From the article: Abstract: An overview of neural network architectures is presented. Some of these architectures have been created in recent years, whereas others originate from many decades ago. Apart from providing a practical tool for comparing deep learning models, the Neural Network Zoo also uncovers a taxonomy of network architectures, their chronology, and traces back lineages and inspirations for these neural information processing systems.
The academic and professional attention to the large synergies hidden in horizontal collaborations is increasing. This study attempts to address the impact of collaborative transport on transportation lead-time and lead-time variability through empirically investigating a group of SMEs involved in a collaborative distribution network. Data was collected for seven pre-cooperation and eight cooperative orders over a period of 14 months. The results of Mann-Whitney U-test show a significant average reduction of 30.8% in the duration of lead times. Lead-time variability was also found to be reduced as the result of changes in the coefficient of variances and the Bartlett’s test for homogeneity of variances. Horizontal collaboration in transport could eventually lead to reduced lead times and lower variability of lead time which results in reduced supply chain costs. This can be achieved by means of direct routing and avoiding multi-transshipment routes which reduces the uncertainty and variability by diminishing the number of stages in the transport chain. Thus, effective lead-time management is considered a source of competitive advantage as it can reduce supply chain costs by lowering inventory levels, but is also capable of improving performance and customer service by offering improved product quality service levels.
Distribution centres are becoming more and more relevant for spatial planning, due to their rapidly increasing size and number. There is little literature, however, that provides a generalized analysis of the size and functional attributes of distribution centres, and none that discusses the relationships between these attributes. Our aim is to fill this gap by providing new evidence and analysis to understand this relationship. We make use of an extensive database of 2888 DCs in the Netherlands to develop a new typology of DCs based on the geographical location of DCs, their functional attributes and client sector characteristics. The analysis shows that the context in which medium sized DCs are operating is more heterogeneous than in the case of very large and small size DCs. This study is a first attempt to analyse this relationship between facility size and functions based on a rich and extensive dataset of large population of DCs. The results can serve as input for further quantitative statistical analysis and international comparison.
The integration of renewable energy resources, controllable devices and energy storage into electricity distribution grids requires Decentralized Energy Management to ensure a stable distribution process. This demands the full integration of information and communication technology into the control of distribution grids. Supervisory Control and Data Acquisition (SCADA) is used to communicate measurements and commands between individual components and the control server. In the future this control is especially needed at medium voltage and probably also at the low voltage. This leads to an increased connectivity and thereby makes the system more vulnerable to cyber-attacks. According to the research agenda NCSRA III, the energy domain is becoming a prime target for cyber-attacks, e.g., abusing control protocol vulnerabilities. Detection of such attacks in SCADA networks is challenging when only relying on existing network Intrusion Detection Systems (IDSs). Although these systems were designed specifically for SCADA, they do not necessarily detect malicious control commands sent in legitimate format. However, analyzing each command in the context of the physical system has the potential to reveal certain inconsistencies. We propose to use dedicated intrusion detection mechanisms, which are fundamentally different from existing techniques used in the Internet. Up to now distribution grids are monitored and controlled centrally, whereby measurements are taken at field stations and send to the control room, which then issues commands back to actuators. In future smart grids, communication with and remote control of field stations is required. Attackers, who gain access to the corresponding communication links to substations can intercept and even exchange commands, which would not be detected by central security mechanisms. We argue that centralized SCADA systems should be enhanced by a distributed intrusion-detection approach to meet the new security challenges. Recently, as a first step a process-aware monitoring approach has been proposed as an additional layer that can be applied directly at Remote Terminal Units (RTUs). However, this allows purely local consistency checks. Instead, we propose a distributed and integrated approach for process-aware monitoring, which includes knowledge about the grid topology and measurements from neighboring RTUs to detect malicious incoming commands. The proposed approach requires a near real-time model of the relevant physical process, direct and secure communication between adjacent RTUs, and synchronized sensor measurements in trustable real-time, labeled with accurate global time-stamps. We investigate, to which extend the grid topology can be integrated into the IDS, while maintaining near real-time performance. Based on topology information and efficient solving of power flow equation we aim to detect e.g. non-consistent voltage drops or the occurrence of over/under-voltage and -current. By this, centrally requested switching commands and transformer tap change commands can be checked on consistency and safety based on the current state of the physical system. The developed concepts are not only relevant to increase the security of the distribution grids but are also crucial to deal with future developments like e.g. the safe integration of microgrids in the distribution networks or the operation of decentralized heat or biogas networks.
Climate change has impacted our planet ecosystem(s) in many ways. Among other alterations, the predominance of long(er) drought periods became a point of concern for many countries. A good example is The Netherlands, a country known by its channels and abundant surface water, which has listed “drought effect mitigation” among the different topics in the last version of its “Innovation Agenda” (Kennis en Innovatie Agenda, KIA). There are many challenges to tackle in such scenario, one of them is solutions for small/decentralized communities that suffer from dry-up of surface reservoirs and have no groundwater source available. Such sites are normally far from big cities and coastal zones, which impair the supply via distribution networks. In such cases, Atmospheric Water Generation (AWG) technologies are a plausible solution. These systems have relatively small production rates (few m3 per day), but they can still provide enough volume for cities with up to 100k inhabitants. Despite having real scale systems already installed in different locations worldwide, most systems are between TRL 5 and 6. Thus need further development. SunCET proposes an in-situ evaluation of an AWG system (WaterWin) developed by two different Dutch companies (Solaq and Sustainable Eyes) in the Brazilian semi-arid state of Ceará. The cooperation with NHL Stenden will provide the necessary expertise, analytical and technical support to conduct the tests. The state government of Ceará built an infrastructure to support the realization of in-situ tests, as they want to further accelerate technology implementation in the state. Such structure will make it possible to share costs and decrease total investments for the SMEs. Finally, it is also intended to help establishing partnerships between Dutch SMEs and Brazilian end users, i.e. municipalities of the Ceará state and small agriculture companies in the region.
