Department of Electrical Power Engineering, Faculty of Engineering Technology, Yarmouk University, Irbid 21163, Jordan.
King Abdullah II School for Information Technology, The University of Jordan, Amman 11942, Jordan.
Sensors (Basel). 2021 Sep 17;21(18):6240. doi: 10.3390/s21186240.
Power system planning and expansion start with forecasting the anticipated future load requirement. Load forecasting is essential for the engineering perspective and a financial perspective. It effectively plays a vital role in the conventional monopolistic operation and electrical utility planning to enhance power system operation, security, stability, minimization of operation cost, and zero emissions. Two Well-developed cases are discussed here to quantify the benefits of additional models, observation, resolution, data type, and how data are necessary for the perception and evolution of the electrical load forecasting in Jordan. Actual load data for more than a year is obtained from the leading electricity company in Jordan. These cases are based on total daily demand and hourly daily demand. This work's main aim is for easy and accurate computation of week ahead electrical system load forecasting based on Jordan's current load measurements. The uncertainties in forecasting have the potential to waste money and resources. This research proposes an optimized multi-layered feed-forward neural network using the recent Grey Wolf Optimizer (GWO). The problem of power forecasting is formulated as a minimization problem. The experimental results are compared with popular optimization methods and show that the proposed method provides very competitive forecasting results.
电力系统规划和扩展始于预测预期的未来负荷需求。负荷预测对于工程视角和财务视角都是必不可少的。它在传统的垄断运营和电力公用事业规划中有效地发挥着至关重要的作用，以增强电力系统的运行、安全性、稳定性、运行成本最小化和零排放。这里讨论了两个发达的案例，以量化额外模型、观测、分辨率、数据类型的好处，以及数据对于约旦电力负荷预测的感知和演变的必要性。从约旦领先的电力公司获得了一年多的实际负荷数据。这些案例基于总日需求和小时日需求。这项工作的主要目的是基于约旦目前的负荷测量，实现简单、准确的周前电力系统负荷预测计算。预测中的不确定性有可能浪费金钱和资源。本研究提出了一种基于最近的灰狼优化器（GWO）的优化多层前馈神经网络。电力预测问题被表述为一个最小化问题。实验结果与流行的优化方法进行了比较，结果表明所提出的方法提供了非常有竞争力的预测结果。
