Browsing by Author "Ahmadian, Saeed"

Now showing 1 - 3 of 3

A Novel Demand Response Management Model to Reduce Smart Grid Costs
(2017) Ahmadian, Saeed; Malki, Heidar A.; Barati, Masoud
DRM means leveling demand curve based on electricity prices. Indeed, using variable price rates, electricity consumers are encouraged to use electricity in periods with cheap electricity price ranges. Therefore, total system cost would decrease efficiently. Motivations: To model dynamics between electricity end-users and utility companies. To present a model with simple implementation on smart households. To reduce electricity production costs and to maximize social welfare.
Detecting Cyber-attacks to Smart Grids and Increasing Resiliency Using Data Driven Algorithms
(2020-08) Ahmadian, Saeed; Malki, Heidar A.; Han, Zhu; Pan, Miao; Rajashekara, Kaushik; Wang, Jianhui
Data driven algorithms can be generally divided into two main categories including optimization methods and machine learning approaches. Optimization methods try to find the optimal decision states by finding the feasible boundaries of the problem. On the other hand, machine learning algorithms aim to find the solutions by iterating via small steps toward the optimal answer following the gradient descents. These two data-driven algorithms are widely deployed in many science and engineering fields and in this dissertation, we use both of these methods to address cyber-security issues of smart grids. We first use the optimization algorithm to present two bi-level problems to address the bidding problem in electricity markets and cyber-attack detection in virtual bidding process in electricity markets. We investigate False Data Injection (FDI) problem in smart grids and the approaches the detect attacks. Both models are solved using mathematical programming with equality constraint (MPEC) and the possible cyber-attack's locations and malicious data are identified. We then study the machine learning abilities to learn the cyber-attacker's behavior using real data. We use the Day-ahead (DA) and Real-time (RT) electricity price and demand to create our initial model of the cyber-attacker. Then, we apply a zero-sum game between the cyber-attacker and system defender using novel machine learning method known as Generative Adversarial Networks (GANs). Then, we present a new deep learning structure to model both cyber-attacker and system defender and aslo flexibility of the system defender to learn different possible attacks. We also use another machine learning approach to mitigate the cyber-attacks effects. Particularly, we use Reinforcement Learning (RL) to investigate the optimal possible actions after the cyber-attack happens in the system. In order to model the possible attack's locations we use multi-stage game between the cyber-attacker and system defender. To model the attacker's moves, we use the Hamiltonian Markov Chain Monte Carlo (H-MCMC) and sample from the posterior distribution of the attack's locations. we then train a deep RL network to learn the optimal actions regarding given game stage and possible future game stages.
Modelling Cyber Attacks on Electricity Market Using Mathematical Programming With Equilibrium Constraints
(IEEE Access, 2/25/2019) Ahmadian, Saeed; Tang, Xiao; Malki, Heidar A.; Han, Zhu
With the development of communication infrastructure in smart grids, cyber security reinforcement has become one of the most challenging issues for power system operators. In this paper, an attacker is considered a participant in the virtual bidding procedure in the day-ahead (DA) and real-time (RT) electricity markets to maximize its profit. The cyber attacker attempts to identify the optimal power system measurements to attack along with the false data injected into measurement devices. Towards the maximum profit, the attacker needs to specify the relation between manipulated meters, virtual power traded in the markets, and electricity prices. Meanwhile, to avoid being detected by the system operator, the attacker considers the physical power system constraints existing in the DA and RT markets. Then, a bi-level optimization model is presented which combines the real electricity market state variables with the attacker decision-variables. Using the mathematical problem with equilibrium constraints, the presented bi-level model is converted into a single level optimization problem and the optimal decision variables for the attacker are obtained. Finally, simulation results are provided to demonstrate the performance of the attacker, which also provides insights for security improvement.