arXiv subjects

Melike Erol-Kantarci

Publications and source records attributed to Melike Erol-Kantarci.

At least 109 records · Page 6Linked to original sources

arXiv2021

Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures

Microgrids (MGs) are important players for the future transactive energy systems where a number of intelligent Internet of Things (IoT) devices interact for energy management in the smart grid. Although there have been many works on MG energy management, most studies assume a perfect communication environment, where communication failures are not considered. In this paper, we consider the MG as a multi-agent environment with IoT devices in which AI agents exchange information with their peers for collaboration. However, the collaboration information may be lost due to communication failures or packet loss. Such events may affect the operation of the whole MG. To this end, we propose a multi-agent Bayesian deep reinforcement learning (BA-DRL) method for MG energy management under communication failures. We first define a multi-agent partially observable Markov decision process (MA-POMDP) to describe agents under communication failures, in which each agent can update its beliefs on the actions of its peers. Then, we apply a double deep Q-learning (DDQN) architecture for Q-value estimation in BA-DRL, and propose a belief-based correlated equilibrium for the joint-action selection of multi-agent BA-DRL. Finally, the simulation results show that BA-DRL is robust to both power supply uncertainty and communication failure uncertainty. BA-DRL has 4.1% and 10.3% higher reward than Nash Deep Q-learning (Nash-DQN) and alternating direction method of multipliers (ADMM) respectively under 1% communication failure probability.

eess.SY↗

arXiv2021

Knowledge Transfer based Radio and Computation Resource Allocation for 5G RAN Slicing

To implement network slicing in 5G, resource allocation is a key function to allocate limited network resources such as radio and computation resources to multiple slices. However, the joint resource allocation also leads to a higher complexity in the network management. In this work, we propose a knowledge transfer based resource allocation (KTRA) method to jointly allocate radio and computation resources for 5G RAN slicing. Compared with existing works, the main difference is that the proposed KTRA method has a knowledge transfer capability. It is designed to use the prior knowledge of similar tasks to improve performance of the target task, e.g., faster convergence speed or higher average reward. The proposed KTRA is compared with Qlearning based resource allocation (QLRA), and KTRA method presents a 18.4% lower URLLC delay and a 30.1% higher eMBB throughput as well as a faster convergence speed.

cs.NI↗

arXiv2021

Competitive Multi-Agent Load Balancing with Adaptive Policies in Wireless Networks

Using Machine Learning (ML) techniques for the next generation wireless networks have shown promising results in the recent years, due to high learning and adaptation capability of ML algorithms. More specifically, ML techniques have been used for load balancing in Self-Organizing Networks (SON). In the context of load balancing and ML, several studies propose network management automation (NMA) from the perspective of a single and centralized agent. However, a single agent domain does not consider the interaction among the agents. In this paper, we propose a more realistic load balancing approach using novel Multi-Agent Deep Deterministic Policy Gradient with Adaptive Policies (MADDPG-AP) scheme that considers throughput, resource block utilization and latency in the network. We compare our proposal with a single-agent RL algorithm named Clipped Double Q-Learning (CDQL) . Simulation results reveal a significant improvement in latency, packet loss ratio and convergence time

cs.NI↗

arXiv2021

Dynamic CU-DU Selection for Resource Allocation in O-RAN Using Actor-Critic Learning

Recently, there has been tremendous efforts by network operators and equipment vendors to adopt intelligence and openness in the next generation radio access network (RAN). The goal is to reach a RAN that can self-optimize in a highly complex setting with multiple platforms, technologies and vendors in a converged compute and connect architecture. In this paper, we propose two nested actor-critic learning based techniques to optimize the placement of resource allocation function, and as well, the decisions for resource allocation. By this, we investigate the impact of observability on the performance of the reinforcement learning based resource allocation. We show that when a network function (NF) is dynamically relocated based on service requirements, using reinforcement learning techniques, latency and throughput gains are obtained.

cs.NI↗

arXiv2021

Smart Home Energy Management: Sequence-to-Sequence Load Forecasting and Q-Learning

A smart home energy management system (HEMS) can contribute towards reducing the energy costs of customers; however, HEMS suffers from uncertainty in both energy generation and consumption patterns. In this paper, we propose a sequence to sequence (Seq2Seq) learning-based supply and load prediction along with reinforcement learning-based HEMS control. We investigate how the prediction method affects the HEMS operation. First, we use Seq2Seq learning to predict photovoltaic (PV) power and home devices' load. We then apply Q-learning for offline optimization of HEMS based on the prediction results. Finally, we test the online performance of the trained Q-learning scheme with actual PV and load data. The Seq2Seq learning is compared with VARMA, SVR, and LSTM in both prediction and operation levels. The simulation results show that Seq2Seq performs better with a lower prediction error and online operation performance.

