Machine learning models have proven to be reliable methods in classification tasks. However, little research has been conducted on the classification of dwelling characteristics based on smart meter and weather data before. Gaining insights into dwelling characteristics, which comprise of the type of heating system used, the number of inhabitants, and the number of solar panels installed, can be helpful in creating or improving the policies to create new dwellings at nearly zero-energy standard. This paper compares different supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Long-short term memory, and methods used to correctly implement these algorithms. These methods include data pre-processing, model validation, and evaluation. Smart meter data, which was used to train several machine learning algorithms, was provided by Groene Mient. The models that were generated by the algorithms were compared on their performance. The results showed that the Long-short term memory performed the best with 96% accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrics were used to produce classification reports, which indicates that the Long-short term memory outperforms the compared models on the evaluation metrics for this specific problem.
The methodology should be a uniform approach that also is flexible enough to accommodate all combinations that make up the different solutions in 6 OPs. For KPIs A and B this required the use of sub-KPIs to differentiate the effects of each (individual and combination of) implemented solutions and prevent double counting of results. This approach also helped to ensure that all 6 OPs use a common way and scope to calculate the various results. Consequently, this allowed the project to capture the results per OP and the total project in one ‘measurement results’ template. The template is used in both the individual OP reports and the ‘KPI Results: Baseline & Final results’ report where all results are accumulated; each instance providing a clear overview of what is achieved. This report outlines the details of the methodology used and applied. It is not just meant to provide a clarification of the results of the project, but is also meant to allow others who are embarking on adopting similar solutions for the purpose of CO2 reduction, becoming more energy autonomous or avoid grid stress or investments to learn about and possibly use the same methodology.
Urban tourism increasingly focuses on the role of hospitality in cities, evolving from a means to strengthen tourism as a ‘product’, towards a focus on tourism as an opportunity for revitalization and transformation of destinations. In this context, cities are considered dynamic communities in which ‘hosts’ (entrepreneurs, residents, municipalities) and ‘guests’ (visitors, tourists) co-habitate and co-create multisensorial experiences. This shift in focus comes hand in hand with increasing awareness of competitiveness and sustainability of destinations, expressed by a harmonious relationship between city residents and visitors and a balanced usage of the city as a shared resource. This is of great importance, given the intense usage of urban spaces – the city center of Amsterdam being an illustrative example – and the multiple purposes that these spaces represent for different stakeholders. This paper presents the outcome of a review study into city hospitality experience indicators. We integrate these indicators as a basis for the development of a new scale for measuring the effectiveness of hospitality interventions in relation to outcome variables such as satisfaction and net promotor score (NPS). We thereby provide an important means for scholars and practitioners to develop sustainable tourism actions inclusive of local community interests, in support of efforts toward more balanced city experiences among all stakeholders.
DISCO aims at fast-tracking upscaling to new generation of urban logistics and smart planning unblocking the transition to decarbonised and digital cities, delivering innovative frameworks and tools, Physical Internet (PI) inspired. To this scope, DISCO will deploy and demonstrate innovative and inclusive urban logistics and planning solutions for dynamic space re-allocation integrating urban freight at local level, within efficiently operated network-of-networks (PI) where the nodes and infrastructure are fixed and mobile based on throughput demands. Solutions are co-designed with the urban logistics community – e.g., cities, logistics service providers, retailers, real estate/public and private infrastructure owners, fleet owners, transport operators, research community, civil society - all together moving a paradigm change from sprawl to data driven, zero-emission and nearby-delivery-based models.
Positive Energy Districts (PEDs) can play an important part in the energy transition by providing a year-round net positive energy balance in urban areas. In creating PEDs, new challenges emerge for decision-makers in government, businesses and for the public. This proposal aims to provide replicable strategies for improving the process of creating PEDs with a particular emphasis on stakeholder engagement, and to create replicable innovative business models for flexible energy production, consumption and storage. The project will involve stakeholders from different backgrounds by collaborating with the province, municipalities, network operators, housing associations, businesses and academia to ensure covering all necessary interests and mobilise support for the PED agenda. Two demo sites are part of the consortium to implement the lessons learnt and to bring new insights from practice to the findings of the project work packages. These are 1), Zwette VI, part of the city of Leeuwarden (NL), where local electricity congestion causes delays in building homes and small industries. And 2) Aalborg East (DK), a mixed-use neighbourhood with well-established partnerships between local stakeholders, seeking to implement green energy solutions with ambitions of moving towards net-zero emissions.
LEVV-LOGIC presenteert een voorstel voor onderzoek naar de inzet van lichte elektrische vrachtvoertuigen (LEVV’s) voor de levering van goederen in steden. In dit project ontwikkelen de Hogeschool van Amsterdam en Hogeschool Rotterdam samen met logistiek dienstverleners, verladers en voertuigaanbieders uit het mkb, netwerkorganisaties, kennisinstellingen en gemeenten nieuwe kennis over logistieke concepten en business modellen met LEVV met als doel de rendabele inzet van LEVV’s in stadslogistiek. De doelstelling komt voort uit een vraag van logistiek dienstverleners uit het mkb. Zij willen LEVV’s inzetten, maar weten niet hoe ze dit rendabel kunnen doen omdat de huidige logistieke processen in de keten afgestemd zijn op de inzet van bestel- en vrachtvoertuigen. Voor overstap naar LEVV’s dienen de logistieke processen anders georganiseerd te worden, want de voertuigen zijn kleiner in omvang en hebben een andere laad- en energievoorziening. Daarnaast is onvoldoende duidelijk voor welke stadslogistieke stromen LEVV’s geschikt zijn en aan welke technische eisen de voertuigen moeten voldoen. Verladers (verzenders van goederen) en voertuigaanbieders zijn actief betrokken bij de uitvoering van het onderzoek om afstemming met de marktvraag en de techniek te garanderen. De projectdeelnemers delen de ambitie om met LEVV’s een bijdrage te leveren aan regionale, nationale en Europese doelstellingen om stedelijk goederenvervoer efficiënter en schoner (“zero emissie”) te organiseren. Het project draagt hier aan bij door middel van vijf activiteiten. De deelnemers in LEVV-LOGIC: 1. onderzoeken de potentie van LEVV voor specifieke stadslogistieke stromen (waaronder food-, webwinkel-, en facilitaire leveringen); 2. ontwerpen nieuwe logistieke concepten met LEVV voor de distributie van goederen van verzender naar ontvanger; 3. vertalen logistieke vereisten naar technische ontwerpen en aanpassingen aan bestaande LEVV’s; 4. experimenten met nieuwe LEVV-concepten in de praktijk; 5. ontwikkelen schaalbare business modellen met LEVV’s. Het project verzekert een sterke relatie met praktijk en wetenschap, omdat zij via haar deelnemers verbonden is aan de Topsector Logistiek, de Green Deal Zero Emissie Stadslogistiek, de Europese federatie voor Cycle Logistics en de Europese onderzoeksprojecten FREVUE (FP7) en CITYLAB (Horizon2020). Via de betrokkenheid van drie lectoren en zes opleidingen van twee hogescholen wordt een brede inzet van de resultaten in het onderwijs gerealiseerd. LEVV-LOGIC hanteert een multidisciplinaire aanpak met aandacht voor de rol van logistiek, techniek, beleid en gedrag. Hiermee versterkt het project professionals van nu en van de toekomst met kennis om problemen in stadslogistiek op te lossen.
