Search

Predicting flows (e.g., the traffic of vehicles, crowds, and bikes), consisting of the in-out traffic at a node and transitions between different nodes, in a spatio-temporal network plays an important role in transportation systems. However, this is a very challenging problem, affected by multiple complex factors, such as the spatial correlation between different locations, temporal correlation among different time intervals, and external factors (like events and weather). In addition, the flow at a node (called node flow) and transitions between nodes (edge flow) mutually influence each other. To address these issues, we propose a multitask deep-learning framework that simultaneously predicts the node flow and edge flow throughout a spatio-temporal network. Based on fully convolutional networks, our approach designs two sophisticated models for predicting node flow and edge flow, respectively. These two models are connected by coupling their latent representations of middle layers, and trained together. The external factor is also integrated into the framework through a gating fusion mechanism. In the edge flow prediction model, we employ an embedding component to deal with the sparse transitions between nodes. We evaluate our method based on the taxicab data in Beijing and New York City. Experimental results show the advantages of our method beyond 11 baselines, such as ConvLSTM, CNN, and Markov Random Field. [ABSTRACT FROM AUTHOR]

Multi-energy systems can provide a constant level of service to end-use energy demands, while deriving delivered energy from a variety of primary/secondary energy sources. This fuel-switching capability can be used to reduce operating expenses, reduce environmental impacts, improve flexibility to accommodate renewable energy, and improve reliability. This paper presents four frameworks for incentivizing energy hub equipment investments for low-carbon operation targets. These frameworks vary in the measures taken to achieve low-carbon operation (explicit constraint versus carbon pricing) and in the relationship between the hub builder and operator (cooperative versus uncoordinated). The underlying energy hub model upon which these frameworks are built is an enhanced greenfield model, introducing “energy buses” to reduce dimensionality. A case study is conducted for a campus being designed in Beijing, and results from each framework are compared to illustrate their relative costs. When the operator cannot be trusted to cooperate in controlling emissions, the system must be “overbuilt” with more expensive equipment to ensure emissions target are met. A taxation-based approach increases overall costs at moderate emissions targets, but this effect decreases at aggressive targets. This paper also compares the cost of less efficient institutional frameworks with the most efficient approach, i.e., cooperation between builder and operator with constraints on emissions. [ABSTRACT FROM AUTHOR]