TLB-pilot: Mitigating TLB Contention Attack on GPUs with Microarchitecture-Aware Scheduling

Co-running GPU kernels on a single GPU can provide high system throughput and improve hardware utilization, but this raises concerns on application security. We reveal that translation lookaside buffer (TLB) attack, one of the common attacks on CPU, can happen on GPU when multiple GPU kernels co-run. We investigate conditions or principles under which a TLB attack can take effect, including the awareness of GPU TLB microarchitecture, being lightweight, and bypassing existing software and hardware mechanisms. This TLB-based attack can be leveraged to conduct Denial-of-Service (or Degradation-of-Service) attacks. Furthermore, we propose a solution to mitigate TLB attacks. In particular, based on the microarchitecture properties of GPU, we introduce a software-based system, TLB-pilot, that binds thread blocks of different kernels to different groups of streaming multiprocessors by considering hardware isolation of last-level TLBs and the application’s resource requirement. TLB-pilot employs lightweight online profiling to collect kernel information before kernel launches. By coordinating software- and hardware-based scheduling and employing a kernel splitting scheme to reduce load imbalance, TLB-pilot effectively mitigates TLB attacks. The result shows that when under TLB attack, TLB-pilot mitigates the attack and provides on average 56.2% and 60.6% improvement in average normalized turnaround times and overall system throughput, respectively, compared to the traditional Multi-Process Service based co-running solution. When under TLB attack, TLB-pilot also provides up to 47.3% and 64.3% improvement (41% and 42.9% on average) in average normalized turnaround times and overall system throughput, respectively, compared to a state-of-the-art co-running solution for efficiently scheduling of thread blocks.

Strategy for Optimal Grid Planning and System Evaluation of Networked Distribution Systems

The meshed network may become a standard for future distribution systems owing to its various benefits regarding voltage profile, reliability, losses, and the distributed generation (DG). Therefore, in Korea, there is a plan to introduce an advanced form of meshed network called a networked distribution system (NDS). This refers to a system with permanent linkages between four distribution lines (DLs) and N×N communication-based protection. To properly introduce NDS to an actual grid, this study proposes a strategy for optimal grid planning and system evaluation. Four different topologies and four practical indicators are explained. First, load imbalance is used to find the optimal grid that maximizes the load capacity. Second, line overload, fault current, and temporary overvoltage (TOV) were used to evaluate the necessity of load transfer, availability of circuit breakers, relay settings, and system stability. PSCAD/EMTDC were employed for the simulation. This study establishes the construction and evaluation guidelines of NDS for distribution system operators (DSOs).

LB-DDQN for Handover Decision in Satellite-Terrestrial Integrated Networks

The frequent handover and handover failure problems obviously degrade the QoS of mobile users in the terrestrial segment (e.g., cellular networks) of satellite-terrestrial integrated networks (STINs). And the traditional handover decision methods rely on the historical data and produce the training cost. To solve these problems, the deep reinforcement learning- (DRL-) based handover decision methods are used in the handover management. In the existing DQN-based handover decision method, the overestimates of DQN method continue. Moreover, the current handover decision methods adopt the greedy strategy which lead to the load imbalance problem in base stations. Considering the handover decision and load imbalance problems, we proposed a load balancing-based double deep Q-network (LB-DDQN) method for handover decision. In the proposed load balancing strategy, we define a load coefficient to express the conditions of loading in each base station. The supplementary load balancing evaluation function evaluates the performance of this load balancing strategy. As the selected basic method, the DDQN method adopts the target Q-network and main Q-network to deal with the overestimate problem of the DQN method. Different from joint optimization, we input the load reward into the designed reward function. And the load coefficient becomes one handover decision factor. In our research, the handover decision and load imbalance problems are solved effectively and jointly. The experimental results show that the proposed LB-DDQN handover decision method obtains good performance in the handover decision. Moreover, the access of mobile users becomes more balancing and the throughput of network is also increased.

Cognitive Control-Loop for Elastic Optical Networks with Space-Division Multiplexing

This paper introduces a new solution to improve network performance by decreasing spectrum fragmentation, crosstalk interference, blocking of virtual networks, cost, and link load imbalance. These problems degrade the performance of Elastic Optical Networks with Space-Division Multiplexing. The proposed solution, called Cognitive control loop (CO-OP), is capable of identifying a set of problems and creating plans to mitigate these problems. The CO-OP comprises four functions that employ learning algorithms to identify problems and plan a series of actions to reduce or eliminate them. The results show that the CO-OP can effectively decrease up to 30% the blocking of requests and up to 50% the crosstalk occurrence compared to existing algorithms.

Association Control Based Load Balancing in Wireless Cellular Networks Using Preamble Sequences

<p>The efficient allocation and use of radio resources is crucial for achieving the maximum possible throughput and capacity in wireless networks. The conventional strongest signal-based user association in cellular networks generally considers only the strength of the signal while selecting a BS, and ignores the level of congestion or load at it. As a consequence, some BSs tend to suffer from heavy load, while their adjacent BSs may carry only light load. This load imbalance severely hampers the network from fully utilizing the network capacity and providing fair services to users. In this thesis, we investigate the applicability of the preamble code sequence, which is mainly used for cell identification, as an implicit information indicator for load balancing in cellular networks. By exploiting the high auto-correlation and low cross-correlation property among preamble sequences, we propose distributed load balancing schemes that implicitly obtain information about the load status of BSs, for intelligent association control. This enables the new users to be attached to BSs with relatively low load in the long term, alleviating the problem of non-uniform user distribution and load imbalance across the network. Extensive simulations are performed with various user densities considering throughput fair and resource fair, as the resource allocation policies in each cell. It is observed that significant improvement in minimum throughput and fair user distribution is achieved by employing our proposed schemes, and preamble sequences can be effectively used as a leverage for better cell-site selection from the viewpoint of fairness provisioning. The load of the entire system is also observed to be balanced, which consequently enhances the capacity of the network, as evidenced by the simulation results.</p>

Association Control Based Load Balancing in Wireless Cellular Networks Using Preamble Sequences

<p>The efficient allocation and use of radio resources is crucial for achieving the maximum possible throughput and capacity in wireless networks. The conventional strongest signal-based user association in cellular networks generally considers only the strength of the signal while selecting a BS, and ignores the level of congestion or load at it. As a consequence, some BSs tend to suffer from heavy load, while their adjacent BSs may carry only light load. This load imbalance severely hampers the network from fully utilizing the network capacity and providing fair services to users. In this thesis, we investigate the applicability of the preamble code sequence, which is mainly used for cell identification, as an implicit information indicator for load balancing in cellular networks. By exploiting the high auto-correlation and low cross-correlation property among preamble sequences, we propose distributed load balancing schemes that implicitly obtain information about the load status of BSs, for intelligent association control. This enables the new users to be attached to BSs with relatively low load in the long term, alleviating the problem of non-uniform user distribution and load imbalance across the network. Extensive simulations are performed with various user densities considering throughput fair and resource fair, as the resource allocation policies in each cell. It is observed that significant improvement in minimum throughput and fair user distribution is achieved by employing our proposed schemes, and preamble sequences can be effectively used as a leverage for better cell-site selection from the viewpoint of fairness provisioning. The load of the entire system is also observed to be balanced, which consequently enhances the capacity of the network, as evidenced by the simulation results.</p>