AI4PublicPolicy / Pilots

AI4PublicPolicy Pilots

A primary objective for AI4PublicPolicy project is to leverage all stakeholders’ participation and feedback for the development and optimization of automated, transparent and citizen-centric public policies. To achieve this the project will leverage feedback from five (5) different user-driven pilots, coordinated by the project’s participating public authorities.

The following table provides an overview of the project’s pilots, including their themes and their linking to other pilots. The latter linking will facilitate the validation of the project’s policy linking and semantic interoperability technologies, as linked pilots will share, repurpose and reuse policy models.

No. Pilot Leaders  Theme – Policies Involved  Linked Pilot(s) 
1 DAEM (Greece)  Policies for Infrastructures Maintenance and Repair; Policies for Parking Space Management and Urban Mobility    CDG (Italy) & NIC (Cyprus) 
2 CDG (Italy)  Policies for Citizens and Business Services Optimization  DAEM (Greece) 
3 NIC (Cyprus)  Policies for Holistic Urban Mobility and Accessibility   DAEM (Greece) 
4 LIS (Portugal)  Energy Management and Optimization Policies  BURGAS (Bulgaria) 
5 BURGAS (Bulgaria)  Data-Driven Water Infrastructure Planning and Maintenance Policies LIS (Portugal) 

Pilot #1: Citizen Centric Management and Optimization of City Resources

Location: Athens, Greece

Pilot Leader(s): Dimos Athinaion Epicheirisi Michanografisis (DAEM) – City of Athens IT Company

Theme – Policies Involved:

  • Policies for Infrastructures Maintenance and Repair;
  • Policies for Parking Space Management and Urban Mobility

The City of Athens is the capital city and largest Municipality in Greece and serves a population of about 750,000 people, swelling to almost 3 million when daily commuters are included. The City has a complex and aged infrastructure (roads, water pipelines, streetlights, public spaces, public buildings, garbage collection facilities, etc.). Furthermore, as one of Europe’s largest metropolitan areas, Athens must deal with significant traffic flows in the city, which must be handled in cost effective and environment efficient ways, but also in ways acceptable by the citizens. The pilot aims at developing, demonstrating and evaluating data-driven, citizen-centric and evidence-based policies about the maintenance of the city’s infrastructure and the citizens’ transport and urban mobility, including the economic implications of these policies.

Use Cases:

  • Maintenance Policies Optimization
  • Predictive Citizen-Centric Transport/Parking Policies Development
  • Economic/Revenue Policies Modelling.

The following KPIs will be tracked:

  • Reduced time in resolving reported incidents;
  • Reduction of the average cost per incident for the city;
  • Increased citizen satisfaction from the infrastructure maintenance activities;
  • Increased citizen satisfaction from the smart parking activities;
  • Increased revenue from parking;
  • Improved average parking availability;
  • Improved “fill rate” and occupancy for the parking positions.

Pilot #2: Citizens and Businesses Services Optimization

Location: Genoa, Italy

Pilot Leader(s): Commune di Genova

Theme – Policies Involved: Policies for Citizens and Business Services Optimization

The pilot will develop a policy development toolkit for the city of Genova, which will enable the public authority to extract and experiment with evidence-based policies about how to optimally organize the operations of the various citizen-facing services and department of the municipality. The toolkit will be integrated in the virtualized platform of the project i.e., it will be an instance of the cloud-based VPME customized to the needs of the municipality of Genova. It will comprise datasets derived from the unique phone number infrastructure and its (digital) interfaces to the various departments and systems of the municipality, as well as citizens’ feedback that will be collected through various channels. The pilot will integrate various AI tools, including tools for analyzing citizens’ feedback, but mainly tools for data-driven policy recommendation, policy simulation and benchmarking. Based on this tool, the pilot system will extract and recommend policies for allocating resources and organizing the operations of the different departments of the municipality.

