--------------------------------------------
Dear Colleagues,
I would like to invite you to submit your valuable research to the Deep Learning and Optimization for Smart Grid Management as a Special Issue of the Journal of Computer and Knowledge Engineering (CKE).
Please accept our apologies if you receive multiple versions of this call through different channels. The details are as follows.
Abstract
The modern power grid faces significant challenges due to the increasing integration of renewable energy sources, growing energy demands, and the need for efficient demand-side management. Deep learning, with its ability to learn complex patterns from large datasets, presents a powerful tool to address these challenges and optimize smart grid operations.
This special issue focuses on the convergence of deep learning techniques and optimization methods for intelligent and efficient smart grid management. We welcome submissions that explore the application of deep learning and Reinforcement Learning in various aspects of smart grids, including:
Load Forecasting: Deep learning models can analyze historical and real-time consumption data from smart meters to accurately predict future electricity demand patterns at various levels (residential, commercial, industrial). This information is crucial for grid operators to plan the generation and distribution of resources efficiently, ensuring a stable and reliable power supply.
Demand Response (DR) Optimization: Deep learning algorithms can be employed to optimize DR programs that encourage consumers to adjust their electricity usage based on grid conditions. This can involve price-based DR, where consumers pay varying rates depending on real-time electricity demand, or incentive-based DR, where consumers receive rewards for reducing consumption during peak periods.
Home Energy Scheduling: Leverage deep learning to schedule energy consumption in residential buildings for optimal utilization of renewable energy sources (e.g., solar panels) and cost savings.
Grid Optimization and Control: Deep learning can be integrated with optimization techniques to optimize grid operations in real-time. This includes tasks such as optimal power flow management, voltage regulation, and congestion management.
Anomaly Detection and Predictive Maintenance: Deep learning models can be trained to identify anomalies in sensor data from IoT devices deployed throughout the grid. This enables early detection of potential equipment failures, allowing for proactive maintenance and preventing costly disruptions
Cybersecurity: Deep learning can be used to enhance cybersecurity in smart grids by detecting and preventing cyberattacks. This is particularly important as the grid becomes increasingly interconnected and reliant on IoT devices.
The topics of interest for this special issue include, but are not limited to:
Deadline: 30th Dec 2024.
Manuscript Submission Information
Manuscripts should be submitted online at https://cke.um.ac.ir/ by registering and logging in to this website. When uploading your article, be sure to select Special Issue in the Select manuscript type section. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles and review articles are invited. Deadline for submission is 31th August 2024. Late submission might be considered in special cases.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process.
Issue Editor: Dr. Seyed Amin Hosseini Seno
Journal Information
The journal of Computer and Knowledge Engineering is founded by the Department of Computer Engineering, Ferdowsi University of Mashhad. It is published twice a year. The journal materials are available both on-line and in printed form. Submission of manuscripts not published before and not being under review by any other journals are encouraged. The authors are welcomed to upload their articles in either pdf or doc file format using the journal’s website. Accepted papers will be formatted by the governing body of the journal to comply with its standards. All submitted papers are single-blind peer reviewed by at least two different reviewers. The journal is very vigilant against any kind of plagiarism and all papers will be checked to make sure all aspects of intellectual property rights are respected. Until the Journals own guidelines on this subject is developed it will use “ACM Policy and Procedures on Plagiarism” policies.