the Ammurea II Factory PT. Petrokimia Gresik using a method artificial neural network backpropagation. And, also obtained the results of the minimum value of MSE (Mean Square Error) with the process using the method artificial neural network backpropagation.</em></p><p><em><br /></em></p>

<p class="JOURNALBODY"><em>The development of electric vehicles is in rapid progress, especially in terms of the main engine drive. The use of solenoid can be applied as an alternative driving electric vehicles instead of a dc motor as the main driver. In this paper, the prototype solenoid machine is applied by using 4 inductors controlled by an Arduino microcontroller and the solenoid driver based on application of Mosfet L298N. The prototype runs successfully. Based on the experimental results, the greater the frequency value applies to the driver, the faster the solenoid moves. The acceleration occures due to the electromagnetic field which is getting stronger and the field is proportional to the frequency value, so the solenoid movement is faster.</em></p>