The electrification of transport has proved to be a breakthrough to uplift the sustainable and eco-friendly platform in the global sector in which electric vehicles (EVs) are considered indispensable. In particular, creating intelligent energy management in the power distribution system integrated with electric vehicle charging stations (EVCS) as a new entity is one of the most important challenging tasks. The implementation of the EVCS network infrastructure should facilitate the adoption of the spatiotemporal electricity demand for EVs. The intelligent decision for the transmission, distribution, energy allocation and charging station placement by the control center or central aggregator is only possible by correctly forecasting its usage, occupancy, and energy or charging demand. Techniques like data analytics have enabled to extract data from the EVCS on a daily basis to store and process all the recorded data. To overcome the above-mentioned challenges related to energy demand forecasting for EVCS network, this work proposes two encoder-decoder models based on convolutional long short-term memory networks (ConvLSTM) and bidirectional ConvLSTM (BiConvLSTM) in combination with the standard long short-term memory (LSTM) network. Data on energy demand from EVCS located in four different cities is used in the proposed models. All datasets are preprocessed to make them suitable for the multi-step time-series learning models in order to make the framework data-centric. The suggested architecture employs the ConvLSTM and BiConvLSTM to extract the key features from the spatiotemporal data of the energy demand data of the EVCS distributed over the time and space. The predicted outcomes generated by the suggested strategy are compared with conventional deep learning models and traditional machine learning techniques.

This paper proposes an optimal route and charging station selection (RCS) algorithm based on model-free deep reinforcement learning (DRL) to overcome the uncertainty issues of the traffic conditions and dynamic arrival charging requests. The proposed DRL based RCS algorithm aims to minimize the total travel time of electric vehicles (EV) charging requests from origin to destination using the selection of the optimal route and charging station considering dynamically changing traffic conditions and unknown future requests. In this paper, we formulate this RCS problem as a Markov decision process model with unknown transition probability. A Deep Q network has been adopted with function approximation to find the optimal electric vehicle charging station (EVCS) selection policy. To obtain the feature states for each EVCS, we define the traffic preprocess module, charging preprocess module and feature extract module. The proposed DRL based RCS algorithm is compared with conventional strategies such as minimum distance, minimum travel time, and minimum waiting time. The performance is evaluated in terms of travel time, waiting time, charging time, driving time, and distance under the various distributions and number of EV charging requests.

Expanding the scale of GPU-based deep learning (DL) clusters would bring not only accelerated AI services but also significant energy consumption costs. In this paper, we propose a cost efficient deep learning job allocation (CE-DLA) approach minimizing the energy consumption cost for the DL cluster operation while guaranteeing the performance requirements of user requests. To do this, we first categorize the DL jobs into two classes: training jobs and inference jobs. Through the architecture-agnostic modeling, our CE-DLA approach is able to conduct the delicate mapping of heterogeneous DL jobs to GPU computing nodes. Second, we design the electricity price-aware DL job allocation so as to minimize the energy consumption cost of the cluster. We show that our approach efficiently avoids the peak-rate time slots of the GPU computing nodes by using the sophisticated mixed-integer nonlinear problem (MINLP) formulation. We additionally integrate the dynamic right-sizing (DRS) method with our CE-DLA approach, so as to minimize the energy consumption of idle nodes having no running job. In order to investigate the realistic behavior of our approach, we measure the actual output from the NVIDIA-based GPU devices with well-known deep neural network (DNN) models. Given the real trace data of the electricity price, we show that the CE-DLA approach outperforms the competitors in views of both the energy consumption cost and the performance for DL job processing.

The recent GPU-based clusters that handle deep learning (DL) tasks have the features of GPU device heterogeneity, a variety of deep neural network (DNN) models, and high computational complexity. Thus, the traditional power capping methods for CPU-based clusters or small-scale GPU devices cannot be applied to the GPU-based clusters handling DL tasks. This article develops a cooperative distributed GPU power capping (CD-GPC) system for GPU-based clusters, aiming to minimize the training completion time of invoked DL tasks without exceeding the limited power budget. Specifically, we first design the frequency scaling approach using the online model estimation based on the recursive least square method. This approach achieves the accurate tuning for DL task training time and power usage of GPU devices without needing offline profiling. Then, we formulate the proposed FS problem as a Lagrangian dual decomposition-based economic model predictive control problem for large-scale heterogeneous GPU clusters. We conduct both the NVIDIA GPU-based lab-scale real experiments and real job trace-based simulation experiments for performance evaluation. Experimental results validate that the proposed system improves the power capping accuracy to have a mean absolute error of $< \!1\%$ , and reduces the deadline violation ratio of invoked DL tasks by 21.5% compared with other recent counterparts.

The explosive increase in deep learning (DL) deployment has led GPU power usage to become a major factor in operational cost of modern HPC clusters. The complex mixture of DL processing, fluctuated renewable generation, and dynamic electricity price impedes the elaborate GPU power control, so as to lead an undesirable cost. However, most previous studies have been concerned only with the design of power management method using DL, and have not care about the cost caused by GPU power consumption for DL processing itself. This paper, as the opposite direction of these trends, proposes a real-time power controller called DeepPow-CTR for cost efficient DL processing in GPU based clusters. We design the GPU frequency scaling algorithm based on model predictive control (MPC), to delicately tune the DL power consumption in response to dynamic renewable generation and electricity price. At the same time, we avoid the unacceptable DL performance degradation by regulating memory-access / feed-forward / back-propagation (MFB) time per each minibatch data in deep neural network (DNN) model training. To solve the designed nonlinear MPC problem rapidly and accurately, we apply the damped Broyden-Fletcher-Goldfarb-Shanno (BFGS) based sequential quadratic programming (SQP) method to our DeepPow-CTR. Our experimental results on lab-scale testbed using real trace data of renewable generation and electricity price, demonstrate that the proposed DeepPow-CTR has superiority and practicality in terms of DL processing power cost and performance, compared to existing methods.