As part of the pilot, the municipality with use its customized VPME instance and the AI tools of the project in the scope of the following use cases:

  1. Evaluation and benchmarking alternative service handling workflows: As part of this use case, CDG will use the policy toolkit for providing data-driven recommendations about how different configurations of internal processes perform when handling requests for citizen services. Specifically, ML/DL techniques will be used to extract rules about the steps entailed in handling a request. Different process configurations will be considered based on the data about citizens’ and businesses’ requests, their types and citizens’ satisfaction feedback.
  2. Optimizing the allocation of resources: This use case will execute ML/DL techniques over data about the citizens’ requests for services and their handling workflows, towards identifying optimal allocation of human resources and other assets (e.g., machines, equipment, software/hardware). The outcome of the toolkit will be a set of data-driven recommendations and rules about how to best allocate resources to the various departments in order to make optimal use of resources, minimize service times and increase citizens’ satisfaction.
  3. Citizens’ requests and policies visualizations: This use case will visualize data about citizens’ requests and about the workflows for handling them in an interactive map/dashboard. Information about the type, location, handling times, citizen demographics etc. associated with each request will be displayed and provided to both policy makers (inside the municipality) and citizens. The dashboard will be used to increase the transparency, trustworthiness and accountability of the policy development process.

The VPME will provide the means for using the AI policy development tools of the above use cases at a strategic level. Hence, they will facilitate not only the creation/formulation of policies, but also their reprogramming and reconfiguration as well. All policy development use cases will engage both citizens and policy makers from CDG. Furthermore, as part of the pilot, the project will also study and implement the required organizational transformation activities.

The following KPIs will be tracked:

  • Improved utilization of resources in the various services/departments of the company;
  • Reduced cost of fulfillment of citizens’ requests;
  • Increased citizens’ and SMEs’ satisfaction;
  • Increased trust in the policy development process.

Pilot #3: Effective Policies for Holistic Urban Mobility and Accessibility

Location: Nicosia, Cyprus

Pilot Leader(s): Nicosia Municipality

Theme – Policies Involved: Policies for Holistic Urban Mobility and Accessibility

The goal of the pilot is to extract and validate policies for the operation of the municipality’s holistic mobile and accessibility platform. More specifically, AI4PublicPolicy will provide Nicosia Municipality with access to customized instances of the project’ s VPME that will enable the public authority to extract and evaluate data-driven urban mobility policies. The policies will consider all the different urban transport options and will aim at optimizing multiple parameters such as cost-effectiveness, sustainability and citizens’ satisfaction. To this end, the pilot will create analytics models about urban transport and mobility policies, while leveraging AI algorithms in order to identify/recommend the parameters that lead to optimal policies. The policies will assume a holistic environment, where all mobility services are interconnected.

Policy makers and other employees of the municipality will use the project’ s VPME and policy development toolkit in the scope of the following use cases:

  1. Optimal urban mobility policies for citizens: This use case will extract and provide to citizens data-driven optimal policies about their mobility in the cities. The policies will consider different optimization targets such as travel time, travel cost, as well as user-defined constraints. They will be presented and visualized to citizens in the form of mobility rules/patterns for different days/times.
  2. Optimal urban mobility policies for the municipality: This use case will recommend/introduce policies that optimize the city’s goals such as sustainability and transport operational cost, while taking into account citizens’ feedback and satisfaction. These parameters will be considered in developing analytical models for the policies. Accordingly, the AI-based policy development, recommendation and benchmarking tools of the project will be used to evaluate alternative mobility/transport policies, notably policies associated with the operation of the various transport modalities.
  3. Accessible urban mobility policies: This use cases will target people with disabilities. Based on AI-based data mining over available transport datasets, it will extract mobility solutions/policies that will enable people with disabilities to get out of their houses and into the city by providing customized on-demand transportation. Based on the extracted policies, innovative business models will be considered, aiming at generating value from data driven knowledge and evidence-based policies. All use cases will involve the use of XAI tools for interpreting the policies in a policy-maker friendly way. Furthermore, all use cases will entail the engagement of citizens and the public administration official in their design and validation.

The following KPIs will be tracked:

  • Reduced transport operational costs for the city;
  • Reduced transportation cost for the citizens;
  • Increased citizens’ satisfaction;
  • Improve transportation sustainability (i.e., reduced CO2 emissions, environmental performance).

