| 1. |
- Li, Wenjing, et al.
(author)
-
PredLife : Predicting Fine-Grained Future Activity Patterns
- 2023
-
In: IEEE Transactions on Big Data. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2332-7790. ; 9:6, s. 1658-1669
-
Journal article (peer-reviewed)abstract
- Activity pattern prediction is a critical part of urban computing, urban planning, intelligent transportation, and so on. Based on a dataset with more than 10 million GPS trajectory records collected by mobile sensors, this research proposed a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines the long-term and short-term dependencies crosswise and also considers randomness, diversity, and uncertainty of individual activity patterns. The proposed results show higher accuracy compared to the ten baselines. The model can generate high diversity results while approximating the original activity patterns distribution. Moreover, the model also has interpretability in revealing the time dependency importance of the activity pattern prediction.
|
|
| 2. |
- Shen, B., et al.
(author)
-
The role of regulatory reforms, market changes, and technology development to make demand response a viable resource in meeting energy challenges
- 2014
-
In: Applied Energy. - : Elsevier BV. - 0306-2619. ; 130, s. 814-823
-
Journal article (peer-reviewed)abstract
- In recent years, demand response and load control automation has gained increased attention from regulators, system operators, utilities, market aggregators, and product vendors. It has become a cost-effective demand-side alternative to traditional supply-side generation technologies to balance the power grid, enable grid integration of renewable energy, and meet growing demands for electricity. There are several factors that have played a role in the development of demand response programs. Existing research are however limited on reviewing in a systematic approach how these factors work together to drive this development. This paper makes an attempt to fill this gap. It provides a comprehensive overview on how policy and regulations, electricity market reform, and technological advancement in the US and other countries have worked for demand response to become a viable demand-side resource to address the energy and environmental challenges. The paper also offers specific recommendations on actions needed to capture untapped demand response potentials in countries that have developed active demand response programs as well as countries that plan to pursue demand response.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Xiong, R., et al.
(author)
-
Lithium-ion battery aging mechanisms and diagnosis method for automotive applications : Recent advances and perspectives
- 2020
-
In: Renewable & sustainable energy reviews. - : Elsevier Ltd. - 1364-0321 .- 1879-0690. ; 131
-
Journal article (peer-reviewed)abstract
- Lithium-ion batteries decay every time as it is used. Aging-induced degradation is unlikely to be eliminated. The aging mechanisms of lithium-ion batteries are manifold and complicated which are strongly linked to many interactive factors, such as battery types, electrochemical reaction stages, and operating conditions. In this paper, we systematically summarize mechanisms and diagnosis of lithium-ion battery aging. Regarding the aging mechanism, effects of different internal side reactions on lithium-ion battery degradation are discussed based on the anode, cathode, and other battery structures. The influence of different external factors on the aging mechanism is explained, in which temperature can exert the greatest impact compared to other external factors. As for aging diagnosis, three widely-used methods are discussed: disassembly-based post-mortem analysis, curve-based analysis, and model-based analysis. Generally, the post-mortem analysis is employed for cross-validation while the curve-based analysis and the model-based analysis provide quantitative analysis. The challenges in the use of quantitative diagnosis and on-board diagnosis on battery aging are also discussed, based on which insights are provided for developing online battery aging diagnosis and battery health management in the next generation of intelligent battery management systems (BMSs).
|
|
