Search for: All records

While Deep Reinforcement Learning has emerged as a de facto approach to many complex experience-driven networking problems, it remains challenging to deploy DRL into real systems. Due to the random exploration or half-trained deep neural networks during the online training process, the DRL agent may make unexpected decisions, which may lead to system performance degradation or even system crash. In this paper, we propose PnP-DRL, an offline-trained, plug and play DRL solution, to leverage the batch reinforcement learning approach to learn the best control policy from pre-collected transition samples without interacting with the system. After being trained without interaction with systems, our Plug and Play DRL agent will start working seamlessly, without additional exploration or possible disruption of the running systems. We implement and evaluate our PnP-DRL solution on a prevalent experience-driven networking problem, Dynamic Adaptive Streaming over HTTP (DASH). Extensive experimental results manifest that 1) The existing batch reinforcement learning method has its limits; 2) Our approach PnP-DRL significantly outperforms classical adaptive bitrate algorithms in average user Quality of Experience (QoE); 3) PnP-DRL, unlike the state-of-the-art online DRL methods, can be off and running without learning gaps, while achieving comparable performances. 

In this paper, we present design, implementation and evaluation of a control framework, EXTRA (EXperience-driven conTRol frAmework), for scheduling in general-purpose Distributed Stream Data Processing Systems (DSDPSs). Our design is novel due to the following reasons. First, EXTRA enables a DSDPS to dynamically change the number of threads on the fly according to system states and demands. Most existing methods, however, use a fixed number of threads to carry workload (for each processing unit of an application), which is specified by a user in advance and does not change during runtime. So our design introduces a whole new dimension for control in DSDPSs, which has a great potential to significantly improve system flexibility and efficiency, but makes the scheduling problem much harder. Second, EXTRA leverages an experience/data driven model-free approach for dynamic control using the emerging Deep Reinforcement Learning (DRL), which enables a DSDPS to learn the best way to control itself from its own experience just as a human learns a skill (such as driving and swimming) without any accurate and mathematically solvable model. We implemented it based on a widely-used DSDPS, Apache Storm, and evaluated its performance with three representative Stream Data Processing (SDP) applications: continuous queries, word count (stream version) and log stream processing. Particularly, we performed experiments under realistic settings (where multiple application instances are mixed up together), rather than a simplified setting (where experiments are conducted only on a single application instance) used in most related works. Extensive experimental results show: 1) Compared to Storm’s default scheduler and the state-of-the-art model-based method, EXTRA substantially reduces average end-to-end tuple processing time by 39.6% and 21.6% respectively on average. 2) EXTRA does lead to more flexible and efficient stream data processing by enabling the use of a variable number of threads. 3) EXTRA is robust in a highly dynamic environment with significant workload change. 

In this paper, we present design, implementation and evaluation of a novel predictive control framework to enable reliable distributed stream data processing, which features a Deep Recurrent Neural Network (DRNN) model for performance prediction, and dynamic grouping for flexible control. Specifically, we present a novel DRNN model, which makes accurate performance prediction with careful consideration for interference of co-located worker processes, according to multilevel runtime statistics. Moreover, we design a new grouping method, dynamic grouping, which can distribute/re-distribute data tuples to downstream tasks according to any given split ratio on the fly. So it can be used to re-direct data tuples to bypass misbehaving workers. We implemented the proposed framework based on a widely used Distributed Stream Data Processing System (DSDPS), Storm. For validation and performance evaluation, we developed two representative stream data processing applications: Windowed URL Count and Continuous Queries. Extensive experimental results show: 1) The proposed DRNN model outperforms widely used baseline solutions, ARIMA and SVR, in terms of prediction accuracy; 2) dynamic grouping works as expected; and 3) the proposed framework enhances reliability by offering minor performance degradation with misbehaving workers. 

Large-scale deep neural networks are both memory and computation-intensive, thereby posing stringent requirements on the computing platforms. Hardware accelerations of deep neural networks have been extensively investigated. Specific forms of binary neural networks (BNNs) and stochastic computing-based neural networks (SCNNs) are particularly appealing to hardware implementations since they can be implemented almost entirely with binary operations. Despite the obvious advantages in hardware implementation, these approximate computing techniques are questioned by researchers in terms of accuracy and universal applicability. Also it is important to understand the relative pros and cons of SCNNs and BNNs in theory and in actual hardware implementations. In order to address these concerns, in this paper, we prove that the ”ideal” SCNNs and BNNs satisfy the universal approximation property with probability 1 (due to the stochastic behavior), which is a new angle from the original approximation property. The proof is conducted by first proving the property for SCNNs from the strong law of large numbers, and then using SCNNs as a “bridge” to prove for BNNs. Besides the universal approximation property, we also derive an appropriate bound for bit length M in order to provide insights for the actual neural network implementations. Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity. In other words, they have the same asymptotic energy consumption with the growth of network size. We also provide a detailed analysis of the pros and cons of SCNNs and BNNs for hardware implementations and conclude that SCNNs are more suitable.