top of page

Publications

Robust and Sequential Deep Reinforcement Learning Approach for the Economic Dispatch Problem Considering Demand Uncertainty

M. Alharbi, A. Alhadlaq, A. Alabdulkareem, M. Alsaleh, and D. Shah

Venue:   TBD

In Preparation

AssessingElectricity Tariffs’ Costs Allocation in Saudi Arabia: Upcoming Challenges for a Needed Redesign

A. Alhadlaq, B. Alaskar, A. Alabdulkareem, A. Alfadda, P. Duenas, and C. Batlle

Redesigning electricity tariffs is a key need to enable an efficient integration of end users. The process requires moving from the plain volumetric prices still currently in force in most jurisdictions, to a more sophisticated format governed, among others, by the cost causality principle. The first step needed to allow for a proper estimation of the changes needed and their potential impact on end users is to assess the current criteria followed to allocate the different sources of costs among them. In this paper, we develop a detailed review of the current electric power system costs’ allocation criteria currently in force in Saudi Arabia. We explore how the costs of the electricity activities have evolved to date and estimate how they are being distributed among the different consumers’ classes. The analysis allows us to highlight the main challenges and potential impacts that will have to be faced to design a novel, economically efficient and socially acceptable tariff methodology in the Kingdom.

Venue:   IEEE Milan PowerTech 2021

Published

Next‑day Electricity Demand Forecast: A New Ensemble Recommendation System Using Peak and Valley

B. Alaskar, A. Alhadlaq, M. Alharbi, S. Alghumayjan, A. Alabdulkareem, M. Alsaleh, and D. Shah

Electricity demand forecast plays a major role in the planning and resource allocation phase of utility companies. In particular, predicted peak and valley (PaV) demand points seems critical, as they determine the maximum required generation capacity and base load to meet the minimum underlying demand, respectively. In this paper, we propose multiple techniques to enhance day-ahead forecasting models by leveraging independent daily PaV predictors to ensemble short-term electricity demand forecasters. These ensemble techniques are then incorporated into a novel ensemble recommendation system (ERS). The ERS suggests the most appropriate ensemble technique to enhance the day-ahead predictor’s performance while minimizing the computation required for testing multiple ensemble algorithms, relative to a single ensemble algorithm. This approach aims to improve the PaV forecasting and to enhance the overall accuracy of the day-ahead forecaster and it can be used with any combination of forecasting models. We demonstrate the effectiveness of our approach through a case study using a time-series prediction database model (tspDB) and a deep neural network (DNN) model for predicting the demand of the next day. The results show an improvement of 33% and 12% in the mean absolute percentage error of the forecasted PaV points using the tspDB and DNN models, respectively, as well as, enhancement in the overall day-ahead forecast.

Venue:   IEEE PES ISGT NA 2021

Published

On the Optimality of Electricity Tariffs for Saudi Arabia’s Residential Sector Considering the Effect of DER

B. Alaskar, A. Alhadlaq, A. Alabdulkareem, and A. Alfadda

Distributed Energy Resources (DER) are being increasingly utilized in the residential sector of the Kingdom of Saudi Arabia (KSA) and is expected to grow even further in the future. This growth increases the flexibility potential of the Saudi power system and suggests a need to maximize the engagement of the end-users to enhance the efficiency of power supply. To this aim, reforming the electricity tariffs can be a powerful tool to improve the efficiency of the network usage for the residential sector while taking into account the integration of DER. Although significant efforts have recently been made in Saudi Arabia to augment end-user rates towards fully cost-efficient levels. The current flat-rate charges does not reflect the excessive cost of electricity production during the peak times. The focus of this paper is to explore how tariff levels could be calculated so as to increase the overall welfare, by minimizing the generation cost of electricity and maximizing the utility function of the demand, which will be applied for different penetration levels of DER.

Venue:   IEEE PES ISGT Europe 2020

Published

bottom of page