• Energy Research
• 2021-2025close
• SG close
• Applied Energy close

Forecasts of the wave heights can assist in the data-driven control of wave energy systems. However, the dynamic properties and extreme fluctuations of the historical observations pose challenges to the construction of forecasting models. This paper proposes a novel dynamic ensemble deep Echo state networks (ESN) to learn the dynamic characteristics of the significant wave height. The dynamic ensemble ESN creates a profound representation of the input and trains an independent readout module for each reservoir. To begin, numerous reservoir layers are built in a hierarchical order, adopting a reservoir pruning approach to filter out the poorer representations. Finally, a dynamic ensemble block is used to integrate the forecasts of all readout layers. The suggested model has been tested on twelve available datasets and statistically outperforms state-of-the-art approaches.

Abstract Clathrate hydrate-based desalination (HyDesal) is a promising desalination technology but it is energy intensive. Developing strategies to reduce the high energy consumption of HyDesal process is necessary for its industrial application. The need for refrigeration requirement for the operation of HyDesal can be offset by LNG cold exergy to reduce its energy consumption. However, the LNG cold exergy utilization efficiency is low due to the large temperature difference between LNG and seawater and hydrate former. In this work, we propose a sustainable process that integrates HyDesal and organic Rankine cycle by utilizing LNG cold exergy to generate fresh water and electricity simultaneously. This integrated process was optimized by adopting particle swarm optimization algorithm to achieve maximal power and fresh water generation. Further, an economic analysis was performed to compare the economic performance of the proposed system and the base case. The results showed that the proposed process could achieve zero specific energy consumption for desalination and generate extra power. The largest fresh water production and power generation of 165.3 tonne/h and 3480 kW were achieved by adopting cyclopentane as hydrate former and mixed working fluid in organic Rankine cycle based on 100 tonne/h of LNG flowrate. The lowest levelized cost of water of the proposed process was 1.946 $ /m3, which was 21.05% lower than that of the base case. Thus, the proposed sustainable process can strengthen the energy–water nexus and reduce the greenhouse gas emission by utilizing LNG cold exergy.