Pilot #4: Energy Management Policies

Location: Lisbon, Portugal

Pilot Leader(s): Lisboa E-Nova – Agência Municipal de Energia e Ambiente

Theme – Policies Involved: Energy Management and Optimization Policies

The pilot focuses on gathering relevant and valid data sources, such as weather, buildings’ characteristics and energy consumption, and with the aid of AI and machine learning algorithms detect patterns and problems regarding energy efficiency, so that possible data-driven policies can be defined to ensure a more sustainable and efficient environment in the city. Data regarding energy consumption will be gathered using smart meters and IoT devices. Apart from the current energy consumption time interval of 15 minutes, with the implementation of IoT devices, a deeper analysis will be made, to analyse specific types of energy consumption in each building, assuming a breakdown of consumption considering the equipment existing in each delivery point. Data regarding buildings archetypes is gathered with the support from other projects of LIS. With these main data sources, AI models can be implemented to analyse patterns and support policy making on general energy performance improvement. Deep Learning models such as long/short-term memory network (LSTM Network), Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs) can also be used to provide forecast on energy consumption. Clustering algorithms, e.g., k-Means, Hierarchical Cluster Analysis and Expectation Maximization can be used to group clients on similar energy usage. Other deep learning models, such as deep neural networks, can be used to detect patterns on the behaviour of different buildings. With the definition of different patterns in buildings, and with the integration of the different information layers, it is possible to create and analyse common behavioural scenarios on each archetype of buildings to better understand real energy performance. This information can be used for data-driven decisions on policies for energy efficiency.

Two main use cases of policy development will be considered:

  1. Energy performance analysis: This use case will identify problems in the buildings’ energy performance and will perform root cause analysis;
  2. Budget planning for energy usage and buildings renovation: This use cases will focus on policy making decisions on budget planning and effective use of budget and public resources towards buildings renovation and energy usage. For instance, policies for the definition of specific financial supporting mechanisms or retrofit schemes will be recommended.

The following KPIs will be tracked:

  • Number of datasets to be gathered and integrated;
  • Number of policy instruments to be extracted/recommended;
  • Level of Compliance to SECAP.

Pilot #5: Data-Driven Water Infrastructure Planning and Maintenance Policies

Location: Burgas, Bulgaria

Pilot Leader(s): Burgas Municipality

Theme – Policies Involved: Data-Driven Water Infrastructure Planning and Maintenance Policies

Burgas Municipality has been heavily investing in the development of a safe and efficient water supply and sanitisation infrastructures, as reflected in recent initiatives, including: (i) The provision of a 32.4 million EUR loan to Burgas Water Supply and Sanitation Operator (“Burgas WSSO”), which is aimed at the co-financing of investments in the infrastructure Burgas WSSO is a state-owned company and sole provider of water supply, wastewater collection and treatment services in the Burgas region; (ii) The recent (March 2021) approval of an investment of over €63 million EUR from the Cohesion Fund to provide better access to drinking water and improved sewerage for the people living in the district of Burgas.

In the scope of the AI4PublibPolicy pilot, EKSO and BURGAS will collaborate in the development of a policy making tool that will create and evaluating alternative water pipes maintenance plans, based on data-driven insights about the water management infrastructure (e.g., information about pipes’ installation, placement, and maintenance) and its operative condition (i.e., leveraging EKSO pipes). The pilot will build and validate policy models that will estimate the potential leakages and maintenance cost, while helping the municipality establish effective maintenance and repair schedules/policies. Specifically, the VPME will be used to assist employees of the municipality and the WSSO in evaluating different maintenance and service policy scenarios, which are associated different maintenance schedules and costs. The project’s tools will recommend, simulate and benchmark policies associated with the development of maintenance, service and repair schedules for water pipes.

The following use cases will be evaluated:

  • Data-Driven Maintenance Costs and Sustainability Analysis for Water Pipes: Leveraging data about the water management networks (i.e. pipes installation & placement) different maintenance schedules will be analyzed from a financial perspective, including service, repair and maintenance costs for the pipes that comprise the water infrastructure. In this direction, specific segments of the infrastructure may be selected for analysis in the scope of the project. Furthermore, alternative maintenance schedules will be analyzed in terms of their cost and environmental impact, towards recommending and selecting the best possible scenarios;
  • Condition-based Monitoring and LCA for Maintenance and Repair policies: This use case will extend the previous one with condition-based monitoring data for water pipes, towards extending their lifecycle and improving maintenance schedule. In this direction, the data-driven analysis will be extended with sensor-data derived by EKSO pipes. The analysis will blend information from the previous use cases with lab based data from EKSO with a view to evaluating the added-value of smart pipes and condition-based maintenance for policy making. Each of the use cases will consider citizens’ feedback and satisfaction about specific maintenance plans, which will be collected through on-line surveys.

The following KPIs will be tracked:

  • Cost Optimization/Savings;
  • Sustainability Improvement (including reduced water losses);
  • Citizens’ satisfaction.

No Comments

Sorry, the comment form is closed at this time.