eess.SY↗

arXiv2021

Risk-Aware Fine-Grained Access Control in Cyber-Physical Contexts

Access to resources by users may need to be granted only upon certain conditions and contexts, perhaps particularly in cyber-physical settings. Unfortunately, creating and modifying context-sensitive access control solutions in dynamic environments creates ongoing challenges to manage the authorization contexts. This paper proposes RASA, a context-sensitive access authorization approach and mechanism leveraging unsupervised machine learning to automatically infer risk-based authorization decision boundaries. We explore RASA in a healthcare usage environment, wherein cyber and physical conditions create context-specific risks for protecting private health information. The risk levels are associated with access control decisions recommended by a security policy. A coupling method is introduced to track coexistence of the objects within context using frequency and duration of coexistence, and these are clustered to reveal sets of actions with common risk levels; these are used to create authorization decision boundaries. In addition, we propose a method for assessing the risk level and labelling the clusters with respect to their corresponding risk levels. We evaluate the promise of RASA-generated policies against a heuristic rule-based policy. By employing three different coupling features (frequency-based, duration-based, and combined features), the decisions of the unsupervised method and that of the policy are more than 99% consistent.

cs.CR↗

arXiv2021

QoS-Aware Load Balancing in Wireless Networks using Clipped Double Q-Learning

In recent years, long-term evolution (LTE) and 5G NR (5th Generation New Radio) technologies have showed great potential to utilize Machine Learning (ML) algorithms in optimizing their operations, both thanks to the availability of fine-grained data from the field, as well as the need arising from growing complexity of networks. The aforementioned complexity sparked mobile operators' attention as a way to reduce the capital expenditures (CAPEX) and the operational (OPEX) expenditures of their networks through network management automation (NMA). NMA falls under the umbrella of Self-Organizing Networks (SON) in which 3GPP has identified some challenges and opportunities in load balancing mechanisms for the Radio Access Networks (RANs). In the context of machine learning and load balancing, several studies have focused on maximizing the overall network throughput or the resource block utilization (RBU). In this paper, we propose a novel Clipped Double Q-Learning (CDQL)-based load balancing approach considering resource block utilization, latency and the Channel Quality Indicator (CQI). We compare our proposal with a traditional handover algorithm and a resource block utilization based handover mechanism. Simulation results reveal that our scheme is able to improve throughput, latency, jitter and packet loss ratio in comparison to the baseline algorithms.

cs.NI↗

arXiv2021

Short-Term Load Forecasting for Smart HomeAppliances with Sequence to Sequence Learning

Appliance-level load forecasting plays a critical role in residential energy management, besides having significant importance for ancillary services performed by the utilities. In this paper, we propose to use an LSTM-based sequence-to-sequence (seq2seq) learning model that can capture the load profiles of appliances. We use a real dataset collected fromfour residential buildings and compare our proposed schemewith three other techniques, namely VARMA, Dilated One Dimensional Convolutional Neural Network, and an LSTM model.The results show that the proposed LSTM-based seq2seq model outperforms other techniques in terms of prediction error in most cases.

eess.SP↗

arXiv2021

RAN Resource Slicing in 5G Using Multi-Agent Correlated Q-Learning

5G is regarded as a revolutionary mobile network, which is expected to satisfy a vast number of novel services, ranging from remote health care to smart cities. However, heterogeneous Quality of Service (QoS) requirements of different services and limited spectrum make the radio resource allocation a challenging problem in 5G. In this paper, we propose a multi-agent reinforcement learning (MARL) method for radio resource slicing in 5G. We model each slice as an intelligent agent that competes for limited radio resources, and the correlated Q-learning is applied for inter-slice resource block (RB) allocation. The proposed correlated Q-learning based interslice RB allocation (COQRA) scheme is compared with Nash Q-learning (NQL), Latency-Reliability-Throughput Q-learning (LRTQ) methods, and the priority proportional fairness (PPF) algorithm. Our simulation results show that the proposed COQRA achieves 32.4% lower latency and 6.3% higher throughput when compared with LRTQ, and 5.8% lower latency and 5.9% higher throughput than NQL. Significantly higher throughput and lower packet drop rate (PDR) is observed in comparison to PPF.

cs.NI↗

arXiv2021

Age of Information Aware VNF Scheduling in Industrial IoT Using Deep Reinforcement Learning

In delay-sensitive industrial internet of things (IIoT) applications, the age of information (AoI) is employed to characterize the freshness of information. Meanwhile, the emerging network function virtualization provides flexibility and agility for service providers to deliver a given network service using a sequence of virtual network functions (VNFs). However, suitable VNF placement and scheduling in these schemes is NP-hard and finding a globally optimal solution by traditional approaches is complex. Recently, deep reinforcement learning (DRL) has appeared as a viable way to solve such problems. In this paper, we first utilize single agent low-complex compound action actor-critic RL to cover both discrete and continuous actions and jointly minimize VNF cost and AoI in terms of network resources under end-to end Quality of Service constraints. To surmount the single-agent capacity limitation for learning, we then extend our solution to a multi-agent DRL scheme in which agents collaborate with each other. Simulation results demonstrate that single-agent schemes significantly outperform the greedy algorithm in terms of average network cost and AoI. Moreover, multi-agent solution decreases the average cost by dividing the tasks between the agents. However, it needs more iterations to be learned due to the requirement on the agents collaboration.

