No abstract

Electric vehicles (EVs) are expected to play a critical role in future transportation systems. A number of countries have published roadmaps aiming to facilitate the adoption of EVs on the road. It is estimated that existing charging facilities will not be able to satisfy the tremendous charging demands of a dramatically increasing number of EVs. Following the rapid development of artificial intelligence and mobile communication technology, certain charging pricing mechanism is expected to influence the charging behavior of EV drivers. In order to maximize the working efficiency of highway charging facilities and the consumption of the renewable energy near charging facilities, this paper proposes a pricing methodology taking into account the charging facility service ratio, traffic flow and renewable energy generation. To support the adoption of the proposed pricing methodology, forecasts of hour-by-hour traffic flow and renewable generation as well as calculation of the shortest paths to different charging stations (CSs) are investigated. A road network testbed based on the Dublin traffic network is established to evaluate the proposed pricing methodology. It is discovered that for certain wind-rich CSs, the proposed pricing methodology can increase the consumption rate of wind energy by up to 82.97%, with an average improvement of 30.73%; for certain solar-rich CSs, it can improve the level of solar energy consumption by up to 59.50% and an average increase of 29.28% is achieved. The proposed pricing methodology can also reduce traffic jams to some extent at both peak and off-peak times. INDEX TERMS Electric vehicle, charging stations, charging pricing methodology, renewable energy consumption. NOMENCLATURE

No abstract

No abstract

This paper proposes and assesses three different control approaches for the hydrocarbon natural gas (HCNG) penetrated integrated energy system (IES). The three control approaches adopt mixed integer linear programing, conditional value at risk (CVaR), and robust optimization (RO), respectively, aiming to mitigate the renewable generation uncertainties. By comparing the performance and efficiency, the most appropriate control approach for the HCNG penetrated IES is identified. The numerical analysis is conducted to evaluate the three control approaches in different scenarios, where the uncertainty level of renewable energy (within the HCNG penetrated IES) varies. The numerical results show that the CVaR-based approach outperforms the other two approaches when renewable uncertainty is high (approximately 30%). In terms of the cost to satisfy the energy demand, the operational cost of the CVaR-based method is 8.29% lower than the RO one, while the RO-based approach has a better performance when the renewable uncertainty is medium (approximately 5%) and it is operational is 0.62% lower than that of the CVaR model. In both evaluation cases, mixed integer linear programing approach cannot meet the energy demand. This paper also compares the operational performance of the IES with and without HCNG. It is shown that the IES with HCNG can significantly improve the capability to accommodate renewable energy with low upgrading cost.

Furui first demonstrated that the identity of both consonant and vowel can be perceived from the C-V transition; later, Stevens proposed that acoustic landmarks are the primary cues for speech perception, and that steady-state regions are secondary or supplemental. Acoustic landmarks are perceptually salient, even in a language one doesn't speak, and it has been demonstrated that non-speakers of the language can identify features such as the primary articulator of the landmark. These factors suggest a strategy for developing language-independent automatic speech recognition: landmarks can potentially be learned once from a suitably labeled corpus and rapidly applied to many other languages. This paper proposes enhancing the cross-lingual portability of a neural network by using landmarks as the secondary task in multi-task learning (MTL). The network is trained in a well-resourced source language with both phone and landmark labels (English), then adapted to an under-resourced target language with only word labels (Iban). Landmark-tasked MTL reduces source-language phone error rate by 2.9% relative, and reduces target-language word error rate by 1.9%-5.9% depending on the amount of target-language training data. These results suggest that landmark-tasked MTL causes the DNN to learn hidden-node features that are useful for cross-lingual adaptation.

Most mainstream automatic speech recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea that some frames are more important than others. Acoustic landmark theory exploits quantal nonlinearities in the articulatory-acoustic and acoustic-perceptual relations to define landmark times at which the speech spectrum abruptly changes or reaches an extremum; frames overlapping landmarks have been demonstrated to be sufficient for speech perception. In this work, experiments are conducted on the TIMIT corpus, with both Gaussian mixture model (GMM) and deep neural network (DNN)-based ASR systems, and it is found that frames containing landmarks are more informative for ASR than others. It is discovered that altering the level of emphasis on landmarks by re-weighting acoustic likelihood tends to reduce the phone error rate (PER). Furthermore, by leveraging the landmark as a heuristic, one of the hybrid DNN frame dropping strategies maintained a PER within 0.44% of optimal when scoring less than half (45.8% to be precise) of the frames. This hybrid strategy outperforms other non-heuristic-based methods and demonstrate the potential of landmarks for reducing computation.

Many cognitive studies have indicated that the path simplicity may be as important as its distance travelled. However, the optimality of paths for current navigation system is often judged purely on the distance travelled or time cost, and not the path simplicity. To balance these factors, this paper presented an algorithm to compute a path that not only possesses fewest turns but also is as short as possible by utilizing the breadth-first-search strategy. The proposed algorithm started searching from a starting point, and expanded layer by layer through searching zero-level reachable points until the endpoint is found, and then deleted unnecessary points in the reverse direction. The forward searching and backward cleaning strategies were presented to build a hierarchical graph of zero-level reachable points, and form a fewestturn-path graph (G*). After that, a classic Dijkstra shortest path algorithm was executed on the G* to obtain a fewestturn-and-shortest path. Comparing with the shortest path in Baidu map, the algorithm in this work has less than half of the turns but the nearly same length. The proposed fewest-turn-and-shortest path algorithm is proved to be more suitable for human beings according to human cognition research.