- Electrical and Electronic Engineering - Research Publications
Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
7 results
Filters
Reset filtersSettings
Statistics
Citations
Search Results
Now showing
1 - 7 of 7
-
ItemNo Preview AvailableGenerative Adversarial Networks for anomaly detection on decentralised dataKatzefa, M ; Cullen, AC ; Alpcan, T ; Leckie, C (PERGAMON-ELSEVIER SCIENCE LTD, 2022)
-
ItemAchieving AI-Enabled Robust End-to-End Quality of Experience Over Backhaul Radio Access NetworksRoy, D ; Rao, AS ; Alpcan, T ; Das, G ; Palaniswami, M (IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2022-09)Emerging applications such as Augmented Reality, the Internet of Vehicles and Remote Surgery require both computing and networking functions working in harmony. The End-to-end (E2E) quality of experience (QoE) for these applications depends on the synchronous allocation of networking and computing resources. However, the relationship between the resources and the E2E QoE outcomes is typically stochastic and non-linear. In order to make efficient resource allocation decisions, it is essential to model these relationships. This article presents a novel machine-learning based approach to learn these relationships and concurrently orchestrate both resources for this purpose. The machine learning models further help make robust allocation decisions regarding stochastic variations and simplify robust optimization to a conventional constrained optimization. When resources are insufficient to accommodate all application requirements, our framework supports executing some of the applications with minimal degradation (graceful degradation) of E2E QoE. We also show how we can implement the learning and optimization methods in a distributed fashion by the Software-Defined Network (SDN) and Kubernetes technologies. Our results show that deep learning-based modelling achieves E2E QoE with approximately 99.8% accuracy, and our robust joint-optimization technique allocates resources efficiently when compared to existing differential services alternatives.
-
ItemAchieving QoS for bursty uRLLC applications over passive optical networksRoy, D ; Rao, AS ; Alpcan, T ; Das, G ; Palaniswami, M (Optica Publishing Group, 2022-05)Emerging real-time applications such as those classified under ultra-reliable low latency (uRLLC) generate bursty traffic and have strict quality of service (QoS) requirements. The passive optical network (PON) is a popular access network technology, which is envisioned to handle such applications at the access segment of the network. However, the existing standards cannot handle strict QoS constraints for such applications. The available solutions rely on instantaneous heuristic decisions and maintain QoS constraints (mostly bandwidth) in an average sense. Existing proposals in generic networks with optimal strategies are computationally complex and are, therefore, not suitable for uRLLC applications. This paper presents a novel computationally efficient, far-sighted bandwidth allocation policy design for facilitating bursty uRLLC traffic in a PON framework while satisfying strict QoS (age of information/delay and bandwidth) requirements. To this purpose, first we design a delay-tracking mechanism, which allows us to model the resource allocation problem from a control-theoretic viewpoint as a model predictive control (MPC) problem. MPC helps in making far-sighted decisions regarding resource allocations and captures the time-varying dynamics of the network. We provide computationally efficient polynomial time solutions and show their implementation in the PON framework. Compared to existing approaches, MPC can improve delay violations by 15% and 45% at loads of 0.8 and 0.9, respectively, for delay-constrained applications of 1 ms and 4 ms. Our approach is also robust to varying traffic arrivals.
-
ItemA Probabilistic Reverse Power Flows Scenario Analysis FrameworkDemazy, A ; Alpcan, T ; Mareels, I (IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2020)
-
ItemWind Versus Storage Allocation for Price Management in Wholesale Electricity MarketsMasoumzadeh, A ; Nekouei, E ; Alpcan, T (Institute of Electrical and Electronics Engineers, 2020-04-01)This paper investigates the impacts of installing regulated wind and electricity storage on average price and price volatility in electricity markets. A stochastic bi-level optimization model is developed, which computes the optimal allocation of new wind and battery capacities, by minimizing a weighted sum of the average market price and price volatility. A fixed budget is allocated on wind and battery capacities in the upper-level problem. The operation of strategic/regulated generation, storage, and transmission players is simulated in the lower-level problem using a stochastic (Bayesian) Cournot-based game model. Australia's national electricity market, which is experiencing occasional price peaks, is considered as the case study. Our simulation results quantitatively illustrate that the regulated wind is more efficient than storage in reducing the average price, while the regulated storage more effectively reduces the price volatility. According to our numerical results, the storage-only solution reduces the average price at most by 9.4%, and the wind-only solution reduces the square root of price volatility at most by 39.3%. However, an optimal mixture of wind and storage can reduce the mean price by 17.6% and the square root of price volatility by 48.1%. It also increases the consumer surplus by 1.52%. Moreover, the optimal mixture of wind and storage is a profitable solution unlike the storage-only solution.
-
ItemSample Complexity of Solving Non-Cooperative GamesNekouei, E ; Nair, GN ; Alpcan, T ; Evans, RJ (Institute of Electrical and Electronics Engineers, 2020-02-01)This paper studies the complexity of solving two classes of non-cooperative games in a distributed manner, in which the players communicate with a set of system nodes over noisy communication channels. The complexity of solving each game class is defined as the minimum number of iterations required to find a Nash equilibrium (NE) of any game in that class with ∈ accuracy. First, we consider the class G of all N-player non-cooperative games with a continuous action space that admit at least one NE. Using information-theoretic inequalities, a lower bound on the complexity of solving G is derived which depends on the Kolmogorov 2∈-capacity of the constraint set and the total capacity of the communication channels. Our results indicate that the game class G can be solved at most exponentially fast. We next consider the class of all N-player non-cooperative games with at least one NE such that the players' utility functions satisfy a certain (differential) constraint. We derive lower bounds on the complexity of solving this game class under both Gaussian and non-Gaussian noise models. Finally, we derive upper and lower bounds on the sample complexity of a class of quadratic games. It is shown that the complexity of solving this game class scales according to Θ (1/∈ 2 ) where € is the accuracy parameter.
-
ItemDesigning tax and subsidy incentives towards a green and reliable electricity marketMasoumzadeh, A ; Alpcan, T ; Nekouei, E (Elsevier, 2020-03-15)Incentive schemes and policies play an important role in reducing carbon emissions from electricity generation. This paper investigates designing tax and subsidy incentives towards a reliable and low emission electricity market, using Australia's National Electricity Market as a case study. In this work, a novel framework is proposed to design interactive tax/subsidy incentives on both emission reduction and resource adequacy in competitive electricity markets as a game model. In our model, market participants decide on their capacity expansion/retirement strategies considering the impact of designed incentive schemes on their long-term operation such that the desired levels of emission reduction and fast response generation are achieved in the network. The simulation results for Australia's electricity market during 2017–2052, indicate the necessity of incentive policies, in spite of the cost reduction trajectory for renewable technologies, to reach the emission intensity reduction above 45% in the market by 2052. In 80% emission intensity reduction scenario, the designed incentive schemes highly encourage the investment on synchronous renewables, +17 GW, storage technologies, +15.7 GW, and transmission lines, +1.6 GW, to support high additional penetration of Variable Renewable Energy, wind and solar, +39 GW, which paves the way to transition to a green and reliable electricity market.