eess.SP↗

arXiv2021

Radio Resource and Beam Management in 5G mmWave Using Clustering and Deep Reinforcement Learning

To optimally cover users in millimeter-Wave (mmWave) networks, clustering is needed to identify the number and direction of beams. The mobility of users motivates the need for an online clustering scheme to maintain up-to-date beams towards those clusters. Furthermore, mobility of users leads to varying patterns of clusters (i.e., users move from the coverage of one beam to another), causing dynamic traffic load per beam. As such, efficient radio resource allocation and beam management is needed to address the dynamicity that arises from mobility of users and their traffic. In this paper, we consider the coexistence of Ultra-Reliable Low-Latency Communication (URLLC) and enhanced Mobile BroadBand (eMBB) users in 5G mmWave networks and propose a Quality-of-Service (QoS) aware clustering and resource allocation scheme. Specifically, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is used for online clustering of users and the selection of the number of beams. In addition, Long Short Term Memory (LSTM)-based Deep Reinforcement Learning (DRL) scheme is used for resource block allocation. The performance of the proposed scheme is compared to a baseline that uses K-means and priority-based proportional fairness for clustering and resource allocation, respectively. Our simulation results show that the proposed scheme outperforms the baseline algorithm in terms of latency, reliability, and rate of URLLC users as well as rate of eMBB users.

cs.NI↗

arXiv2021

Machine Learning-based Inter-Beam Inter-Cell Interference Mitigation in mmWave

In this paper, we address inter-beam inter-cell interference mitigation in 5G networks that employ millimeter-wave (mmWave), beamforming and non-orthogonal multiple access (NOMA) techniques. Those techniques play a key role in improving network capacity and spectral efficiency by multiplexing users on both spatial and power domains. In addition, the coverage area of multiple beams from different cells can intersect, allowing more flexibility in user-cell association. However, the intersection of coverage areas also implies increased inter-beam inter-cell interference, i.e. interference among beams formed by nearby cells. Therefore, joint user-cell association and inter-beam power allocation stand as a promising solution to mitigate inter-beam, inter-cell interference. In this paper, we consider a 5G mmWave network and propose a reinforcement learning algorithm to perform joint user-cell association and inter-beam power allocation to maximize the sum rate of the network. The proposed algorithm is compared to a uniform power allocation that equally divides power among beams per cell. Simulation results present a performance enhancement of 13-30% in network's sum-rate corresponding to the lowest and highest traffic loads, respectively.

cs.NI↗

arXiv2021

AI-enabled Future Wireless Networks: Challenges, Opportunities and Open Issues

A plethora of demanding services and use cases mandate a revolutionary shift in the management of future wireless network resources. Indeed, when tight quality of service demands of applications are combined with increased complexity of the network, legacy network management routines will become unfeasible in 6G. Artificial Intelligence (AI) is emerging as a fundamental enabler to orchestrate the network resources from bottom to top. AI-enabled radio access and AI-enabled core will open up new opportunities for automated configuration of 6G. On the other hand, there are many challenges in AI-enabled networks that need to be addressed. Long convergence time, memory complexity, and complex behaviour of machine learning algorithms under uncertainty as well as highly dynamic channel, traffic and mobility conditions of the network contribute to the challenges. In this paper, we survey the state-of-art research in utilizing machine learning techniques in improving the performance of wireless networks. In addition, we identify challenges and open issues to provide a roadmap for the researchers.

cs.NI↗

arXiv2021

Correlated Deep Q-learning based Microgrid Energy Management

Microgrid (MG) energy management is an important part of MG operation. Various entities are generally involved in the energy management of an MG, e.g., energy storage system (ESS), renewable energy resources (RER) and the load of users, and it is crucial to coordinate these entities. Considering the significant potential of machine learning techniques, this paper proposes a correlated deep Q-learning (CDQN) based technique for the MG energy management. Each electrical entity is modeled as an agent which has a neural network to predict its own Q-values, after which the correlated Q-equilibrium is used to coordinate the operation among agents. In this paper, the Long Short Term Memory networks (LSTM) based deep Q-learning algorithm is introduced and the correlated equilibrium is proposed to coordinate agents. The simulation result shows 40.9% and 9.62% higher profit for ESS agent and photovoltaic (PV) agent, respectively.

eess.SY↗

arXiv2021

Decentralized Microgrid Energy Management: A Multi-agent Correlated Q-learning Approach

Microgrids (MG) are anticipated to be important players in the future smart grid. For proper operation of MGs an Energy Management System (EMS) is essential. The EMS of an MG could be rather complicated when renewable energy resources (RER), energy storage system (ESS) and demand side management (DSM) need to be orchestrated. Furthermore, these systems may belong to different entities and competition may exist between them. Nash equilibrium is most commonly used for coordination of such entities however the convergence and existence of Nash equilibrium can not always be guaranteed. To this end, we use the correlated equilibrium to coordinate agents, whose convergence can be guaranteed. In this paper, we build an energy trading model based on mid-market rate, and propose a correlated Q-learning (CEQ) algorithm to maximize the revenue of each agent. Our results show that CEQ is able to balance the revenue of agents without harming total benefit. In addition, compared with Q-learning without correlation, CEQ could save 19.3% cost for the DSM agent and 44.2% more benefits for the ESS agent.

eess.SY↗

arXiv2021

Multi Agent Team Learning in Disaggregated Virtualized Open Radio Access Networks (O-RAN)

Starting from the Cloud Radio Access Network (C-RAN), continuing with the virtual Radio Access Network (vRAN) and most recently with Open RAN (O-RAN) initiative, Radio Access Network (RAN) architectures have significantly evolved in the past decade. In the last few years, the wireless industry has witnessed a strong trend towards disaggregated, virtualized and open RANs, with numerous tests and deployments world wide. One unique aspect that motivates this paper is the availability of new opportunities that arise from using machine learning to optimize the RAN in closed-loop, i.e. without human intervention, where the complexity of disaggregation and virtualization makes well-known Self-Organized Networking (SON) solutions inadequate. In our view, Multi-Agent Systems (MASs) with team learning, can play an essential role in the control and coordination of controllers of O-RAN, i.e. near-real-time and non-real-time RAN Intelligent Controller (RIC). In this article, we first present the state-of-the-art research in multi-agent systems and team learning, then we provide an overview of the landscape in RAN disaggregation and virtualization, as well as O-RAN which emphasizes the open interfaces introduced by the O-RAN Alliance. We present a case study for agent placement and the AI feedback required in O-RAN, and finally, we identify challenges and open issues to provide a roadmap for researchers.

cs.MA↗

arXiv2021

Reinforcement Learning Based Dynamic Function Splitting in Disaggregated Green Open RANs

With the growing momentum around Open RAN (O-RAN) initiatives, performing dynamic Function Splitting (FS) in disaggregated and virtualized Radio Access Networks (vRANs), in an efficient way, is becoming highly important. An equally important efficiency demand is emerging from the energy consumption dimension of the RAN hardware and software. Supplying the RAN with Renewable Energy Sources (RESs) promises to boost the energy-efficiency. Yet, FS in such a dynamic setting, calls for intelligent mechanisms that can adapt to the varying conditions of the RES supply and the traffic load on the mobile network. In this paper, we propose a reinforcement learning (RL)-based dynamic function splitting (RLDFS) technique that decides on the function splits in an O-RAN to make the best use of RES supply and minimize operator costs. We also formulate an operational expenditure minimization problem. We evaluate the performance of the proposed approach on a real data set of solar irradiation and traffic rate variations. Our results show that the proposed RLDFS method makes effective use of RES and reduces the cost of an MNO. We also investigate the impact of the size of solar panels and batteries which may guide MNOs to decide on proper RES and battery sizing for their networks.

cs.NI↗

arXiv2021

Actor-Critic Learning Based QoS-Aware Scheduler for Reconfigurable Wireless Networks

The flexibility offered by reconfigurable wireless networks, provide new opportunities for various applications such as online AR/VR gaming, high-quality video streaming and autonomous vehicles, that desire high-bandwidth, reliable and low-latency communications. These applications come with very stringent Quality of Service (QoS) requirements and increase the burden over mobile networks. Currently, there is a huge spectrum scarcity due to the massive data explosion and this problem can be solved by helps of Reconfigurable Wireless Networks (RWNs) where nodes have reconfiguration and perception capabilities. Therefore, a necessity of AI-assisted algorithms for resource block allocation is observed. To tackle this challenge, in this paper, we propose an actor-critic learning-based scheduler for allocating resource blocks in a RWN. Various traffic types with different QoS levels are assigned to our agents to provide more realistic results. We also include mobility in our simulations to increase the dynamicity of networks. The proposed model is compared with another actor-critic model and with other traditional schedulers; proportional fair (PF) and Channel and QoS Aware (CQA) techniques. The proposed models are evaluated by considering the delay experienced by user equipment (UEs), successful transmissions and head-of-the-line delays. The results show that the proposed model noticeably outperforms other techniques in different aspects.

cs.NI↗